commit 9005105e5244b107e5a0c2a0653d2db37609cf1e Author: Christian Schabesberger Date: Wed Mar 1 18:47:52 2017 +0100 initial commit diff --git a/AbstractStreamInfo.java b/AbstractStreamInfo.java new file mode 100644 index 000000000..bfa86b3f7 --- /dev/null +++ b/AbstractStreamInfo.java @@ -0,0 +1,41 @@ +package org.schabi.newpipe.extractor; + +/** + * Copyright (C) Christian Schabesberger 2016 + * AbstractStreamInfo.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +/**Common properties between StreamInfo and StreamInfoItem.*/ +public abstract class AbstractStreamInfo { + public enum StreamType { + NONE, // placeholder to check if stream type was checked or not + VIDEO_STREAM, + AUDIO_STREAM, + LIVE_STREAM, + AUDIO_LIVE_STREAM, + FILE + } + + public StreamType stream_type; + public int service_id = -1; + public String id = ""; + public String title = ""; + public String uploader = ""; + public String thumbnail_url = ""; + public String webpage_url = ""; + public String upload_date = ""; + public long view_count = -1; +} diff --git a/DashMpdParser.java b/DashMpdParser.java new file mode 100644 index 000000000..527750a86 --- /dev/null +++ b/DashMpdParser.java @@ -0,0 +1,93 @@ +package org.schabi.newpipe.extractor; + +import org.schabi.newpipe.extractor.exceptions.ParsingException; +import org.schabi.newpipe.extractor.exceptions.ReCaptchaException; +import org.schabi.newpipe.extractor.stream_info.AudioStream; +import org.w3c.dom.Document; +import org.w3c.dom.Element; +import org.w3c.dom.NodeList; + +import java.io.ByteArrayInputStream; +import java.io.IOException; +import java.io.InputStream; +import java.util.List; +import java.util.Vector; + +import javax.xml.parsers.DocumentBuilder; +import javax.xml.parsers.DocumentBuilderFactory; + +/** + * Created by Christian Schabesberger on 02.02.16. + * + * Copyright (C) Christian Schabesberger 2016 + * DashMpdParser.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class DashMpdParser { + + private DashMpdParser() { + } + + static class DashMpdParsingException extends ParsingException { + DashMpdParsingException(String message, Exception e) { + super(message, e); + } + } + + public static List getAudioStreams(String dashManifestUrl) + throws DashMpdParsingException, ReCaptchaException { + String dashDoc; + Downloader downloader = NewPipe.getDownloader(); + try { + dashDoc = downloader.download(dashManifestUrl); + } catch(IOException ioe) { + throw new DashMpdParsingException("Could not get dash mpd: " + dashManifestUrl, ioe); + } catch (ReCaptchaException e) { + throw new ReCaptchaException("reCaptcha Challenge needed"); + } + Vector audioStreams = new Vector<>(); + + try { + DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance(); + DocumentBuilder builder = factory.newDocumentBuilder(); + InputStream stream = new ByteArrayInputStream(dashDoc.getBytes()); + + Document doc = builder.parse(stream); + NodeList adaptationSetList = doc.getElementsByTagName("AdaptationSet"); + for(int i = 0; i < adaptationSetList.getLength(); i++) { + Element adaptationSet = (Element) adaptationSetList.item(i); + String memeType = adaptationSet.getAttribute("mimeType"); + if(memeType.contains("audio")) { + Element representation = (Element) adaptationSet.getElementsByTagName("Representation").item(0); + String url = representation.getElementsByTagName("BaseURL").item(0).getTextContent(); + int bandwidth = Integer.parseInt(representation.getAttribute("bandwidth")); + int samplingRate = Integer.parseInt(representation.getAttribute("audioSamplingRate")); + int format = -1; + if(memeType.equals(MediaFormat.WEBMA.mimeType)) { + format = MediaFormat.WEBMA.id; + } else if(memeType.equals(MediaFormat.M4A.mimeType)) { + format = MediaFormat.M4A.id; + } + audioStreams.add(new AudioStream(url, format, bandwidth, samplingRate)); + } + } + } + catch(Exception e) { + throw new DashMpdParsingException("Could not parse Dash mpd", e); + } + return audioStreams; + } +} diff --git a/Downloader.java b/Downloader.java new file mode 100644 index 000000000..fe85696b5 --- /dev/null +++ b/Downloader.java @@ -0,0 +1,52 @@ +package org.schabi.newpipe.extractor; + +import org.schabi.newpipe.extractor.exceptions.ReCaptchaException; + +import java.io.IOException; +import java.util.Map; + +/** + * Created by Christian Schabesberger on 28.01.16. + * + * Copyright (C) Christian Schabesberger 2016 + * Downloader.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public interface Downloader { + + /**Download the text file at the supplied URL as in download(String), + * but set the HTTP header field "Accept-Language" to the supplied string. + * @param siteUrl the URL of the text file to return the contents of + * @param language the language (usually a 2-character code) to set as the preferred language + * @return the contents of the specified text file + * @throws IOException*/ + String download(String siteUrl, String language) throws IOException, ReCaptchaException; + + /**Download the text file at the supplied URL as in download(String), + * but set the HTTP header field "Accept-Language" to the supplied string. + * @param siteUrl the URL of the text file to return the contents of + * @param customProperties set request header properties + * @return the contents of the specified text file + * @throws IOException*/ + String download(String siteUrl, Map customProperties) throws IOException, ReCaptchaException; + + /**Download (via HTTP) the text file located at the supplied URL, and return its contents. + * Primarily intended for downloading web pages. + * @param siteUrl the URL of the text file to download + * @return the contents of the specified text file + * @throws IOException*/ + String download(String siteUrl) throws IOException, ReCaptchaException; +} diff --git a/InfoItem.java b/InfoItem.java new file mode 100644 index 000000000..a3395e8e4 --- /dev/null +++ b/InfoItem.java @@ -0,0 +1,33 @@ +package org.schabi.newpipe.extractor; + +/** + * Created by the-scrabi on 11.02.17. + * + * Copyright (C) Christian Schabesberger 2017 + * InfoItem.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public interface InfoItem { + public enum InfoType { + STREAM, + PLAYLIST, + CHANNEL + } + + InfoType infoType(); + String getTitle(); + String getLink(); +} diff --git a/InfoItemCollector.java b/InfoItemCollector.java new file mode 100644 index 000000000..d3b0927a1 --- /dev/null +++ b/InfoItemCollector.java @@ -0,0 +1,61 @@ +package org.schabi.newpipe.extractor; + +import org.schabi.newpipe.extractor.exceptions.ExtractionException; + +import java.util.List; +import java.util.Vector; + +/** + * Created by Christian Schabesberger on 12.02.17. + * + * Copyright (C) Christian Schabesberger 2017 + * InfoItemCollector.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class InfoItemCollector { + private List itemList = new Vector<>(); + private List errors = new Vector<>(); + private int serviceId = -1; + + public InfoItemCollector(int serviceId) { + this.serviceId = serviceId; + } + + public List getItemList() { + return itemList; + } + public List getErrors() { + return errors; + } + protected void addFromCollector(InfoItemCollector otherC) throws ExtractionException { + if(serviceId != otherC.serviceId) { + throw new ExtractionException("Service Id does not equal: " + + NewPipe.getNameOfService(serviceId) + + " and " + NewPipe.getNameOfService(otherC.serviceId)); + } + errors.addAll(otherC.errors); + itemList.addAll(otherC.itemList); + } + protected void addError(Exception e) { + errors.add(e); + } + protected void addItem(InfoItem item) { + itemList.add(item); + } + protected int getServiceId() { + return serviceId; + } +} diff --git a/LICENSE b/LICENSE new file mode 100644 index 000000000..94a9ed024 --- /dev/null +++ b/LICENSE @@ -0,0 +1,674 @@ + GNU GENERAL PUBLIC LICENSE + Version 3, 29 June 2007 + + Copyright (C) 2007 Free Software Foundation, Inc. + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The GNU General Public License is a free, copyleft license for +software and other kinds of works. + + The licenses for most software and other practical works are designed +to take away your freedom to share and change the works. By contrast, +the GNU General Public License is intended to guarantee your freedom to +share and change all versions of a program--to make sure it remains free +software for all its users. We, the Free Software Foundation, use the +GNU General Public License for most of our software; it applies also to +any other work released this way by its authors. You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +them if you wish), that you receive source code or can get it if you +want it, that you can change the software or use pieces of it in new +free programs, and that you know you can do these things. + + To protect your rights, we need to prevent others from denying you +these rights or asking you to surrender the rights. Therefore, you have +certain responsibilities if you distribute copies of the software, or if +you modify it: responsibilities to respect the freedom of others. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must pass on to the recipients the same +freedoms that you received. You must make sure that they, too, receive +or can get the source code. And you must show them these terms so they +know their rights. + + Developers that use the GNU GPL protect your rights with two steps: +(1) assert copyright on the software, and (2) offer you this License +giving you legal permission to copy, distribute and/or modify it. + + For the developers' and authors' protection, the GPL clearly explains +that there is no warranty for this free software. For both users' and +authors' sake, the GPL requires that modified versions be marked as +changed, so that their problems will not be attributed erroneously to +authors of previous versions. + + Some devices are designed to deny users access to install or run +modified versions of the software inside them, although the manufacturer +can do so. This is fundamentally incompatible with the aim of +protecting users' freedom to change the software. The systematic +pattern of such abuse occurs in the area of products for individuals to +use, which is precisely where it is most unacceptable. Therefore, we +have designed this version of the GPL to prohibit the practice for those +products. If such problems arise substantially in other domains, we +stand ready to extend this provision to those domains in future versions +of the GPL, as needed to protect the freedom of users. + + Finally, every program is threatened constantly by software patents. +States should not allow patents to restrict development and use of +software on general-purpose computers, but in those that do, we wish to +avoid the special danger that patents applied to a free program could +make it effectively proprietary. To prevent this, the GPL assures that +patents cannot be used to render the program non-free. + + The precise terms and conditions for copying, distribution and +modification follow. + + TERMS AND CONDITIONS + + 0. Definitions. + + "This License" refers to version 3 of the GNU General Public License. + + "Copyright" also means copyright-like laws that apply to other kinds of +works, such as semiconductor masks. + + "The Program" refers to any copyrightable work licensed under this +License. Each licensee is addressed as "you". "Licensees" and +"recipients" may be individuals or organizations. + + To "modify" a work means to copy from or adapt all or part of the work +in a fashion requiring copyright permission, other than the making of an +exact copy. The resulting work is called a "modified version" of the +earlier work or a work "based on" the earlier work. + + A "covered work" means either the unmodified Program or a work based +on the Program. + + To "propagate" a work means to do anything with it that, without +permission, would make you directly or secondarily liable for +infringement under applicable copyright law, except executing it on a +computer or modifying a private copy. Propagation includes copying, +distribution (with or without modification), making available to the +public, and in some countries other activities as well. + + To "convey" a work means any kind of propagation that enables other +parties to make or receive copies. Mere interaction with a user through +a computer network, with no transfer of a copy, is not conveying. + + An interactive user interface displays "Appropriate Legal Notices" +to the extent that it includes a convenient and prominently visible +feature that (1) displays an appropriate copyright notice, and (2) +tells the user that there is no warranty for the work (except to the +extent that warranties are provided), that licensees may convey the +work under this License, and how to view a copy of this License. If +the interface presents a list of user commands or options, such as a +menu, a prominent item in the list meets this criterion. + + 1. Source Code. + + The "source code" for a work means the preferred form of the work +for making modifications to it. "Object code" means any non-source +form of a work. + + A "Standard Interface" means an interface that either is an official +standard defined by a recognized standards body, or, in the case of +interfaces specified for a particular programming language, one that +is widely used among developers working in that language. + + The "System Libraries" of an executable work include anything, other +than the work as a whole, that (a) is included in the normal form of +packaging a Major Component, but which is not part of that Major +Component, and (b) serves only to enable use of the work with that +Major Component, or to implement a Standard Interface for which an +implementation is available to the public in source code form. A +"Major Component", in this context, means a major essential component +(kernel, window system, and so on) of the specific operating system +(if any) on which the executable work runs, or a compiler used to +produce the work, or an object code interpreter used to run it. + + The "Corresponding Source" for a work in object code form means all +the source code needed to generate, install, and (for an executable +work) run the object code and to modify the work, including scripts to +control those activities. However, it does not include the work's +System Libraries, or general-purpose tools or generally available free +programs which are used unmodified in performing those activities but +which are not part of the work. For example, Corresponding Source +includes interface definition files associated with source files for +the work, and the source code for shared libraries and dynamically +linked subprograms that the work is specifically designed to require, +such as by intimate data communication or control flow between those +subprograms and other parts of the work. + + The Corresponding Source need not include anything that users +can regenerate automatically from other parts of the Corresponding +Source. + + The Corresponding Source for a work in source code form is that +same work. + + 2. Basic Permissions. + + All rights granted under this License are granted for the term of +copyright on the Program, and are irrevocable provided the stated +conditions are met. This License explicitly affirms your unlimited +permission to run the unmodified Program. The output from running a +covered work is covered by this License only if the output, given its +content, constitutes a covered work. This License acknowledges your +rights of fair use or other equivalent, as provided by copyright law. + + You may make, run and propagate covered works that you do not +convey, without conditions so long as your license otherwise remains +in force. You may convey covered works to others for the sole purpose +of having them make modifications exclusively for you, or provide you +with facilities for running those works, provided that you comply with +the terms of this License in conveying all material for which you do +not control copyright. Those thus making or running the covered works +for you must do so exclusively on your behalf, under your direction +and control, on terms that prohibit them from making any copies of +your copyrighted material outside their relationship with you. + + Conveying under any other circumstances is permitted solely under +the conditions stated below. Sublicensing is not allowed; section 10 +makes it unnecessary. + + 3. Protecting Users' Legal Rights From Anti-Circumvention Law. + + No covered work shall be deemed part of an effective technological +measure under any applicable law fulfilling obligations under article +11 of the WIPO copyright treaty adopted on 20 December 1996, or +similar laws prohibiting or restricting circumvention of such +measures. + + When you convey a covered work, you waive any legal power to forbid +circumvention of technological measures to the extent such circumvention +is effected by exercising rights under this License with respect to +the covered work, and you disclaim any intention to limit operation or +modification of the work as a means of enforcing, against the work's +users, your or third parties' legal rights to forbid circumvention of +technological measures. + + 4. Conveying Verbatim Copies. + + You may convey verbatim copies of the Program's source code as you +receive it, in any medium, provided that you conspicuously and +appropriately publish on each copy an appropriate copyright notice; +keep intact all notices stating that this License and any +non-permissive terms added in accord with section 7 apply to the code; +keep intact all notices of the absence of any warranty; and give all +recipients a copy of this License along with the Program. + + You may charge any price or no price for each copy that you convey, +and you may offer support or warranty protection for a fee. + + 5. Conveying Modified Source Versions. + + You may convey a work based on the Program, or the modifications to +produce it from the Program, in the form of source code under the +terms of section 4, provided that you also meet all of these conditions: + + a) The work must carry prominent notices stating that you modified + it, and giving a relevant date. + + b) The work must carry prominent notices stating that it is + released under this License and any conditions added under section + 7. This requirement modifies the requirement in section 4 to + "keep intact all notices". + + c) You must license the entire work, as a whole, under this + License to anyone who comes into possession of a copy. This + License will therefore apply, along with any applicable section 7 + additional terms, to the whole of the work, and all its parts, + regardless of how they are packaged. This License gives no + permission to license the work in any other way, but it does not + invalidate such permission if you have separately received it. + + d) If the work has interactive user interfaces, each must display + Appropriate Legal Notices; however, if the Program has interactive + interfaces that do not display Appropriate Legal Notices, your + work need not make them do so. + + A compilation of a covered work with other separate and independent +works, which are not by their nature extensions of the covered work, +and which are not combined with it such as to form a larger program, +in or on a volume of a storage or distribution medium, is called an +"aggregate" if the compilation and its resulting copyright are not +used to limit the access or legal rights of the compilation's users +beyond what the individual works permit. Inclusion of a covered work +in an aggregate does not cause this License to apply to the other +parts of the aggregate. + + 6. Conveying Non-Source Forms. + + You may convey a covered work in object code form under the terms +of sections 4 and 5, provided that you also convey the +machine-readable Corresponding Source under the terms of this License, +in one of these ways: + + a) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by the + Corresponding Source fixed on a durable physical medium + customarily used for software interchange. + + b) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by a + written offer, valid for at least three years and valid for as + long as you offer spare parts or customer support for that product + model, to give anyone who possesses the object code either (1) a + copy of the Corresponding Source for all the software in the + product that is covered by this License, on a durable physical + medium customarily used for software interchange, for a price no + more than your reasonable cost of physically performing this + conveying of source, or (2) access to copy the + Corresponding Source from a network server at no charge. + + c) Convey individual copies of the object code with a copy of the + written offer to provide the Corresponding Source. This + alternative is allowed only occasionally and noncommercially, and + only if you received the object code with such an offer, in accord + with subsection 6b. + + d) Convey the object code by offering access from a designated + place (gratis or for a charge), and offer equivalent access to the + Corresponding Source in the same way through the same place at no + further charge. You need not require recipients to copy the + Corresponding Source along with the object code. If the place to + copy the object code is a network server, the Corresponding Source + may be on a different server (operated by you or a third party) + that supports equivalent copying facilities, provided you maintain + clear directions next to the object code saying where to find the + Corresponding Source. Regardless of what server hosts the + Corresponding Source, you remain obligated to ensure that it is + available for as long as needed to satisfy these requirements. + + e) Convey the object code using peer-to-peer transmission, provided + you inform other peers where the object code and Corresponding + Source of the work are being offered to the general public at no + charge under subsection 6d. + + A separable portion of the object code, whose source code is excluded +from the Corresponding Source as a System Library, need not be +included in conveying the object code work. + + A "User Product" is either (1) a "consumer product", which means any +tangible personal property which is normally used for personal, family, +or household purposes, or (2) anything designed or sold for incorporation +into a dwelling. In determining whether a product is a consumer product, +doubtful cases shall be resolved in favor of coverage. For a particular +product received by a particular user, "normally used" refers to a +typical or common use of that class of product, regardless of the status +of the particular user or of the way in which the particular user +actually uses, or expects or is expected to use, the product. A product +is a consumer product regardless of whether the product has substantial +commercial, industrial or non-consumer uses, unless such uses represent +the only significant mode of use of the product. + + "Installation Information" for a User Product means any methods, +procedures, authorization keys, or other information required to install +and execute modified versions of a covered work in that User Product from +a modified version of its Corresponding Source. The information must +suffice to ensure that the continued functioning of the modified object +code is in no case prevented or interfered with solely because +modification has been made. + + If you convey an object code work under this section in, or with, or +specifically for use in, a User Product, and the conveying occurs as +part of a transaction in which the right of possession and use of the +User Product is transferred to the recipient in perpetuity or for a +fixed term (regardless of how the transaction is characterized), the +Corresponding Source conveyed under this section must be accompanied +by the Installation Information. But this requirement does not apply +if neither you nor any third party retains the ability to install +modified object code on the User Product (for example, the work has +been installed in ROM). + + The requirement to provide Installation Information does not include a +requirement to continue to provide support service, warranty, or updates +for a work that has been modified or installed by the recipient, or for +the User Product in which it has been modified or installed. Access to a +network may be denied when the modification itself materially and +adversely affects the operation of the network or violates the rules and +protocols for communication across the network. + + Corresponding Source conveyed, and Installation Information provided, +in accord with this section must be in a format that is publicly +documented (and with an implementation available to the public in +source code form), and must require no special password or key for +unpacking, reading or copying. + + 7. Additional Terms. + + "Additional permissions" are terms that supplement the terms of this +License by making exceptions from one or more of its conditions. +Additional permissions that are applicable to the entire Program shall +be treated as though they were included in this License, to the extent +that they are valid under applicable law. If additional permissions +apply only to part of the Program, that part may be used separately +under those permissions, but the entire Program remains governed by +this License without regard to the additional permissions. + + When you convey a copy of a covered work, you may at your option +remove any additional permissions from that copy, or from any part of +it. (Additional permissions may be written to require their own +removal in certain cases when you modify the work.) You may place +additional permissions on material, added by you to a covered work, +for which you have or can give appropriate copyright permission. + + Notwithstanding any other provision of this License, for material you +add to a covered work, you may (if authorized by the copyright holders of +that material) supplement the terms of this License with terms: + + a) Disclaiming warranty or limiting liability differently from the + terms of sections 15 and 16 of this License; or + + b) Requiring preservation of specified reasonable legal notices or + author attributions in that material or in the Appropriate Legal + Notices displayed by works containing it; or + + c) Prohibiting misrepresentation of the origin of that material, or + requiring that modified versions of such material be marked in + reasonable ways as different from the original version; or + + d) Limiting the use for publicity purposes of names of licensors or + authors of the material; or + + e) Declining to grant rights under trademark law for use of some + trade names, trademarks, or service marks; or + + f) Requiring indemnification of licensors and authors of that + material by anyone who conveys the material (or modified versions of + it) with contractual assumptions of liability to the recipient, for + any liability that these contractual assumptions directly impose on + those licensors and authors. + + All other non-permissive additional terms are considered "further +restrictions" within the meaning of section 10. If the Program as you +received it, or any part of it, contains a notice stating that it is +governed by this License along with a term that is a further +restriction, you may remove that term. If a license document contains +a further restriction but permits relicensing or conveying under this +License, you may add to a covered work material governed by the terms +of that license document, provided that the further restriction does +not survive such relicensing or conveying. + + If you add terms to a covered work in accord with this section, you +must place, in the relevant source files, a statement of the +additional terms that apply to those files, or a notice indicating +where to find the applicable terms. + + Additional terms, permissive or non-permissive, may be stated in the +form of a separately written license, or stated as exceptions; +the above requirements apply either way. + + 8. Termination. + + You may not propagate or modify a covered work except as expressly +provided under this License. Any attempt otherwise to propagate or +modify it is void, and will automatically terminate your rights under +this License (including any patent licenses granted under the third +paragraph of section 11). + + However, if you cease all violation of this License, then your +license from a particular copyright holder is reinstated (a) +provisionally, unless and until the copyright holder explicitly and +finally terminates your license, and (b) permanently, if the copyright +holder fails to notify you of the violation by some reasonable means +prior to 60 days after the cessation. + + Moreover, your license from a particular copyright holder is +reinstated permanently if the copyright holder notifies you of the +violation by some reasonable means, this is the first time you have +received notice of violation of this License (for any work) from that +copyright holder, and you cure the violation prior to 30 days after +your receipt of the notice. + + Termination of your rights under this section does not terminate the +licenses of parties who have received copies or rights from you under +this License. If your rights have been terminated and not permanently +reinstated, you do not qualify to receive new licenses for the same +material under section 10. + + 9. Acceptance Not Required for Having Copies. + + You are not required to accept this License in order to receive or +run a copy of the Program. Ancillary propagation of a covered work +occurring solely as a consequence of using peer-to-peer transmission +to receive a copy likewise does not require acceptance. However, +nothing other than this License grants you permission to propagate or +modify any covered work. These actions infringe copyright if you do +not accept this License. Therefore, by modifying or propagating a +covered work, you indicate your acceptance of this License to do so. + + 10. Automatic Licensing of Downstream Recipients. + + Each time you convey a covered work, the recipient automatically +receives a license from the original licensors, to run, modify and +propagate that work, subject to this License. You are not responsible +for enforcing compliance by third parties with this License. + + An "entity transaction" is a transaction transferring control of an +organization, or substantially all assets of one, or subdividing an +organization, or merging organizations. If propagation of a covered +work results from an entity transaction, each party to that +transaction who receives a copy of the work also receives whatever +licenses to the work the party's predecessor in interest had or could +give under the previous paragraph, plus a right to possession of the +Corresponding Source of the work from the predecessor in interest, if +the predecessor has it or can get it with reasonable efforts. + + You may not impose any further restrictions on the exercise of the +rights granted or affirmed under this License. For example, you may +not impose a license fee, royalty, or other charge for exercise of +rights granted under this License, and you may not initiate litigation +(including a cross-claim or counterclaim in a lawsuit) alleging that +any patent claim is infringed by making, using, selling, offering for +sale, or importing the Program or any portion of it. + + 11. Patents. + + A "contributor" is a copyright holder who authorizes use under this +License of the Program or a work on which the Program is based. The +work thus licensed is called the contributor's "contributor version". + + A contributor's "essential patent claims" are all patent claims +owned or controlled by the contributor, whether already acquired or +hereafter acquired, that would be infringed by some manner, permitted +by this License, of making, using, or selling its contributor version, +but do not include claims that would be infringed only as a +consequence of further modification of the contributor version. For +purposes of this definition, "control" includes the right to grant +patent sublicenses in a manner consistent with the requirements of +this License. + + Each contributor grants you a non-exclusive, worldwide, royalty-free +patent license under the contributor's essential patent claims, to +make, use, sell, offer for sale, import and otherwise run, modify and +propagate the contents of its contributor version. + + In the following three paragraphs, a "patent license" is any express +agreement or commitment, however denominated, not to enforce a patent +(such as an express permission to practice a patent or covenant not to +sue for patent infringement). To "grant" such a patent license to a +party means to make such an agreement or commitment not to enforce a +patent against the party. + + If you convey a covered work, knowingly relying on a patent license, +and the Corresponding Source of the work is not available for anyone +to copy, free of charge and under the terms of this License, through a +publicly available network server or other readily accessible means, +then you must either (1) cause the Corresponding Source to be so +available, or (2) arrange to deprive yourself of the benefit of the +patent license for this particular work, or (3) arrange, in a manner +consistent with the requirements of this License, to extend the patent +license to downstream recipients. "Knowingly relying" means you have +actual knowledge that, but for the patent license, your conveying the +covered work in a country, or your recipient's use of the covered work +in a country, would infringe one or more identifiable patents in that +country that you have reason to believe are valid. + + If, pursuant to or in connection with a single transaction or +arrangement, you convey, or propagate by procuring conveyance of, a +covered work, and grant a patent license to some of the parties +receiving the covered work authorizing them to use, propagate, modify +or convey a specific copy of the covered work, then the patent license +you grant is automatically extended to all recipients of the covered +work and works based on it. + + A patent license is "discriminatory" if it does not include within +the scope of its coverage, prohibits the exercise of, or is +conditioned on the non-exercise of one or more of the rights that are +specifically granted under this License. You may not convey a covered +work if you are a party to an arrangement with a third party that is +in the business of distributing software, under which you make payment +to the third party based on the extent of your activity of conveying +the work, and under which the third party grants, to any of the +parties who would receive the covered work from you, a discriminatory +patent license (a) in connection with copies of the covered work +conveyed by you (or copies made from those copies), or (b) primarily +for and in connection with specific products or compilations that +contain the covered work, unless you entered into that arrangement, +or that patent license was granted, prior to 28 March 2007. + + Nothing in this License shall be construed as excluding or limiting +any implied license or other defenses to infringement that may +otherwise be available to you under applicable patent law. + + 12. No Surrender of Others' Freedom. + + If conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot convey a +covered work so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you may +not convey it at all. For example, if you agree to terms that obligate you +to collect a royalty for further conveying from those to whom you convey +the Program, the only way you could satisfy both those terms and this +License would be to refrain entirely from conveying the Program. + + 13. Use with the GNU Affero General Public License. + + Notwithstanding any other provision of this License, you have +permission to link or combine any covered work with a work licensed +under version 3 of the GNU Affero General Public License into a single +combined work, and to convey the resulting work. The terms of this +License will continue to apply to the part which is the covered work, +but the special requirements of the GNU Affero General Public License, +section 13, concerning interaction through a network will apply to the +combination as such. + + 14. Revised Versions of this License. + + The Free Software Foundation may publish revised and/or new versions of +the GNU General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + + Each version is given a distinguishing version number. If the +Program specifies that a certain numbered version of the GNU General +Public License "or any later version" applies to it, you have the +option of following the terms and conditions either of that numbered +version or of any later version published by the Free Software +Foundation. If the Program does not specify a version number of the +GNU General Public License, you may choose any version ever published +by the Free Software Foundation. + + If the Program specifies that a proxy can decide which future +versions of the GNU General Public License can be used, that proxy's +public statement of acceptance of a version permanently authorizes you +to choose that version for the Program. + + Later license versions may give you additional or different +permissions. However, no additional obligations are imposed on any +author or copyright holder as a result of your choosing to follow a +later version. + + 15. Disclaimer of Warranty. + + THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY +APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT +HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY +OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, +THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR +PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM +IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF +ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + + 16. Limitation of Liability. + + IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS +THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY +GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE +USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF +DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD +PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), +EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF +SUCH DAMAGES. + + 17. Interpretation of Sections 15 and 16. + + If the disclaimer of warranty and limitation of liability provided +above cannot be given local legal effect according to their terms, +reviewing courts shall apply local law that most closely approximates +an absolute waiver of all civil liability in connection with the +Program, unless a warranty or assumption of liability accompanies a +copy of the Program in return for a fee. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +state the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + + Copyright (C) + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . + +Also add information on how to contact you by electronic and paper mail. + + If the program does terminal interaction, make it output a short +notice like this when it starts in an interactive mode: + + Copyright (C) + This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, your program's commands +might be different; for a GUI interface, you would use an "about box". + + You should also get your employer (if you work as a programmer) or school, +if any, to sign a "copyright disclaimer" for the program, if necessary. +For more information on this, and how to apply and follow the GNU GPL, see +. + + The GNU General Public License does not permit incorporating your program +into proprietary programs. If your program is a subroutine library, you +may consider it more useful to permit linking proprietary applications with +the library. If this is what you want to do, use the GNU Lesser General +Public License instead of this License. But first, please read +. diff --git a/MediaFormat.java b/MediaFormat.java new file mode 100644 index 000000000..1455fe396 --- /dev/null +++ b/MediaFormat.java @@ -0,0 +1,83 @@ +package org.schabi.newpipe.extractor; + +/** + * Created by Adam Howard on 08/11/15. + * + * Copyright (c) Christian Schabesberger + * and Adam Howard 2015 + * + * MediaFormat.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +/**Static data about various media formats support by Newpipe, eg mime type, extension*/ + +public enum MediaFormat { + //video and audio combined formats + // id name suffix mime type + MPEG_4 (0x0, "MPEG-4", "mp4", "video/mp4"), + v3GPP (0x1, "3GPP", "3gp", "video/3gpp"), + WEBM (0x2, "WebM", "webm", "video/webm"), + // audio formats + M4A (0x3, "m4a", "m4a", "audio/mp4"), + WEBMA (0x4, "WebM", "webm", "audio/webm"); + + public final int id; + @SuppressWarnings("WeakerAccess") + public final String name; + @SuppressWarnings("WeakerAccess") + public final String suffix; + public final String mimeType; + + MediaFormat(int id, String name, String suffix, String mimeType) { + this.id = id; + this.name = name; + this.suffix = suffix; + this.mimeType = mimeType; + } + + /**Return the friendly name of the media format with the supplied id + * @param ident the id of the media format. Currently an arbitrary, NewPipe-specific number. + * @return the friendly name of the MediaFormat associated with this ids, + * or an empty String if none match it.*/ + public static String getNameById(int ident) { + for (MediaFormat vf : MediaFormat.values()) { + if(vf.id == ident) return vf.name; + } + return ""; + } + + /**Return the file extension of the media format with the supplied id + * @param ident the id of the media format. Currently an arbitrary, NewPipe-specific number. + * @return the file extension of the MediaFormat associated with this ids, + * or an empty String if none match it.*/ + public static String getSuffixById(int ident) { + for (MediaFormat vf : MediaFormat.values()) { + if(vf.id == ident) return vf.suffix; + } + return ""; + } + + /**Return the MIME type of the media format with the supplied id + * @param ident the id of the media format. Currently an arbitrary, NewPipe-specific number. + * @return the MIME type of the MediaFormat associated with this ids, + * or an empty String if none match it.*/ + public static String getMimeById(int ident) { + for (MediaFormat vf : MediaFormat.values()) { + if(vf.id == ident) return vf.mimeType; + } + return ""; + } +} diff --git a/NewPipe.java b/NewPipe.java new file mode 100644 index 000000000..4e8e4aa3d --- /dev/null +++ b/NewPipe.java @@ -0,0 +1,88 @@ +package org.schabi.newpipe.extractor; + +import org.schabi.newpipe.extractor.exceptions.ExtractionException; +import org.schabi.newpipe.extractor.services.youtube.YoutubeService; + +/** + * Created by Christian Schabesberger on 23.08.15. + * + * Copyright (C) Christian Schabesberger 2015 + * NewPipe.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +/**Provides access to the video streaming services supported by NewPipe. + * Currently only Youtube until the API becomes more stable.*/ + +@SuppressWarnings("ALL") +public class NewPipe { + + private NewPipe() { + } + + private static final String TAG = NewPipe.class.toString(); + + + private static Downloader downloader = null; + + public static StreamingService[] getServices() { + return ServiceList.serviceList; + } + public static StreamingService getService(int serviceId)throws ExtractionException { + for(StreamingService s : ServiceList.serviceList) { + if(s.getServiceId() == serviceId) { + return s; + } + } + return null; + } + public static StreamingService getService(String serviceName) throws ExtractionException { + return ServiceList.serviceList[getIdOfService(serviceName)]; + } + public static String getNameOfService(int id) { + try { + return getService(id).getServiceInfo().name; + } catch (Exception e) { + System.err.println("Service id not known"); + e.printStackTrace(); + return ""; + } + } + public static int getIdOfService(String serviceName) { + for(int i = 0; i < ServiceList.serviceList.length; i++) { + if(ServiceList.serviceList[i].getServiceInfo().name.equals(serviceName)) { + return i; + } + } + return -1; + } + + public static void init(Downloader d) { + downloader = d; + } + + public static Downloader getDownloader() { + return downloader; + } + + public static StreamingService getServiceByUrl(String url) { + for(StreamingService s : ServiceList.serviceList) { + if(s.getLinkTypeByUrl(url) != StreamingService.LinkType.NONE) { + return s; + } + } + return null; + } +} diff --git a/Parser.java b/Parser.java new file mode 100644 index 000000000..8e70f751c --- /dev/null +++ b/Parser.java @@ -0,0 +1,77 @@ +package org.schabi.newpipe.extractor; + +import org.schabi.newpipe.extractor.exceptions.ParsingException; + +import java.io.UnsupportedEncodingException; +import java.net.URLDecoder; +import java.util.HashMap; +import java.util.Map; +import java.util.regex.Matcher; +import java.util.regex.Pattern; + +/** + * Created by Christian Schabesberger on 02.02.16. + * + * Copyright (C) Christian Schabesberger 2016 + * Parser.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +/** avoid using regex !!! */ +public class Parser { + + private Parser() { + } + + public static class RegexException extends ParsingException { + public RegexException(String message) { + super(message); + } + } + + public static String matchGroup1(String pattern, String input) throws RegexException { + return matchGroup(pattern, input, 1); + } + + public static String matchGroup(String pattern, String input, int group) throws RegexException { + Pattern pat = Pattern.compile(pattern); + Matcher mat = pat.matcher(input); + boolean foundMatch = mat.find(); + if (foundMatch) { + return mat.group(group); + } + else { + //Log.e(TAG, "failed to find pattern \""+pattern+"\" inside of \""+input+"\""); + if(input.length() > 1024) { + throw new RegexException("failed to find pattern \""+pattern); + } else { + throw new RegexException("failed to find pattern \"" + pattern + " inside of " + input + "\""); + } + } + } + + public static Map compatParseMap(final String input) throws UnsupportedEncodingException { + Map map = new HashMap<>(); + for(String arg : input.split("&")) { + String[] splitArg = arg.split("="); + if(splitArg.length > 1) { + map.put(splitArg[0], URLDecoder.decode(splitArg[1], "UTF-8")); + } else { + map.put(splitArg[0], ""); + } + } + return map; + } +} diff --git a/README.md b/README.md new file mode 100644 index 000000000..92ffdd54d --- /dev/null +++ b/README.md @@ -0,0 +1,5 @@ +NewPipe Extractor +================= + +This is the system independent core of [NewPipe](https://github.com/TeamNewPipe/NewPipe). +It can be used to create your own java based NewPipe client. diff --git a/ServiceList.java b/ServiceList.java new file mode 100644 index 000000000..89b350cb4 --- /dev/null +++ b/ServiceList.java @@ -0,0 +1,13 @@ +package org.schabi.newpipe.extractor; + +import org.schabi.newpipe.extractor.services.youtube.YoutubeService; + +/** + * Created by the-scrabi on 18.02.17. + */ + +class ServiceList { + public static final StreamingService[] serviceList = { + new YoutubeService(0) + }; +} diff --git a/StreamingService.java b/StreamingService.java new file mode 100644 index 000000000..ed3c17bfc --- /dev/null +++ b/StreamingService.java @@ -0,0 +1,78 @@ +package org.schabi.newpipe.extractor; + +import org.schabi.newpipe.extractor.channel.ChannelExtractor; +import org.schabi.newpipe.extractor.exceptions.ExtractionException; +import org.schabi.newpipe.extractor.search.SearchEngine; +import org.schabi.newpipe.extractor.stream_info.StreamExtractor; + +import java.io.IOException; + +/** + * Created by Christian Schabesberger on 23.08.15. + * + * Copyright (C) Christian Schabesberger 2016 + * StreamingService.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public abstract class StreamingService { + public class ServiceInfo { + public String name = ""; + } + + public enum LinkType { + NONE, + STREAM, + CHANNEL, + PLAYLIST + } + + private int serviceId; + + public StreamingService(int id) { + serviceId = id; + } + + public abstract ServiceInfo getServiceInfo(); + + public abstract StreamExtractor getExtractorInstance(String url) + throws IOException, ExtractionException; + public abstract SearchEngine getSearchEngineInstance(); + public abstract UrlIdHandler getStreamUrlIdHandlerInstance(); + public abstract UrlIdHandler getChannelUrlIdHandlerInstance(); + public abstract ChannelExtractor getChannelExtractorInstance(String url, int page) + throws ExtractionException, IOException; + public abstract SuggestionExtractor getSuggestionExtractorInstance(); + + public final int getServiceId() { + return serviceId; + } + + /** + * figure out where the link is pointing to (a channel, video, playlist, etc.) + */ + public final LinkType getLinkTypeByUrl(String url) { + UrlIdHandler sH = getStreamUrlIdHandlerInstance(); + UrlIdHandler cH = getChannelUrlIdHandlerInstance(); + + if(sH.acceptUrl(url)) { + return LinkType.STREAM; + } else if(cH.acceptUrl(url)) { + return LinkType.CHANNEL; + } else { + return LinkType.NONE; + } + } +} diff --git a/SuggestionExtractor.java b/SuggestionExtractor.java new file mode 100644 index 000000000..f198bc5e0 --- /dev/null +++ b/SuggestionExtractor.java @@ -0,0 +1,43 @@ +package org.schabi.newpipe.extractor; + +import org.schabi.newpipe.extractor.exceptions.ExtractionException; + +import java.io.IOException; +import java.util.List; + +/** + * Created by Christian Schabesberger on 28.09.16. + * + * Copyright (C) Christian Schabesberger 2016 + * SuggestionExtractor.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public abstract class SuggestionExtractor { + + private int serviceId; + + public SuggestionExtractor(int serviceId) { + this.serviceId = serviceId; + } + + public abstract List suggestionList( + String query,String contentCountry) + throws ExtractionException, IOException; + + public int getServiceId() { + return serviceId; + } +} diff --git a/UrlIdHandler.java b/UrlIdHandler.java new file mode 100644 index 000000000..1218e7b8c --- /dev/null +++ b/UrlIdHandler.java @@ -0,0 +1,35 @@ +package org.schabi.newpipe.extractor; + +import org.schabi.newpipe.extractor.exceptions.ParsingException; + +/** + * Created by Christian Schabesberger on 26.07.16. + * + * Copyright (C) Christian Schabesberger 2016 + * UrlIdHandler.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public interface UrlIdHandler { + + String getUrl(String videoId); + String getId(String siteUrl) throws ParsingException; + String cleanUrl(String siteUrl) throws ParsingException; + + /**When a VIEW_ACTION is caught this function will test if the url delivered within the calling + Intent was meant to be watched with this Service. + Return false if this service shall not allow to be called through ACTIONs.*/ + boolean acceptUrl(String videoUrl); +} diff --git a/channel/ChannelExtractor.java b/channel/ChannelExtractor.java new file mode 100644 index 000000000..fe7b9f7eb --- /dev/null +++ b/channel/ChannelExtractor.java @@ -0,0 +1,62 @@ +package org.schabi.newpipe.extractor.channel; + +import org.schabi.newpipe.extractor.UrlIdHandler; +import org.schabi.newpipe.extractor.exceptions.ExtractionException; +import org.schabi.newpipe.extractor.exceptions.ParsingException; +import org.schabi.newpipe.extractor.stream_info.StreamInfoItemCollector; + +import java.io.IOException; + +/** + * Created by Christian Schabesberger on 25.07.16. + * + * Copyright (C) Christian Schabesberger 2016 + * ChannelExtractor.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public abstract class ChannelExtractor { + private int serviceId; + private String url; + private UrlIdHandler urlIdHandler; + private StreamInfoItemCollector previewInfoCollector; + private int page = -1; + + public ChannelExtractor(UrlIdHandler urlIdHandler, String url, int page, int serviceId) + throws ExtractionException, IOException { + this.url = url; + this.page = page; + this.serviceId = serviceId; + this.urlIdHandler = urlIdHandler; + previewInfoCollector = new StreamInfoItemCollector(urlIdHandler, serviceId); + } + + public String getUrl() { return url; } + public UrlIdHandler getUrlIdHandler() { return urlIdHandler; } + public StreamInfoItemCollector getStreamPreviewInfoCollector() { + return previewInfoCollector; + } + + public abstract String getChannelName() throws ParsingException; + public abstract String getAvatarUrl() throws ParsingException; + public abstract String getBannerUrl() throws ParsingException; + public abstract String getFeedUrl() throws ParsingException; + public abstract StreamInfoItemCollector getStreams() throws ParsingException; + public abstract long getSubscriberCount() throws ParsingException; + public abstract boolean hasNextPage() throws ParsingException; + public int getServiceId() { + return serviceId; + } +} diff --git a/channel/ChannelInfo.java b/channel/ChannelInfo.java new file mode 100644 index 000000000..e1fd96ada --- /dev/null +++ b/channel/ChannelInfo.java @@ -0,0 +1,86 @@ +package org.schabi.newpipe.extractor.channel; + +import org.schabi.newpipe.extractor.InfoItem; +import org.schabi.newpipe.extractor.exceptions.ParsingException; +import org.schabi.newpipe.extractor.stream_info.StreamInfoItem; +import org.schabi.newpipe.extractor.stream_info.StreamInfoItemCollector; + +import java.util.List; +import java.util.Vector; + +/** + * Created by Christian Schabesberger on 31.07.16. + * + * Copyright (C) Christian Schabesberger 2016 + * ChannelInfo.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class ChannelInfo { + public void addException(Exception e) { + errors.add(e); + } + + public static ChannelInfo getInfo(ChannelExtractor extractor) + throws ParsingException { + ChannelInfo info = new ChannelInfo(); + + // importand data + info.service_id = extractor.getServiceId(); + info.channel_name = extractor.getChannelName(); + info.hasNextPage = extractor.hasNextPage(); + + try { + info.avatar_url = extractor.getAvatarUrl(); + } catch (Exception e) { + info.errors.add(e); + } + try { + info.banner_url = extractor.getBannerUrl(); + } catch (Exception e) { + info.errors.add(e); + } + try { + info.feed_url = extractor.getFeedUrl(); + } catch(Exception e) { + info.errors.add(e); + } + try { + StreamInfoItemCollector c = extractor.getStreams(); + info.related_streams = c.getItemList(); + info.errors.addAll(c.getErrors()); + } catch(Exception e) { + info.errors.add(e); + } + try { + info.subscriberCount = extractor.getSubscriberCount(); + } catch (Exception e) { + info.errors.add(e); + } + + return info; + } + + public int service_id = -1; + public String channel_name = ""; + public String avatar_url = ""; + public String banner_url = ""; + public String feed_url = ""; + public List related_streams = null; + public long subscriberCount = -1; + public boolean hasNextPage = false; + + public List errors = new Vector<>(); +} diff --git a/channel/ChannelInfoItem.java b/channel/ChannelInfoItem.java new file mode 100644 index 000000000..b834d28e6 --- /dev/null +++ b/channel/ChannelInfoItem.java @@ -0,0 +1,44 @@ +package org.schabi.newpipe.extractor.channel; + +import org.schabi.newpipe.extractor.InfoItem; + +/** + * Created by Christian Schabesberger on 11.02.17. + * + * Copyright (C) Christian Schabesberger 2017 + * ChannelInfoItem.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class ChannelInfoItem implements InfoItem { + + public int serviceId = -1; + public String channelName = ""; + public String thumbnailUrl = ""; + public String webPageUrl = ""; + public String description = ""; + public long subscriberCount = -1; + public int videoAmount = -1; + + public InfoType infoType() { + return InfoType.CHANNEL; + } + public String getTitle() { + return channelName; + } + public String getLink() { + return webPageUrl; + } +} diff --git a/channel/ChannelInfoItemCollector.java b/channel/ChannelInfoItemCollector.java new file mode 100644 index 000000000..525820d44 --- /dev/null +++ b/channel/ChannelInfoItemCollector.java @@ -0,0 +1,74 @@ +package org.schabi.newpipe.extractor.channel; + +import org.schabi.newpipe.extractor.InfoItemCollector; +import org.schabi.newpipe.extractor.NewPipe; +import org.schabi.newpipe.extractor.exceptions.FoundAdException; +import org.schabi.newpipe.extractor.exceptions.ParsingException; +import org.schabi.newpipe.extractor.stream_info.StreamInfoItem; +import org.schabi.newpipe.extractor.stream_info.StreamInfoItemExtractor; + +/** + * Created by Christian Schabesberger on 12.02.17. + * + * Copyright (C) Christian Schabesberger 2017 + * ChannelInfoItemCollector.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class ChannelInfoItemCollector extends InfoItemCollector { + public ChannelInfoItemCollector(int serviceId) { + super(serviceId); + } + + public ChannelInfoItem extract(ChannelInfoItemExtractor extractor) throws ParsingException { + ChannelInfoItem resultItem = new ChannelInfoItem(); + // importand information + resultItem.channelName = extractor.getChannelName(); + + resultItem.serviceId = getServiceId(); + resultItem.webPageUrl = extractor.getWebPageUrl(); + + // optional information + try { + resultItem.subscriberCount = extractor.getSubscriberCount(); + } catch (Exception e) { + addError(e); + } + try { + resultItem.videoAmount = extractor.getVideoAmount(); + } catch (Exception e) { + addError(e); + } + try { + resultItem.thumbnailUrl = extractor.getThumbnailUrl(); + } catch (Exception e) { + addError(e); + } + try { + resultItem.description = extractor.getDescription(); + } catch (Exception e) { + addError(e); + } + return resultItem; + } + + public void commit(ChannelInfoItemExtractor extractor) throws ParsingException { + try { + addItem(extract(extractor)); + } catch (Exception e) { + addError(e); + } + } +} diff --git a/channel/ChannelInfoItemExtractor.java b/channel/ChannelInfoItemExtractor.java new file mode 100644 index 000000000..864415cdd --- /dev/null +++ b/channel/ChannelInfoItemExtractor.java @@ -0,0 +1,32 @@ +package org.schabi.newpipe.extractor.channel; + +import org.schabi.newpipe.extractor.exceptions.ParsingException; + +/** + * Created by Christian Schabesberger on 12.02.17. + * + * Copyright (C) Christian Schabesberger 2017 + * ChannelInfoItemExtractor.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public interface ChannelInfoItemExtractor { + String getThumbnailUrl() throws ParsingException; + String getChannelName() throws ParsingException; + String getWebPageUrl() throws ParsingException; + String getDescription() throws ParsingException; + long getSubscriberCount() throws ParsingException; + int getVideoAmount() throws ParsingException; +} diff --git a/copyright b/copyright new file mode 100644 index 000000000..421086567 --- /dev/null +++ b/copyright @@ -0,0 +1,15 @@ +Copyright: 2017 Christian Schabesberger + +License: GPL-3.0+ + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . diff --git a/exceptions/ExtractionException.java b/exceptions/ExtractionException.java new file mode 100644 index 000000000..311850187 --- /dev/null +++ b/exceptions/ExtractionException.java @@ -0,0 +1,33 @@ +package org.schabi.newpipe.extractor.exceptions; + +/** + * Created by Christian Schabesberger on 30.01.16. + * + * Copyright (C) Christian Schabesberger 2016 + * ExtractionException.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class ExtractionException extends Exception { + public ExtractionException(String message) { + super(message); + } + public ExtractionException(Throwable cause) { + super(cause); + } + public ExtractionException(String message, Throwable cause) { + super(message, cause); + } +} \ No newline at end of file diff --git a/exceptions/FoundAdException.java b/exceptions/FoundAdException.java new file mode 100644 index 000000000..4d6d29826 --- /dev/null +++ b/exceptions/FoundAdException.java @@ -0,0 +1,30 @@ +package org.schabi.newpipe.extractor.exceptions; + +/** + * Created by Christian Schabesberger on 12.09.16. + * + * Copyright (C) Christian Schabesberger 2016 + * FoundAdException.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class FoundAdException extends ParsingException { + public FoundAdException(String message) { + super(message); + } + public FoundAdException(String message, Throwable cause) { + super(message, cause); + } +} diff --git a/exceptions/ParsingException.java b/exceptions/ParsingException.java new file mode 100644 index 000000000..41a7acce1 --- /dev/null +++ b/exceptions/ParsingException.java @@ -0,0 +1,31 @@ +package org.schabi.newpipe.extractor.exceptions; + +/** + * Created by Christian Schabesberger on 31.01.16. + * + * Copyright (C) Christian Schabesberger 2016 + * ParsingException.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + + +public class ParsingException extends ExtractionException { + public ParsingException(String message) { + super(message); + } + public ParsingException(String message, Throwable cause) { + super(message, cause); + } +} \ No newline at end of file diff --git a/exceptions/ReCaptchaException.java b/exceptions/ReCaptchaException.java new file mode 100644 index 000000000..a28ec99f9 --- /dev/null +++ b/exceptions/ReCaptchaException.java @@ -0,0 +1,27 @@ +package org.schabi.newpipe.extractor.exceptions; + +/** + * Created by beneth on 07.12.16. + * + * Copyright (C) Christian Schabesberger 2016 + * ReCaptchaException.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class ReCaptchaException extends ExtractionException { + public ReCaptchaException(String message) { + super(message); + } +} diff --git a/search/InfoItemSearchCollector.java b/search/InfoItemSearchCollector.java new file mode 100644 index 000000000..b7ec0e3c1 --- /dev/null +++ b/search/InfoItemSearchCollector.java @@ -0,0 +1,79 @@ +package org.schabi.newpipe.extractor.search; + +import org.schabi.newpipe.extractor.InfoItemCollector; +import org.schabi.newpipe.extractor.UrlIdHandler; +import org.schabi.newpipe.extractor.channel.ChannelInfoItemCollector; +import org.schabi.newpipe.extractor.channel.ChannelInfoItemExtractor; +import org.schabi.newpipe.extractor.exceptions.ExtractionException; +import org.schabi.newpipe.extractor.exceptions.FoundAdException; +import org.schabi.newpipe.extractor.exceptions.ParsingException; +import org.schabi.newpipe.extractor.stream_info.StreamInfoItemCollector; +import org.schabi.newpipe.extractor.stream_info.StreamInfoItemExtractor; + +/** + * Created by Christian Schabesberger on 12.02.17. + * + * Copyright (C) Christian Schabesberger 2017 + * InfoItemSearchCollector.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class InfoItemSearchCollector extends InfoItemCollector { + private String suggestion = ""; + private StreamInfoItemCollector streamCollector; + private ChannelInfoItemCollector channelCollector; + + SearchResult result = new SearchResult(); + + InfoItemSearchCollector(UrlIdHandler handler, int serviceId) { + super(serviceId); + streamCollector = new StreamInfoItemCollector(handler, serviceId); + channelCollector = new ChannelInfoItemCollector(serviceId); + } + + public void setSuggestion(String suggestion) { + this.suggestion = suggestion; + } + + public SearchResult getSearchResult() throws ExtractionException { + + addFromCollector(channelCollector); + addFromCollector(streamCollector); + + result.suggestion = suggestion; + result.errors = getErrors(); + return result; + } + + public void commit(StreamInfoItemExtractor extractor) { + try { + result.resultList.add(streamCollector.extract(extractor)); + } catch(FoundAdException ae) { + System.err.println("Found add"); + } catch (Exception e) { + addError(e); + } + } + + public void commit(ChannelInfoItemExtractor extractor) { + try { + result.resultList.add(channelCollector.extract(extractor)); + } catch(FoundAdException ae) { + System.err.println("Found add"); + } catch (Exception e) { + addError(e); + } + } +} diff --git a/search/SearchEngine.java b/search/SearchEngine.java new file mode 100644 index 000000000..9cef050eb --- /dev/null +++ b/search/SearchEngine.java @@ -0,0 +1,53 @@ +package org.schabi.newpipe.extractor.search; + +import org.schabi.newpipe.extractor.UrlIdHandler; +import org.schabi.newpipe.extractor.exceptions.ExtractionException; +import org.schabi.newpipe.extractor.stream_info.StreamInfoItemCollector; + +import java.io.IOException; +import java.util.EnumSet; + +/** + * Created by Christian Schabesberger on 10.08.15. + * + * Copyright (C) Christian Schabesberger 2015 + * SearchEngine.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public abstract class SearchEngine { + public enum Filter { + STREAM, CHANNEL, PLAY_LIST + } + + public static class NothingFoundException extends ExtractionException { + public NothingFoundException(String message) { + super(message); + } + } + private InfoItemSearchCollector collector; + + public SearchEngine(UrlIdHandler urlIdHandler, int serviceId) { + collector = new InfoItemSearchCollector(urlIdHandler, serviceId); + } + + protected InfoItemSearchCollector getInfoItemSearchCollector() { + return collector; + } + //Result search(String query, int page); + public abstract InfoItemSearchCollector search( + String query, int page, String contentCountry, EnumSet filter) + throws ExtractionException, IOException; +} diff --git a/search/SearchResult.java b/search/SearchResult.java new file mode 100644 index 000000000..155b43747 --- /dev/null +++ b/search/SearchResult.java @@ -0,0 +1,56 @@ +package org.schabi.newpipe.extractor.search; + +import org.schabi.newpipe.extractor.InfoItem; +import org.schabi.newpipe.extractor.exceptions.ExtractionException; +import org.schabi.newpipe.extractor.stream_info.StreamInfoItem; + +import java.io.IOException; +import java.util.EnumSet; +import java.util.List; +import java.util.Vector; + +/** + * Created by Christian Schabesberger on 29.02.16. + * + * Copyright (C) Christian Schabesberger 2016 + * SearchResult.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class SearchResult { + public static SearchResult getSearchResult(SearchEngine engine, String query, + int page, String languageCode, EnumSet filter) + throws ExtractionException, IOException { + + SearchResult result = engine + .search(query, page, languageCode, filter) + .getSearchResult(); + if(result.resultList.isEmpty()) { + if(result.suggestion.isEmpty()) { + if(result.errors.isEmpty()) { + throw new ExtractionException("Empty result despite no error"); + } + } else { + // This is used as a fallback. Do not relay on it !!! + throw new SearchEngine.NothingFoundException(result.suggestion); + } + } + return result; + } + + public String suggestion = ""; + public List resultList = new Vector<>(); + public List errors = new Vector<>(); +} diff --git a/services/youtube/YoutubeChannelExtractor.java b/services/youtube/YoutubeChannelExtractor.java new file mode 100644 index 000000000..0b8fda717 --- /dev/null +++ b/services/youtube/YoutubeChannelExtractor.java @@ -0,0 +1,361 @@ +package org.schabi.newpipe.extractor.services.youtube; + + + +import org.json.JSONException; +import org.json.JSONObject; +import org.jsoup.Jsoup; +import org.jsoup.nodes.Document; +import org.jsoup.nodes.Element; +import org.schabi.newpipe.extractor.AbstractStreamInfo; +import org.schabi.newpipe.extractor.Downloader; +import org.schabi.newpipe.extractor.NewPipe; +import org.schabi.newpipe.extractor.Parser; +import org.schabi.newpipe.extractor.UrlIdHandler; +import org.schabi.newpipe.extractor.channel.ChannelExtractor; +import org.schabi.newpipe.extractor.exceptions.ExtractionException; +import org.schabi.newpipe.extractor.exceptions.ParsingException; +import org.schabi.newpipe.extractor.stream_info.StreamInfoItemCollector; +import org.schabi.newpipe.extractor.stream_info.StreamInfoItemExtractor; + + +import java.io.IOException; + +/** + * Created by Christian Schabesberger on 25.07.16. + * + * Copyright (C) Christian Schabesberger 2016 + * YoutubeChannelExtractor.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class YoutubeChannelExtractor extends ChannelExtractor { + + private static final String TAG = YoutubeChannelExtractor.class.toString(); + + // private CSSOMParser cssParser = new CSSOMParser(new SACParserCSS3()); + + private Document doc = null; + + private boolean isAjaxPage = false; + private static String userUrl = ""; + private static String channelName = ""; + private static String avatarUrl = ""; + private static String bannerUrl = ""; + private static String feedUrl = ""; + private static long subscriberCount = -1; + // the fist page is html all other pages are ajax. Every new page can be requested by sending + // this request url. + private static String nextPageUrl = ""; + + public YoutubeChannelExtractor(UrlIdHandler urlIdHandler, String url, int page, int serviceId) + throws ExtractionException, IOException { + super(urlIdHandler, url, page, serviceId); + + Downloader downloader = NewPipe.getDownloader(); + + url = urlIdHandler.cleanUrl(url) ; //+ "/video?veiw=0&flow=list&sort=dd"; + + if(page == 0) { + if (isUserUrl(url)) { + userUrl = url; + } else { + // we first need to get the user url. Otherwise we can't find videos + String channelPageContent = downloader.download(url); + Document channelDoc = Jsoup.parse(channelPageContent, url); + userUrl = getUserUrl(channelDoc); + } + + userUrl = userUrl + "/videos?veiw=0&flow=list&sort=dd&live_view=10000"; + String pageContent = downloader.download(userUrl); + doc = Jsoup.parse(pageContent, userUrl); + nextPageUrl = getNextPageUrl(doc); + isAjaxPage = false; + } else { + String ajaxDataRaw = downloader.download(nextPageUrl); + JSONObject ajaxData; + try { + ajaxData = new JSONObject(ajaxDataRaw); + String htmlDataRaw = ajaxData.getString("content_html"); + doc = Jsoup.parse(htmlDataRaw, nextPageUrl); + + String nextPageHtmlDataRaw = ajaxData.getString("load_more_widget_html"); + if(!nextPageHtmlDataRaw.isEmpty()) { + Document nextPageData = Jsoup.parse(nextPageHtmlDataRaw, nextPageUrl); + nextPageUrl = getNextPageUrl(nextPageData); + } else { + nextPageUrl = ""; + } + } catch (JSONException e) { + throw new ParsingException("Could not parse json data for next page", e); + } + isAjaxPage = true; + } + } + + @Override + public String getChannelName() throws ParsingException { + try { + if(!isAjaxPage) { + channelName = doc.select("span[class=\"qualified-channel-title-text\"]").first() + .select("a").first().text(); + } + return channelName; + } catch(Exception e) { + throw new ParsingException("Could not get channel name"); + } + } + + @Override + public String getAvatarUrl() throws ParsingException { + try { + if(!isAjaxPage) { + avatarUrl = doc.select("img[class=\"channel-header-profile-image\"]") + .first().attr("abs:src"); + } + return avatarUrl; + } catch(Exception e) { + throw new ParsingException("Could not get avatar", e); + } + } + + @Override + public String getBannerUrl() throws ParsingException { + try { + if(!isAjaxPage) { + Element el = doc.select("div[id=\"gh-banner\"]").first().select("style").first(); + String cssContent = el.html(); + String url = "https:" + Parser.matchGroup1("url\\(([^)]+)\\)", cssContent); + + if (url.contains("s.ytimg.com") || url.contains("default_banner")) { + bannerUrl = null; + } else { + bannerUrl = url; + } + } + return bannerUrl; + } catch(Exception e) { + throw new ParsingException("Could not get Banner", e); + } + } + + @Override + public StreamInfoItemCollector getStreams() throws ParsingException { + StreamInfoItemCollector collector = getStreamPreviewInfoCollector(); + Element ul; + if(isAjaxPage) { + ul = doc.select("body").first(); + } else { + ul = doc.select("ul[id=\"browse-items-primary\"]").first(); + } + + for(final Element li : ul.children()) { + if (li.select("div[class=\"feed-item-dismissable\"]").first() != null) { + collector.commit(new StreamInfoItemExtractor() { + @Override + public AbstractStreamInfo.StreamType getStreamType() throws ParsingException { + return AbstractStreamInfo.StreamType.VIDEO_STREAM; + } + + @Override + public boolean isAd() throws ParsingException { + if(!li.select("span[class*=\"icon-not-available\"]").isEmpty()) { + return true; + } else { + return false; + } + } + + @Override + public String getWebPageUrl() throws ParsingException { + try { + Element el = li.select("div[class=\"feed-item-dismissable\"]").first(); + Element dl = el.select("h3").first().select("a").first(); + return dl.attr("abs:href"); + } catch (Exception e) { + throw new ParsingException("Could not get web page url for the video", e); + } + } + + @Override + public String getTitle() throws ParsingException { + try { + Element el = li.select("div[class=\"feed-item-dismissable\"]").first(); + Element dl = el.select("h3").first().select("a").first(); + return dl.text(); + } catch (Exception e) { + throw new ParsingException("Could not get title", e); + } + } + + @Override + public int getDuration() throws ParsingException { + try { + return YoutubeParsingHelper.parseDurationString( + li.select("span[class=\"video-time\"]").first().text()); + } catch(Exception e) { + if(isLiveStream(li)) { + // -1 for no duration + return -1; + } else { + throw new ParsingException("Could not get Duration: " + getTitle(), e); + } + } + } + + @Override + public String getUploader() throws ParsingException { + return getChannelName(); + } + + @Override + public String getUploadDate() throws ParsingException { + try { + Element meta = li.select("div[class=\"yt-lockup-meta\"]").first(); + Element li = meta.select("li").first(); + if (li == null && meta != null) { + //this means we have a youtube red video + return ""; + }else { + return li.text(); + } + } catch(Exception e) { + throw new ParsingException("Could not get uplaod date", e); + } + } + + @Override + public long getViewCount() throws ParsingException { + String output; + String input; + try { + input = li.select("div[class=\"yt-lockup-meta\"]").first() + .select("li").get(1) + .text(); + } catch (IndexOutOfBoundsException e) { + return -1; + } + + output = Parser.matchGroup1("([0-9,\\. ]*)", input) + .replace(" ", "") + .replace(".", "") + .replace(",", ""); + + try { + return Long.parseLong(output); + } catch (NumberFormatException e) { + // if this happens the video probably has no views + if(!input.isEmpty()) { + return 0; + } else { + throw new ParsingException("Could not handle input: " + input, e); + } + } + } + + @Override + public String getThumbnailUrl() throws ParsingException { + try { + String url; + Element te = li.select("span[class=\"yt-thumb-clip\"]").first() + .select("img").first(); + url = te.attr("abs:src"); + // Sometimes youtube sends links to gif files which somehow seem to not exist + // anymore. Items with such gif also offer a secondary image source. So we are going + // to use that if we've caught such an item. + if (url.contains(".gif")) { + url = te.attr("abs:data-thumb"); + } + return url; + } catch (Exception e) { + throw new ParsingException("Could not get thumbnail url", e); + } + } + + private boolean isLiveStream(Element item) { + Element bla = item.select("span[class*=\"yt-badge-live\"]").first(); + + if(bla == null) { + // sometimes livestreams dont have badges but sill are live streams + // if video time is not available we most likly have an offline livestream + if(item.select("span[class*=\"video-time\"]").first() == null) { + return true; + } + } + return bla != null; + } + }); + } + } + + return collector; + } + + @Override + public long getSubscriberCount() throws ParsingException { + Element el = doc.select("span[class*=\"yt-subscription-button-subscriber-count\"]") + .first(); + if(el != null) { + subscriberCount = Long.parseLong(el.text().replaceAll("\\D+","")); + } else if(el == null && subscriberCount == -1) { + throw new ParsingException("Could not get subscriber count"); + } + return subscriberCount; + } + + @Override + public String getFeedUrl() throws ParsingException { + try { + if(userUrl.contains("channel")) { + //channels don't have feeds in youtube, only user can provide such + return ""; + } + if(!isAjaxPage) { + feedUrl = doc.select("link[title=\"RSS\"]").first().attr("abs:href"); + } + return feedUrl; + } catch(Exception e) { + throw new ParsingException("Could not get feed url", e); + } + } + + @Override + public boolean hasNextPage() throws ParsingException { + return !nextPageUrl.isEmpty(); + } + + private String getUserUrl(Document d) throws ParsingException { + return d.select("span[class=\"qualified-channel-title-text\"]").first() + .select("a").first().attr("abs:href"); + } + + private boolean isUserUrl(String url) throws ParsingException { + return url.contains("/user/"); + } + + private String getNextPageUrl(Document d) throws ParsingException { + try { + Element button = d.select("button[class*=\"yt-uix-load-more\"]").first(); + if(button != null) { + return button.attr("abs:data-uix-load-more-href"); + } else { + // sometimes channels are simply so small, they don't have a second/next4q page + return ""; + } + } catch(Exception e) { + throw new ParsingException("could not load next page url", e); + } + } +} diff --git a/services/youtube/YoutubeChannelInfoItemExtractor.java b/services/youtube/YoutubeChannelInfoItemExtractor.java new file mode 100644 index 000000000..7dafb63e8 --- /dev/null +++ b/services/youtube/YoutubeChannelInfoItemExtractor.java @@ -0,0 +1,83 @@ +package org.schabi.newpipe.extractor.services.youtube; + +import org.schabi.newpipe.extractor.Parser; +import org.schabi.newpipe.extractor.channel.ChannelInfoItemExtractor; +import org.schabi.newpipe.extractor.exceptions.ParsingException; +import org.jsoup.nodes.Element; + +/** + * Created by Christian Schabesberger on 12.02.17. + * + * Copyright (C) Christian Schabesberger 2017 + * YoutubeChannelInfoItemExtractor.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class YoutubeChannelInfoItemExtractor implements ChannelInfoItemExtractor { + private Element el; + + public YoutubeChannelInfoItemExtractor(Element el) { + this.el = el; + } + + public String getThumbnailUrl() throws ParsingException { + Element img = el.select("span[class*=\"yt-thumb-simple\"]").first() + .select("img").first(); + + String url = img.attr("abs:src"); + + if(url.contains("gif")) { + url = img.attr("abs:data-thumb"); + } + return url; + } + + public String getChannelName() throws ParsingException { + return el.select("a[class*=\"yt-uix-tile-link\"]").first() + .text(); + } + + public String getWebPageUrl() throws ParsingException { + return el.select("a[class*=\"yt-uix-tile-link\"]").first() + .attr("abs:href"); + } + + public long getSubscriberCount() throws ParsingException { + Element subsEl = el.select("span[class*=\"yt-subscriber-count\"]").first(); + if(subsEl == null) { + return 0; + } else { + return Integer.parseInt(subsEl.text().replaceAll("\\D+","")); + } + } + + public int getVideoAmount() throws ParsingException { + Element metaEl = el.select("ul[class*=\"yt-lockup-meta-info\"]").first(); + if(metaEl == null) { + return 0; + } else { + return Integer.parseInt(metaEl.text().replaceAll("\\D+","")); + } + } + + public String getDescription() throws ParsingException { + Element desEl = el.select("div[class*=\"yt-lockup-description\"]").first(); + if(desEl == null) { + return ""; + } else { + return desEl.text(); + } + } +} diff --git a/services/youtube/YoutubeChannelUrlIdHandler.java b/services/youtube/YoutubeChannelUrlIdHandler.java new file mode 100644 index 000000000..23960f608 --- /dev/null +++ b/services/youtube/YoutubeChannelUrlIdHandler.java @@ -0,0 +1,47 @@ +package org.schabi.newpipe.extractor.services.youtube; + +import org.schabi.newpipe.extractor.Parser; +import org.schabi.newpipe.extractor.UrlIdHandler; +import org.schabi.newpipe.extractor.exceptions.ParsingException; + +/** + * Created by Christian Schabesberger on 25.07.16. + * + * Copyright (C) Christian Schabesberger 2016 + * YoutubeChannelUrlIdHandler.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class YoutubeChannelUrlIdHandler implements UrlIdHandler { + + public String getUrl(String channelId) { + return "https://www.youtube.com/" + channelId; + } + + public String getId(String siteUrl) throws ParsingException { + return Parser.matchGroup1("/(user/[A-Za-z0-9_-]*|channel/[A-Za-z0-9_-]*)", siteUrl); + } + + public String cleanUrl(String siteUrl) throws ParsingException { + return getUrl(getId(siteUrl)); + } + + public boolean acceptUrl(String videoUrl) { + return (videoUrl.contains("youtube") || + videoUrl.contains("youtu.be")) && + ( videoUrl.contains("/user/") || + videoUrl.contains("/channel/")); + } +} diff --git a/services/youtube/YoutubeParsingHelper.java b/services/youtube/YoutubeParsingHelper.java new file mode 100644 index 000000000..3b4ad42e1 --- /dev/null +++ b/services/youtube/YoutubeParsingHelper.java @@ -0,0 +1,66 @@ +package org.schabi.newpipe.extractor.services.youtube; + + +import org.schabi.newpipe.extractor.exceptions.ParsingException; + +/** + * Created by Christian Schabesberger on 02.03.16. + * + * Copyright (C) Christian Schabesberger 2016 + * YoutubeParsingHelper.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class YoutubeParsingHelper { + + private YoutubeParsingHelper() { + } + + public static int parseDurationString(String input) + throws ParsingException, NumberFormatException { + String[] splitInput = input.split(":"); + String days = "0"; + String hours = "0"; + String minutes = "0"; + String seconds; + + switch(splitInput.length) { + case 4: + days = splitInput[0]; + hours = splitInput[1]; + minutes = splitInput[2]; + seconds = splitInput[3]; + break; + case 3: + hours = splitInput[0]; + minutes = splitInput[1]; + seconds = splitInput[2]; + break; + case 2: + minutes = splitInput[0]; + seconds = splitInput[1]; + break; + case 1: + seconds = splitInput[0]; + break; + default: + throw new ParsingException("Error duration string with unknown format: " + input); + } + return ((((Integer.parseInt(days) * 24) + + Integer.parseInt(hours) * 60) + + Integer.parseInt(minutes)) * 60) + + Integer.parseInt(seconds); + } +} diff --git a/services/youtube/YoutubeSearchEngine.java b/services/youtube/YoutubeSearchEngine.java new file mode 100644 index 000000000..d650535f7 --- /dev/null +++ b/services/youtube/YoutubeSearchEngine.java @@ -0,0 +1,119 @@ +package org.schabi.newpipe.extractor.services.youtube; + +import org.jsoup.Jsoup; +import org.jsoup.nodes.Document; +import org.jsoup.nodes.Element; +import org.schabi.newpipe.extractor.Downloader; +import org.schabi.newpipe.extractor.NewPipe; +import org.schabi.newpipe.extractor.UrlIdHandler; +import org.schabi.newpipe.extractor.exceptions.ExtractionException; +import org.schabi.newpipe.extractor.search.InfoItemSearchCollector; +import org.schabi.newpipe.extractor.search.SearchEngine; + +import java.net.URLEncoder; +import java.io.IOException; +import java.util.EnumSet; + + +/** + * Created by Christian Schabesberger on 09.08.15. + * + * Copyright (C) Christian Schabesberger 2015 + * YoutubeSearchEngine.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class YoutubeSearchEngine extends SearchEngine { + + private static final String TAG = YoutubeSearchEngine.class.toString(); + public static final String CHARSET_UTF_8 = "UTF-8"; + + public YoutubeSearchEngine(UrlIdHandler urlIdHandler, int serviceId) { + super(urlIdHandler, serviceId); + } + + @Override + public InfoItemSearchCollector search(String query, + int page, + String languageCode, + EnumSet filter) + throws IOException, ExtractionException { + InfoItemSearchCollector collector = getInfoItemSearchCollector(); + + + Downloader downloader = NewPipe.getDownloader(); + + String url = "https://www.youtube.com/results" + + "?q=" + URLEncoder.encode(query, CHARSET_UTF_8) + + "&page=" + Integer.toString(page + 1); + if(filter.contains(Filter.STREAM) && !filter.contains(Filter.CHANNEL)) { + url += "&sp=EgIQAQ%253D%253D"; + } else if(!filter.contains(Filter.STREAM) && filter.contains(Filter.CHANNEL)) { + url += "&sp=EgIQAg%253D%253D"; + } + + String site; + //String url = builder.build().toString(); + //if we've been passed a valid language code, append it to the URL + if(!languageCode.isEmpty()) { + //assert Pattern.matches("[a-z]{2}(-([A-Z]{2}|[0-9]{1,3}))?", languageCode); + site = downloader.download(url, languageCode); + } + else { + site = downloader.download(url); + } + + Document doc = Jsoup.parse(site, url); + Element list = doc.select("ol[class=\"item-section\"]").first(); + + for (Element item : list.children()) { + /* First we need to determine which kind of item we are working with. + Youtube depicts five different kinds of items on its search result page. These are + regular videos, playlists, channels, two types of video suggestions, and a "no video + found" item. Since we only want videos, we need to filter out all the others. + An example for this can be seen here: + https://www.youtube.com/results?search_query=asdf&page=1 + + We already applied a filter to the url, so we don't need to care about channels and + playlists now. + */ + + Element el; + + // both types of spell correction item + if ((el = item.select("div[class*=\"spell-correction\"]").first()) != null) { + collector.setSuggestion(el.select("a").first().text()); + if(list.children().size() == 1) { + throw new NothingFoundException("Did you mean: " + el.select("a").first().text()); + } + // search message item + } else if ((el = item.select("div[class*=\"search-message\"]").first()) != null) { + throw new NothingFoundException(el.text()); + + // video item type + } else if ((el = item.select("div[class*=\"yt-lockup-video\"]").first()) != null) { + collector.commit(new YoutubeStreamInfoItemExtractor(el)); + } else if((el = item.select("div[class*=\"yt-lockup-channel\"]").first()) != null) { + collector.commit(new YoutubeChannelInfoItemExtractor(el)); + } else { + // noinspection ConstantConditions + // simply ignore not known items + // throw new ExtractionException("unexpected element found: \"" + item + "\""); + } + } + + return collector; + } +} diff --git a/services/youtube/YoutubeService.java b/services/youtube/YoutubeService.java new file mode 100644 index 000000000..c8cc68fd5 --- /dev/null +++ b/services/youtube/YoutubeService.java @@ -0,0 +1,82 @@ +package org.schabi.newpipe.extractor.services.youtube; + +import org.schabi.newpipe.extractor.StreamingService; +import org.schabi.newpipe.extractor.UrlIdHandler; +import org.schabi.newpipe.extractor.channel.ChannelExtractor; +import org.schabi.newpipe.extractor.exceptions.ExtractionException; +import org.schabi.newpipe.extractor.search.SearchEngine; +import org.schabi.newpipe.extractor.SuggestionExtractor; +import org.schabi.newpipe.extractor.stream_info.StreamExtractor; + +import java.io.IOException; + + +/** + * Created by Christian Schabesberger on 23.08.15. + * + * Copyright (C) Christian Schabesberger 2015 + * YoutubeService.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class YoutubeService extends StreamingService { + + public YoutubeService(int id) { + super(id); + } + + @Override + public ServiceInfo getServiceInfo() { + ServiceInfo serviceInfo = new ServiceInfo(); + serviceInfo.name = "Youtube"; + return serviceInfo; + } + @Override + public StreamExtractor getExtractorInstance(String url) + throws ExtractionException, IOException { + UrlIdHandler urlIdHandler = YoutubeStreamUrlIdHandler.getInstance(); + if(urlIdHandler.acceptUrl(url)) { + return new YoutubeStreamExtractor(urlIdHandler, url, getServiceId()); + } + else { + throw new IllegalArgumentException("supplied String is not a valid Youtube URL"); + } + } + @Override + public SearchEngine getSearchEngineInstance() { + return new YoutubeSearchEngine(getStreamUrlIdHandlerInstance(), getServiceId()); + } + + @Override + public UrlIdHandler getStreamUrlIdHandlerInstance() { + return YoutubeStreamUrlIdHandler.getInstance(); + } + + @Override + public UrlIdHandler getChannelUrlIdHandlerInstance() { + return new YoutubeChannelUrlIdHandler(); + } + + @Override + public ChannelExtractor getChannelExtractorInstance(String url, int page) + throws ExtractionException, IOException { + return new YoutubeChannelExtractor(getChannelUrlIdHandlerInstance(), url, page, getServiceId()); + } + + @Override + public SuggestionExtractor getSuggestionExtractorInstance() { + return new YoutubeSuggestionExtractor(getServiceId()); + } +} diff --git a/services/youtube/YoutubeStreamExtractor.java b/services/youtube/YoutubeStreamExtractor.java new file mode 100644 index 000000000..2df361644 --- /dev/null +++ b/services/youtube/YoutubeStreamExtractor.java @@ -0,0 +1,878 @@ +package org.schabi.newpipe.extractor.services.youtube; + +import org.json.JSONException; +import org.json.JSONObject; +import org.jsoup.Jsoup; +import org.jsoup.nodes.Document; +import org.jsoup.nodes.Element; +import org.mozilla.javascript.Context; +import org.mozilla.javascript.Function; +import org.mozilla.javascript.ScriptableObject; +import org.schabi.newpipe.extractor.AbstractStreamInfo; +import org.schabi.newpipe.extractor.exceptions.ExtractionException; +import org.schabi.newpipe.extractor.exceptions.ParsingException; +import org.schabi.newpipe.extractor.exceptions.ReCaptchaException; +import org.schabi.newpipe.extractor.stream_info.AudioStream; +import org.schabi.newpipe.extractor.Downloader; +import org.schabi.newpipe.extractor.NewPipe; +import org.schabi.newpipe.extractor.Parser; +import org.schabi.newpipe.extractor.UrlIdHandler; +import org.schabi.newpipe.extractor.MediaFormat; +import org.schabi.newpipe.extractor.stream_info.StreamExtractor; +import org.schabi.newpipe.extractor.stream_info.StreamInfo; +import org.schabi.newpipe.extractor.stream_info.StreamInfoItemCollector; +import org.schabi.newpipe.extractor.stream_info.StreamInfoItemExtractor; +import org.schabi.newpipe.extractor.stream_info.VideoStream; + +import java.io.IOException; +import java.util.List; +import java.util.Map; +import java.util.Vector; +import java.util.regex.Matcher; +import java.util.regex.Pattern; + +/** + * Created by Christian Schabesberger on 06.08.15. + * + * Copyright (C) Christian Schabesberger 2015 + * YoutubeStreamExtractor.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class YoutubeStreamExtractor extends StreamExtractor { + public static final String URL_ENCODED_FMT_STREAM_MAP = "url_encoded_fmt_stream_map"; + public static final String HTTPS = "https:"; + public static final String CONTENT = "content"; + public static final String REGEX_INT = "[^\\d]"; + + // exceptions + + public class DecryptException extends ParsingException { + DecryptException(String message, Throwable cause) { + super(message, cause); + } + } + + // special content not available exceptions + + public class GemaException extends ContentNotAvailableException { + GemaException(String message) { + super(message); + } + } + + public class LiveStreamException extends ContentNotAvailableException { + LiveStreamException(String message) { + super(message); + } + } + + // ---------------- + + // Sometimes if the html page of youtube is already downloaded, youtube web page will internally + // download the /get_video_info page. Since a certain date dashmpd url is only available over + // this /get_video_info page, so we always need to download this one to. + // %%video_id%% will be replaced by the actual video id + // $$el_type$$ will be replaced by the actual el_type (se the declarations below) + private static final String GET_VIDEO_INFO_URL = + "https://www.youtube.com/get_video_info?video_id=%%video_id%%$$el_type$$&ps=default&eurl=&gl=US&hl=en"; + // eltype is necessary for the url above + private static final String EL_INFO = "el=info"; + + public enum ItagType { + AUDIO, + VIDEO, + VIDEO_ONLY + } + + private static class ItagItem { + public ItagItem(int id, ItagType type, MediaFormat format, String res, int fps) { + this.id = id; + this.itagType = type; + this.mediaFormatId = format.id; + this.resolutionString = res; + this.fps = fps; + } + public ItagItem(int id, ItagType type, MediaFormat format, int samplingRate, int bandWidth) { + this.id = id; + this.itagType = type; + this.mediaFormatId = format.id; + this.samplingRate = samplingRate; + this.bandWidth = bandWidth; + } + public int id; + public ItagType itagType; + public int mediaFormatId; + public String resolutionString; + public int fps = -1; + public int samplingRate = -1; + public int bandWidth = -1; + } + + private static final ItagItem[] itagList = { + // video streams + // id, ItagType, MediaFormat, Resolution, fps + new ItagItem(17, ItagType.VIDEO, MediaFormat.v3GPP, "144p", 12), + new ItagItem(18, ItagType.VIDEO, MediaFormat.MPEG_4, "360p", 24), + new ItagItem(22, ItagType.VIDEO, MediaFormat.MPEG_4, "720p", 24), + new ItagItem(36, ItagType.VIDEO, MediaFormat.v3GPP, "240p", 24), + new ItagItem(37, ItagType.VIDEO, MediaFormat.MPEG_4, "1080p", 24), + new ItagItem(38, ItagType.VIDEO, MediaFormat.MPEG_4, "1080p", 24), + new ItagItem(43, ItagType.VIDEO, MediaFormat.WEBM, "360p", 24), + new ItagItem(44, ItagType.VIDEO, MediaFormat.WEBM, "480p", 24), + new ItagItem(45, ItagType.VIDEO, MediaFormat.WEBM, "720p", 24), + new ItagItem(46, ItagType.VIDEO, MediaFormat.WEBM, "1080p", 24), + // audio streams + // id, ItagType, MediaFormat, samplingR, bandwidth + new ItagItem(249, ItagType.AUDIO, MediaFormat.WEBMA, 0, 0), // bandwith/samplingR 0 because not known + new ItagItem(250, ItagType.AUDIO, MediaFormat.WEBMA, 0, 0), + new ItagItem(171, ItagType.AUDIO, MediaFormat.WEBMA, 0, 0), + new ItagItem(140, ItagType.AUDIO, MediaFormat.M4A, 0, 0), + new ItagItem(251, ItagType.AUDIO, MediaFormat.WEBMA, 0, 0), + // video only streams + new ItagItem(160, ItagType.VIDEO_ONLY, MediaFormat.MPEG_4, "144p", 24), + new ItagItem(133, ItagType.VIDEO_ONLY, MediaFormat.MPEG_4, "240p", 24), + new ItagItem(134, ItagType.VIDEO_ONLY, MediaFormat.MPEG_4, "360p", 24), + new ItagItem(135, ItagType.VIDEO_ONLY, MediaFormat.MPEG_4, "480p", 24), + new ItagItem(136, ItagType.VIDEO_ONLY, MediaFormat.MPEG_4, "720p", 24), + new ItagItem(137, ItagType.VIDEO_ONLY, MediaFormat.MPEG_4, "1080p", 24), + }; + + /**These lists only contain itag formats that are supported by the common Android Video player. + However if you are looking for a list showing all itag formats, look at + https://github.com/rg3/youtube-dl/issues/1687 */ + + public static boolean itagIsSupported(int itag) { + for(ItagItem item : itagList) { + if(itag == item.id) { + return true; + } + } + return false; + } + + public static ItagItem getItagItem(int itag) throws ParsingException { + for(ItagItem item : itagList) { + if(itag == item.id) { + return item; + } + } + throw new ParsingException("itag=" + Integer.toString(itag) + " not supported"); + } + + private static final String TAG = YoutubeStreamExtractor.class.toString(); + private final Document doc; + private JSONObject playerArgs; + private boolean isAgeRestricted; + private Map videoInfoPage; + + // static values + private static final String DECRYPTION_FUNC_NAME="decrypt"; + + // cached values + private static volatile String decryptionCode = ""; + + UrlIdHandler urlidhandler = YoutubeStreamUrlIdHandler.getInstance(); + String pageUrl = ""; + + public YoutubeStreamExtractor(UrlIdHandler urlIdHandler, String pageUrl, int serviceId) + throws ExtractionException, IOException { + super(urlIdHandler, pageUrl, serviceId); + //most common videoInfo fields are now set in our superclass, for all services + this.pageUrl = pageUrl; + Downloader downloader = NewPipe.getDownloader(); + String pageContent = downloader.download(urlidhandler.cleanUrl(pageUrl)); + doc = Jsoup.parse(pageContent, pageUrl); + JSONObject ytPlayerConfig; + String playerUrl; + + // Check if the video is age restricted + if (pageContent.contains(" method + je.printStackTrace(); + System.err.println("failed to load title from JSON args; trying to extract it from HTML"); + try { // fall through to fall-back + return doc.select("meta[name=title]").attr(CONTENT); + } catch (Exception e) { + throw new ParsingException("failed permanently to load title.", e); + } + } + } + + @Override + public String getDescription() throws ParsingException { + try { + return doc.select("p[id=\"eow-description\"]").first().html(); + } catch (Exception e) {//todo: add fallback method <-- there is no ... as long as i know + throw new ParsingException("failed to load description.", e); + } + } + + @Override + public String getUploader() throws ParsingException { + try { + if (playerArgs == null) { + return videoInfoPage.get("author"); + } + //json player args method + return playerArgs.getString("author"); + } catch(JSONException je) { + je.printStackTrace(); + System.err.println( + "failed to load uploader name from JSON args; trying to extract it from HTML"); + } try {//fall through to fallback HTML method + return doc.select("div.yt-user-info").first().text(); + } catch (Exception e) { + throw new ParsingException("failed permanently to load uploader name.", e); + } + } + + @Override + public int getLength() throws ParsingException { + try { + if (playerArgs == null) { + return Integer.valueOf(videoInfoPage.get("length_seconds")); + } + return playerArgs.getInt("length_seconds"); + } catch (JSONException e) {//todo: find fallback method + throw new ParsingException("failed to load video duration from JSON args", e); + } + } + + @Override + public long getViewCount() throws ParsingException { + try { + String viewCountString = doc.select("meta[itemprop=interactionCount]").attr(CONTENT); + return Long.parseLong(viewCountString); + } catch (Exception e) {//todo: find fallback method + throw new ParsingException("failed to get number of views", e); + } + } + + @Override + public String getUploadDate() throws ParsingException { + try { + return doc.select("meta[itemprop=datePublished]").attr(CONTENT); + } catch (Exception e) {//todo: add fallback method + throw new ParsingException("failed to get upload date.", e); + } + } + + @Override + public String getThumbnailUrl() throws ParsingException { + //first attempt getting a small image version + //in the html extracting part we try to get a thumbnail with a higher resolution + // Try to get high resolution thumbnail if it fails use low res from the player instead + try { + return doc.select("link[itemprop=\"thumbnailUrl\"]").first().attr("abs:href"); + } catch(Exception e) { + System.err.println("Could not find high res Thumbnail. Using low res instead"); + } + try { //fall through to fallback + return playerArgs.getString("thumbnail_url"); + } catch (JSONException je) { + throw new ParsingException( + "failed to extract thumbnail URL from JSON args; trying to extract it from HTML", je); + } catch (NullPointerException ne) { + // Get from the video info page instead + return videoInfoPage.get("thumbnail_url"); + } + } + + @Override + public String getUploaderThumbnailUrl() throws ParsingException { + try { + return doc.select("a[class*=\"yt-user-photo\"]").first() + .select("img").first() + .attr("abs:data-thumb"); + } catch (Exception e) {//todo: add fallback method + throw new ParsingException("failed to get uploader thumbnail URL.", e); + } + } + + @Override + public String getDashMpdUrl() throws ParsingException { + try { + String dashManifestUrl = ""; + if(videoInfoPage != null && videoInfoPage.containsKey("dashmpd")) { + dashManifestUrl = videoInfoPage.get("dashmpd"); + } else if (playerArgs.has("dashmpd")) { + dashManifestUrl = playerArgs.getString("dashmpd"); + } else { + return ""; + } + if(!dashManifestUrl.contains("/signature/")) { + String encryptedSig = Parser.matchGroup1("/s/([a-fA-F0-9\\.]+)", dashManifestUrl); + String decryptedSig; + + decryptedSig = decryptSignature(encryptedSig, decryptionCode); + dashManifestUrl = dashManifestUrl.replace("/s/" + encryptedSig, "/signature/" + decryptedSig); + } + return dashManifestUrl; + } catch (Exception e) { + throw new ParsingException( + "Could not get \"dashmpd\" maybe VideoInfoPage is broken.", e); + } + } + + + @Override + public List getAudioStreams() throws ParsingException { + Vector audioStreams = new Vector<>(); + try{ + String encodedUrlMap; + // playerArgs could be null if the video is age restricted + if (playerArgs == null) { + if(videoInfoPage.containsKey("adaptive_fmts")) { + encodedUrlMap = videoInfoPage.get("adaptive_fmts"); + } else { + return null; + } + } else { + if(playerArgs.has("adaptive_fmts")) { + encodedUrlMap = playerArgs.getString("adaptive_fmts"); + } else { + return null; + } + } + for(String url_data_str : encodedUrlMap.split(",")) { + // This loop iterates through multiple streams, therefor tags + // is related to one and the same stream at a time. + Map tags = Parser.compatParseMap( + org.jsoup.parser.Parser.unescapeEntities(url_data_str, true)); + + int itag = Integer.parseInt(tags.get("itag")); + + if (itagIsSupported(itag)) { + ItagItem itagItem = getItagItem(itag); + if (itagItem.itagType == ItagType.AUDIO) { + String streamUrl = tags.get("url"); + // if video has a signature: decrypt it and add it to the url + if (tags.get("s") != null) { + streamUrl = streamUrl + "&signature=" + + decryptSignature(tags.get("s"), decryptionCode); + } + + audioStreams.add(new AudioStream(streamUrl, + itagItem.mediaFormatId, + itagItem.bandWidth, + itagItem.samplingRate)); + } + } + } + } catch (Exception e) { + throw new ParsingException("Could not get audiostreams", e); + } + return audioStreams; + } + + @Override + public List getVideoStreams() throws ParsingException { + Vector videoStreams = new Vector<>(); + + try{ + String encodedUrlMap; + // playerArgs could be null if the video is age restricted + if (playerArgs == null) { + encodedUrlMap = videoInfoPage.get(URL_ENCODED_FMT_STREAM_MAP); + } else { + encodedUrlMap = playerArgs.getString(URL_ENCODED_FMT_STREAM_MAP); + } + for(String url_data_str : encodedUrlMap.split(",")) { + try { + // This loop iterates through multiple streams, therefor tags + // is related to one and the same stream at a time. + Map tags = Parser.compatParseMap( + org.jsoup.parser.Parser.unescapeEntities(url_data_str, true)); + + int itag = Integer.parseInt(tags.get("itag")); + + if (itagIsSupported(itag)) { + ItagItem itagItem = getItagItem(itag); + if(itagItem.itagType == ItagType.VIDEO) { + String streamUrl = tags.get("url"); + // if video has a signature: decrypt it and add it to the url + if (tags.get("s") != null) { + streamUrl = streamUrl + "&signature=" + + decryptSignature(tags.get("s"), decryptionCode); + } + videoStreams.add(new VideoStream( + streamUrl, + itagItem.mediaFormatId, + itagItem.resolutionString)); + } + } + } catch (Exception e) { + //todo: dont log throw an error + System.err.println("Could not get Video stream."); + e.printStackTrace(); + } + } + + } catch (Exception e) { + throw new ParsingException("Failed to get video streams", e); + } + + if(videoStreams.isEmpty()) { + throw new ParsingException("Failed to get any video stream"); + } + return videoStreams; + } + + @Override + public List getVideoOnlyStreams() throws ParsingException { + return null; + } + + /**Attempts to parse (and return) the offset to start playing the video from. + * @return the offset (in seconds), or 0 if no timestamp is found.*/ + @Override + public int getTimeStamp() throws ParsingException { + String timeStamp; + try { + timeStamp = Parser.matchGroup1("((#|&|\\?)t=\\d{0,3}h?\\d{0,3}m?\\d{1,3}s?)", pageUrl); + } catch (Parser.RegexException e) { + // catch this instantly since an url does not necessarily have to have a time stamp + + // -2 because well the testing system will then know its the regex that failed :/ + // not good i know + return -2; + } + + if(!timeStamp.isEmpty()) { + try { + String secondsString = ""; + String minutesString = ""; + String hoursString = ""; + try { + secondsString = Parser.matchGroup1("(\\d{1,3})s", timeStamp); + minutesString = Parser.matchGroup1("(\\d{1,3})m", timeStamp); + hoursString = Parser.matchGroup1("(\\d{1,3})h", timeStamp); + } catch (Exception e) { + //it could be that time is given in another method + if (secondsString.isEmpty() //if nothing was got, + && minutesString.isEmpty()//treat as unlabelled seconds + && hoursString.isEmpty()) { + secondsString = Parser.matchGroup1("t=(\\d+)", timeStamp); + } + } + + int seconds = secondsString.isEmpty() ? 0 : Integer.parseInt(secondsString); + int minutes = minutesString.isEmpty() ? 0 : Integer.parseInt(minutesString); + int hours = hoursString.isEmpty() ? 0 : Integer.parseInt(hoursString); + + //don't trust BODMAS! + return seconds + (60 * minutes) + (3600 * hours); + //Log.d(TAG, "derived timestamp value:"+ret); + //the ordering varies internationally + } catch (ParsingException e) { + throw new ParsingException("Could not get timestamp.", e); + } + } else { + return 0; + } + } + + @Override + public int getAgeLimit() throws ParsingException { + if (!isAgeRestricted) { + return 0; + } + try { + return Integer.valueOf(doc.head() + .getElementsByAttributeValue("property", "og:restrictions:age") + .attr(CONTENT).replace("+", "")); + } catch (Exception e) { + throw new ParsingException("Could not get age restriction"); + } + } + + @Override + public String getAverageRating() throws ParsingException { + try { + if (playerArgs == null) { + return videoInfoPage.get("avg_rating"); + } + return playerArgs.getString("avg_rating"); + } catch (JSONException e) { + throw new ParsingException("Could not get Average rating", e); + } + } + + @Override + public int getLikeCount() throws ParsingException { + String likesString = ""; + try { + + Element button = doc.select("button.like-button-renderer-like-button").first(); + try { + likesString = button.select("span.yt-uix-button-content").first().text(); + } catch (NullPointerException e) { + //if this ckicks in our button has no content and thefore likes/dislikes are disabled + return -1; + } + return Integer.parseInt(likesString.replaceAll(REGEX_INT, "")); + } catch (NumberFormatException nfe) { + throw new ParsingException( + "failed to parse likesString \"" + likesString + "\" as integers", nfe); + } catch (Exception e) { + throw new ParsingException("Could not get like count", e); + } + } + + @Override + public int getDislikeCount() throws ParsingException { + String dislikesString = ""; + try { + Element button = doc.select("button.like-button-renderer-dislike-button").first(); + try { + dislikesString = button.select("span.yt-uix-button-content").first().text(); + } catch (NullPointerException e) { + //if this kicks in our button has no content and therefore likes/dislikes are disabled + return -1; + } + return Integer.parseInt(dislikesString.replaceAll(REGEX_INT, "")); + } catch(NumberFormatException nfe) { + throw new ParsingException( + "failed to parse dislikesString \"" + dislikesString + "\" as integers", nfe); + } catch(Exception e) { + throw new ParsingException("Could not get dislike count", e); + } + } + + @Override + public StreamInfoItemExtractor getNextVideo() throws ParsingException { + try { + return extractVideoPreviewInfo(doc.select("div[class=\"watch-sidebar-section\"]").first() + .select("li").first()); + } catch(Exception e) { + throw new ParsingException("Could not get next video", e); + } + } + + @Override + public StreamInfoItemCollector getRelatedVideos() throws ParsingException { + try { + StreamInfoItemCollector collector = getStreamPreviewInfoCollector(); + Element ul = doc.select("ul[id=\"watch-related\"]").first(); + if(ul != null) { + for (Element li : ul.children()) { + // first check if we have a playlist. If so leave them out + if (li.select("a[class*=\"content-link\"]").first() != null) { + collector.commit(extractVideoPreviewInfo(li)); + } + } + } + return collector; + } catch(Exception e) { + throw new ParsingException("Could not get related videos", e); + } + } + + @Override + public String getPageUrl() { + return pageUrl; + } + + @Override + public String getChannelUrl() throws ParsingException { + try { + return doc.select("div[class=\"yt-user-info\"]").first().children() + .select("a").first().attr("abs:href"); + } catch(Exception e) { + throw new ParsingException("Could not get channel link", e); + } + } + + @Override + public StreamInfo.StreamType getStreamType() throws ParsingException { + //todo: if implementing livestream support this value should be generated dynamically + return StreamInfo.StreamType.VIDEO_STREAM; + } + + /**Provides information about links to other videos on the video page, such as related videos. + * This is encapsulated in a StreamInfoItem object, + * which is a subset of the fields in a full StreamInfo.*/ + private StreamInfoItemExtractor extractVideoPreviewInfo(final Element li) { + return new StreamInfoItemExtractor() { + @Override + public AbstractStreamInfo.StreamType getStreamType() throws ParsingException { + return AbstractStreamInfo.StreamType.VIDEO_STREAM; + } + + @Override + public boolean isAd() throws ParsingException { + if(!li.select("span[class*=\"icon-not-available\"]").isEmpty()) { + return true; + } else { + return false; + } + } + + @Override + public String getWebPageUrl() throws ParsingException { + return li.select("a.content-link").first().attr("abs:href"); + } + + @Override + public String getTitle() throws ParsingException { + //todo: check NullPointerException causing + return li.select("span.title").first().text(); + //this page causes the NullPointerException, after finding it by searching for "tjvg": + //https://www.youtube.com/watch?v=Uqg0aEhLFAg + } + + @Override + public int getDuration() throws ParsingException { + return YoutubeParsingHelper.parseDurationString( + li.select("span.video-time").first().text()); + } + + @Override + public String getUploader() throws ParsingException { + return li.select("span.g-hovercard").first().text(); + } + + @Override + public String getUploadDate() throws ParsingException { + return null; + } + + @Override + public long getViewCount() throws ParsingException { + //this line is unused + //String views = li.select("span.view-count").first().text(); + + //Log.i(TAG, "title:"+info.title); + //Log.i(TAG, "view count:"+views); + + try { + return Long.parseLong(li.select("span.view-count") + .first().text().replaceAll(REGEX_INT, "")); + } catch (Exception e) { + //related videos sometimes have no view count + return 0; + } + } + + @Override + public String getThumbnailUrl() throws ParsingException { + Element img = li.select("img").first(); + String thumbnailUrl = img.attr("abs:src"); + // Sometimes youtube sends links to gif files which somehow seem to not exist + // anymore. Items with such gif also offer a secondary image source. So we are going + // to use that if we caught such an item. + if (thumbnailUrl.contains(".gif")) { + thumbnailUrl = img.attr("data-thumb"); + } + if (thumbnailUrl.startsWith("//")) { + thumbnailUrl = HTTPS + thumbnailUrl; + } + return thumbnailUrl; + } + }; + } + + + private String loadDecryptionCode(String playerUrl) throws DecryptException { + String decryptionFuncName; + String decryptionFunc; + String helperObjectName; + String helperObject; + String callerFunc = "function " + DECRYPTION_FUNC_NAME + "(a){return %%(a);}"; + String decryptionCode; + + try { + Downloader downloader = NewPipe.getDownloader(); + if(!playerUrl.contains("https://youtube.com")) { + //sometimes the https://youtube.com part does not get send with + //than we have to add it by hand + playerUrl = "https://youtube.com" + playerUrl; + } + String playerCode = downloader.download(playerUrl); + + decryptionFuncName = + Parser.matchGroup("([\"\\'])signature\\1\\s*,\\s*([a-zA-Z0-9$]+)\\(", playerCode, 2); + + String functionPattern = "(" + + decryptionFuncName.replace("$", "\\$") + + "=function\\([a-zA-Z0-9_]+\\)\\{.+?\\})"; + decryptionFunc = "var " + Parser.matchGroup1(functionPattern, playerCode) + ";"; + + helperObjectName = Parser + .matchGroup1(";([A-Za-z0-9_\\$]{2})\\...\\(", decryptionFunc); + + String helperPattern = "(var " + + helperObjectName.replace("$", "\\$") + "=\\{.+?\\}\\};)"; + helperObject = Parser.matchGroup1(helperPattern, playerCode); + + + callerFunc = callerFunc.replace("%%", decryptionFuncName); + decryptionCode = helperObject + decryptionFunc + callerFunc; + } catch(IOException ioe) { + throw new DecryptException("Could not load decrypt function", ioe); + } catch(Exception e) { + throw new DecryptException("Could not parse decrypt function ", e); + } + + return decryptionCode; + } + + private String decryptSignature(String encryptedSig, String decryptionCode) + throws DecryptException{ + Context context = Context.enter(); + context.setOptimizationLevel(-1); + Object result = null; + try { + ScriptableObject scope = context.initStandardObjects(); + context.evaluateString(scope, decryptionCode, "decryptionCode", 1, null); + Function decryptionFunc = (Function) scope.get("decrypt", scope); + result = decryptionFunc.call(context, scope, scope, new Object[]{encryptedSig}); + } catch (Exception e) { + throw new DecryptException("could not get decrypt signature", e); + } finally { + Context.exit(); + } + return result == null ? "" : result.toString(); + } + + private String findErrorReason(Document doc) { + String errorMessage = doc.select("h1[id=\"unavailable-message\"]").first().text(); + if(errorMessage.contains("GEMA")) { + // Gema sometimes blocks youtube music content in germany: + // https://www.gema.de/en/ + // Detailed description: + // https://en.wikipedia.org/wiki/GEMA_%28German_organization%29 + return "GEMA"; + } + return ""; + } +} diff --git a/services/youtube/YoutubeStreamInfoItemExtractor.java b/services/youtube/YoutubeStreamInfoItemExtractor.java new file mode 100644 index 000000000..44d606e2d --- /dev/null +++ b/services/youtube/YoutubeStreamInfoItemExtractor.java @@ -0,0 +1,186 @@ +package org.schabi.newpipe.extractor.services.youtube; + +import org.jsoup.nodes.Element; +import org.schabi.newpipe.extractor.AbstractStreamInfo; +import org.schabi.newpipe.extractor.Parser; +import org.schabi.newpipe.extractor.exceptions.FoundAdException; +import org.schabi.newpipe.extractor.exceptions.ParsingException; +import org.schabi.newpipe.extractor.stream_info.StreamInfoItemExtractor; + +/** + * Copyright (C) Christian Schabesberger 2016 + * YoutubeStreamInfoItemExtractor.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class YoutubeStreamInfoItemExtractor implements StreamInfoItemExtractor { + + private final Element item; + + public YoutubeStreamInfoItemExtractor(Element item) throws FoundAdException { + this.item = item; + } + + @Override + public String getWebPageUrl() throws ParsingException { + try { + Element el = item.select("div[class*=\"yt-lockup-video\"").first(); + Element dl = el.select("h3").first().select("a").first(); + return dl.attr("abs:href"); + } catch (Exception e) { + throw new ParsingException("Could not get web page url for the video", e); + } + } + + @Override + public String getTitle() throws ParsingException { + try { + Element el = item.select("div[class*=\"yt-lockup-video\"").first(); + Element dl = el.select("h3").first().select("a").first(); + return dl.text(); + } catch (Exception e) { + throw new ParsingException("Could not get title", e); + } + } + + @Override + public int getDuration() throws ParsingException { + try { + return YoutubeParsingHelper.parseDurationString( + item.select("span[class=\"video-time\"]").first().text()); + } catch(Exception e) { + if(isLiveStream(item)) { + // -1 for no duration + return -1; + } else { + throw new ParsingException("Could not get Duration: " + getTitle(), e); + } + } + } + + @Override + public String getUploader() throws ParsingException { + try { + return item.select("div[class=\"yt-lockup-byline\"]").first() + .select("a").first() + .text(); + } catch (Exception e) { + throw new ParsingException("Could not get uploader", e); + } + } + + @Override + public String getUploadDate() throws ParsingException { + try { + Element div = item.select("div[class=\"yt-lockup-meta\"]").first(); + if(div == null) { + return null; + } else { + return div.select("li").first().text(); + } + } catch(Exception e) { + throw new ParsingException("Could not get uplaod date", e); + } + } + + @Override + public long getViewCount() throws ParsingException { + String output; + String input; + try { + Element div = item.select("div[class=\"yt-lockup-meta\"]").first(); + if(div == null) { + return -1; + } else { + input = div.select("li").get(1) + .text(); + } + } catch (IndexOutOfBoundsException e) { + if(isLiveStream(item)) { + // -1 for no view count + return -1; + } else { + throw new ParsingException( + "Could not parse yt-lockup-meta although available: " + getTitle(), e); + } + } + + output = Parser.matchGroup1("([0-9,\\. ]*)", input) + .replace(" ", "") + .replace(".", "") + .replace(",", ""); + + try { + return Long.parseLong(output); + } catch (NumberFormatException e) { + // if this happens the video probably has no views + if(!input.isEmpty()) { + return 0; + } else { + throw new ParsingException("Could not handle input: " + input, e); + } + } + } + + @Override + public String getThumbnailUrl() throws ParsingException { + try { + String url; + Element te = item.select("div[class=\"yt-thumb video-thumb\"]").first() + .select("img").first(); + url = te.attr("abs:src"); + // Sometimes youtube sends links to gif files which somehow seem to not exist + // anymore. Items with such gif also offer a secondary image source. So we are going + // to use that if we've caught such an item. + if (url.contains(".gif")) { + url = te.attr("abs:data-thumb"); + } + return url; + } catch (Exception e) { + throw new ParsingException("Could not get thumbnail url", e); + } + } + + @Override + public AbstractStreamInfo.StreamType getStreamType() { + if(isLiveStream(item)) { + return AbstractStreamInfo.StreamType.LIVE_STREAM; + } else { + return AbstractStreamInfo.StreamType.VIDEO_STREAM; + } + } + + @Override + public boolean isAd() throws ParsingException { + if(!item.select("span[class*=\"icon-not-available\"]").isEmpty()) { + return true; + } else { + return false; + } + } + + private boolean isLiveStream(Element item) { + Element bla = item.select("span[class*=\"yt-badge-live\"]").first(); + + if(bla == null) { + // sometimes livestreams dont have badges but sill are live streams + // if video time is not available we most likly have an offline livestream + if(item.select("span[class*=\"video-time\"]").first() == null) { + return true; + } + } + return bla != null; + } +} diff --git a/services/youtube/YoutubeStreamUrlIdHandler.java b/services/youtube/YoutubeStreamUrlIdHandler.java new file mode 100644 index 000000000..8c08a6101 --- /dev/null +++ b/services/youtube/YoutubeStreamUrlIdHandler.java @@ -0,0 +1,163 @@ +package org.schabi.newpipe.extractor.services.youtube; + +import org.schabi.newpipe.extractor.Downloader; +import org.schabi.newpipe.extractor.NewPipe; +import org.schabi.newpipe.extractor.Parser; +import org.schabi.newpipe.extractor.UrlIdHandler; +import org.schabi.newpipe.extractor.exceptions.FoundAdException; +import org.schabi.newpipe.extractor.exceptions.ParsingException; +import org.schabi.newpipe.extractor.exceptions.ReCaptchaException; + +import java.io.IOException; +import java.io.UnsupportedEncodingException; +import java.net.URI; +import java.net.URISyntaxException; +import java.net.URLDecoder; + +/** + * Created by Christian Schabesberger on 02.02.16. + * + * Copyright (C) Christian Schabesberger 2016 + * YoutubeStreamUrlIdHandler.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class YoutubeStreamUrlIdHandler implements UrlIdHandler { + + private static final YoutubeStreamUrlIdHandler instance = new YoutubeStreamUrlIdHandler(); + private static final String ID_PATTERN = "([\\-a-zA-Z0-9_]{11})"; + + private YoutubeStreamUrlIdHandler() {} + + public static YoutubeStreamUrlIdHandler getInstance() { + return instance; + } + + @Override + public String getUrl(String videoId) { + return "https://www.youtube.com/watch?v=" + videoId; + } + + @Override + public String getId(String url) throws ParsingException, IllegalArgumentException { + if(url.isEmpty()) { + throw new IllegalArgumentException("The url parameter should not be empty"); + } + + String id; + String lowercaseUrl = url.toLowerCase(); + if(lowercaseUrl.contains("youtube")) { + if (url.contains("attribution_link")) { + try { + String escapedQuery = Parser.matchGroup1("u=(.[^&|$]*)", url); + String query = URLDecoder.decode(escapedQuery, "UTF-8"); + id = Parser.matchGroup1("v=" + ID_PATTERN, query); + } catch (UnsupportedEncodingException uee) { + throw new ParsingException("Could not parse attribution_link", uee); + } + } else if(lowercaseUrl.contains("youtube.com/shared?ci=")) { + return getRealIdFromSharedLink(url); + } else if (url.contains("vnd.youtube")) { + id = Parser.matchGroup1(ID_PATTERN, url); + } else if (url.contains("embed")) { + id = Parser.matchGroup1("embed/" + ID_PATTERN, url); + } else if(url.contains("googleads")) { + throw new FoundAdException("Error found add: " + url); + } else { + id = Parser.matchGroup1("[?&]v=" + ID_PATTERN, url); + } + } + else if(lowercaseUrl.contains("youtu.be")) { + if(url.contains("v=")) { + id = Parser.matchGroup1("v=" + ID_PATTERN, url); + } else { + id = Parser.matchGroup1("[Yy][Oo][Uu][Tt][Uu]\\.[Bb][Ee]/" + ID_PATTERN, url); + } + } + else { + throw new ParsingException("Error no suitable url: " + url); + } + + + if(!id.isEmpty()){ + return id; + } else { + throw new ParsingException("Error could not parse url: " + url); + } + } + + /** + * Get the real url from a shared uri. + * + * Shared URI's look like this: + * 
+     *     * https://www.youtube.com/shared?ci=PJICrTByb3E
+     *     * vnd.youtube://www.youtube.com/shared?ci=PJICrTByb3E&feature=twitter-deep-link
+     *
+ * @param url The shared url + * @return the id of the stream + * @throws ParsingException + */ + private String getRealIdFromSharedLink(String url) throws ParsingException { + URI uri; + try { + uri = new URI(url); + } catch (URISyntaxException e) { + throw new ParsingException("Invalid shared link", e); + } + String sharedId = getSharedId(uri); + Downloader downloader = NewPipe.getDownloader(); + String content; + try { + content = downloader.download("https://www.youtube.com/shared?ci=" + sharedId); + } catch (IOException | ReCaptchaException e) { + throw new ParsingException("Unable to resolve shared link", e); + } + // is this bad? is this fragile?: + String realId = Parser.matchGroup1("rel=\"shortlink\" href=\"https://youtu.be/" + ID_PATTERN, content); + if(sharedId.equals(realId)) { + throw new ParsingException("Got same id for as shared id: " + sharedId); + } + return realId; + } + + private String getSharedId(URI uri) throws ParsingException { + if (!"/shared".equals(uri.getPath())) { + throw new ParsingException("Not a shared link: " + uri.toString() + " (path != " + uri.getPath() + ")"); + } + return Parser.matchGroup1("ci=" + ID_PATTERN, uri.getQuery()); + } + + public String cleanUrl(String complexUrl) throws ParsingException { + return getUrl(getId(complexUrl)); + } + + @Override + public boolean acceptUrl(String videoUrl) { + String lowercaseUrl = videoUrl.toLowerCase(); + if(lowercaseUrl.contains("youtube") || + lowercaseUrl.contains("youtu.be")) { + // bad programming I know + try { + getId(videoUrl); + return true; + } catch (Exception e) { + return false; + } + } else { + return false; + } + } +} diff --git a/services/youtube/YoutubeSuggestionExtractor.java b/services/youtube/YoutubeSuggestionExtractor.java new file mode 100644 index 000000000..0535961e8 --- /dev/null +++ b/services/youtube/YoutubeSuggestionExtractor.java @@ -0,0 +1,99 @@ +package org.schabi.newpipe.extractor.services.youtube; + +import org.schabi.newpipe.extractor.Downloader; +import org.schabi.newpipe.extractor.NewPipe; +import org.schabi.newpipe.extractor.exceptions.ExtractionException; +import org.schabi.newpipe.extractor.exceptions.ParsingException; +import org.schabi.newpipe.extractor.SuggestionExtractor; +import org.w3c.dom.Node; +import org.w3c.dom.NodeList; +import org.xml.sax.InputSource; +import org.xml.sax.SAXException; + +import java.io.ByteArrayInputStream; +import java.io.IOException; +import java.net.URLEncoder; +import java.util.ArrayList; +import java.util.List; + +import javax.xml.parsers.DocumentBuilder; +import javax.xml.parsers.DocumentBuilderFactory; +import javax.xml.parsers.ParserConfigurationException; + +/** + * Created by Christian Schabesberger on 28.09.16. + * + * Copyright (C) Christian Schabesberger 2015 + * YoutubeSuggestionExtractor.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class YoutubeSuggestionExtractor extends SuggestionExtractor { + + public static final String CHARSET_UTF_8 = "UTF-8"; + + public YoutubeSuggestionExtractor(int serviceId) { + super(serviceId); + } + + @Override + public List suggestionList( + String query, String contentCountry) + throws ExtractionException, IOException { + List suggestions = new ArrayList<>(); + + Downloader dl = NewPipe.getDownloader(); + + String url = "https://suggestqueries.google.com/complete/search" + + "?client=" + "" + + "&output=" + "toolbar" + + "&ds=" + "yt" + + "&hl=" + URLEncoder.encode(contentCountry, CHARSET_UTF_8) + + "&q=" + URLEncoder.encode(query, CHARSET_UTF_8); + + + String response = dl.download(url); + + //TODO: Parse xml data using Jsoup not done + DocumentBuilderFactory dbFactory = DocumentBuilderFactory.newInstance(); + DocumentBuilder dBuilder; + org.w3c.dom.Document doc = null; + + try { + dBuilder = dbFactory.newDocumentBuilder(); + doc = dBuilder.parse(new InputSource( + new ByteArrayInputStream(response.getBytes(CHARSET_UTF_8)))); + doc.getDocumentElement().normalize(); + } catch (ParserConfigurationException | SAXException | IOException e) { + throw new ParsingException("Could not parse document."); + } + + try { + NodeList nList = doc.getElementsByTagName("CompleteSuggestion"); + for (int temp = 0; temp < nList.getLength(); temp++) { + + NodeList nList1 = doc.getElementsByTagName("suggestion"); + Node nNode1 = nList1.item(temp); + if (nNode1.getNodeType() == Node.ELEMENT_NODE) { + org.w3c.dom.Element eElement = (org.w3c.dom.Element) nNode1; + suggestions.add(eElement.getAttribute("data")); + } + } + return suggestions; + } catch(Exception e) { + throw new ParsingException("Could not get suggestions form document.", e); + } + } +} diff --git a/stream_info/AudioStream.java b/stream_info/AudioStream.java new file mode 100644 index 000000000..98eb17620 --- /dev/null +++ b/stream_info/AudioStream.java @@ -0,0 +1,46 @@ +package org.schabi.newpipe.extractor.stream_info; + +/** + * Created by Christian Schabesberger on 04.03.16. + * + * Copyright (C) Christian Schabesberger 2016 + * AudioStream.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class AudioStream { + public String url = ""; + public int format = -1; + public int bandwidth = -1; + public int sampling_rate = -1; + + public AudioStream(String url, int format, int bandwidth, int samplingRate) { + this.url = url; this.format = format; + this.bandwidth = bandwidth; this.sampling_rate = samplingRate; + } + + // reveals whether two streams are the same, but have different urls + public boolean equalStats(AudioStream cmp) { + return format == cmp.format + && bandwidth == cmp.bandwidth + && sampling_rate == cmp.sampling_rate; + } + + // reveals whether two streams are equal + public boolean equals(AudioStream cmp) { + return cmp != null && equalStats(cmp) + && url == cmp.url; + } +} diff --git a/stream_info/StreamExtractor.java b/stream_info/StreamExtractor.java new file mode 100644 index 000000000..1b7c1b5ab --- /dev/null +++ b/stream_info/StreamExtractor.java @@ -0,0 +1,104 @@ +package org.schabi.newpipe.extractor.stream_info; + +/** + * Created by Christian Schabesberger on 10.08.15. + * + * Copyright (C) Christian Schabesberger 2016 + * StreamExtractor.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +import org.schabi.newpipe.extractor.UrlIdHandler; +import org.schabi.newpipe.extractor.exceptions.ExtractionException; +import org.schabi.newpipe.extractor.exceptions.ParsingException; + +import java.util.List; + +/**Scrapes information from a video streaming service (eg, YouTube).*/ + + +@SuppressWarnings("ALL") +public abstract class StreamExtractor { + + private int serviceId; + private String url; + private UrlIdHandler urlIdHandler; + private StreamInfoItemCollector previewInfoCollector; + + public class ExtractorInitException extends ExtractionException { + public ExtractorInitException(String message) { + super(message); + } + public ExtractorInitException(Throwable cause) { + super(cause); + } + public ExtractorInitException(String message, Throwable cause) { + super(message, cause); + } + } + + public class ContentNotAvailableException extends ParsingException { + public ContentNotAvailableException(String message) { + super(message); + } + public ContentNotAvailableException(String message, Throwable cause) { + super(message, cause); + } + } + + public StreamExtractor(UrlIdHandler urlIdHandler, String url, int serviceId) { + this.serviceId = serviceId; + this.urlIdHandler = urlIdHandler; + previewInfoCollector = new StreamInfoItemCollector(urlIdHandler, serviceId); + } + + protected StreamInfoItemCollector getStreamPreviewInfoCollector() { + return previewInfoCollector; + } + + public String getUrl() { + return url; + } + + public UrlIdHandler getUrlIdHandler() { + return urlIdHandler; + } + + public abstract int getTimeStamp() throws ParsingException; + public abstract String getTitle() throws ParsingException; + public abstract String getDescription() throws ParsingException; + public abstract String getUploader() throws ParsingException; + public abstract String getChannelUrl() throws ParsingException; + public abstract int getLength() throws ParsingException; + public abstract long getViewCount() throws ParsingException; + public abstract String getUploadDate() throws ParsingException; + public abstract String getThumbnailUrl() throws ParsingException; + public abstract String getUploaderThumbnailUrl() throws ParsingException; + public abstract List getAudioStreams() throws ParsingException; + public abstract List getVideoStreams() throws ParsingException; + public abstract List getVideoOnlyStreams() throws ParsingException; + public abstract String getDashMpdUrl() throws ParsingException; + public abstract int getAgeLimit() throws ParsingException; + public abstract String getAverageRating() throws ParsingException; + public abstract int getLikeCount() throws ParsingException; + public abstract int getDislikeCount() throws ParsingException; + public abstract StreamInfoItemExtractor getNextVideo() throws ParsingException; + public abstract StreamInfoItemCollector getRelatedVideos() throws ParsingException; + public abstract String getPageUrl(); + public abstract StreamInfo.StreamType getStreamType() throws ParsingException; + public int getServiceId() { + return serviceId; + } +} diff --git a/stream_info/StreamInfo.java b/stream_info/StreamInfo.java new file mode 100644 index 000000000..cf3df49d8 --- /dev/null +++ b/stream_info/StreamInfo.java @@ -0,0 +1,294 @@ +package org.schabi.newpipe.extractor.stream_info; + +import org.schabi.newpipe.extractor.AbstractStreamInfo; +import org.schabi.newpipe.extractor.DashMpdParser; +import org.schabi.newpipe.extractor.InfoItem; +import org.schabi.newpipe.extractor.UrlIdHandler; +import org.schabi.newpipe.extractor.exceptions.ExtractionException; + +import java.io.IOException; +import java.util.List; +import java.util.Vector; + +/** + * Created by Christian Schabesberger on 26.08.15. + * + * Copyright (C) Christian Schabesberger 2016 + * StreamInfo.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +/**Info object for opened videos, ie the video ready to play.*/ +@SuppressWarnings("ALL") +public class StreamInfo extends AbstractStreamInfo { + + public static class StreamExctractException extends ExtractionException { + StreamExctractException(String message) { + super(message); + } + } + + public StreamInfo() {} + + /**Creates a new StreamInfo object from an existing AbstractVideoInfo. + * All the shared properties are copied to the new StreamInfo.*/ + @SuppressWarnings("WeakerAccess") + public StreamInfo(AbstractStreamInfo avi) { + this.id = avi.id; + this.title = avi.title; + this.uploader = avi.uploader; + this.thumbnail_url = avi.thumbnail_url; + this.webpage_url = avi.webpage_url; + this.upload_date = avi.upload_date; + this.upload_date = avi.upload_date; + this.view_count = avi.view_count; + + //todo: better than this + if(avi instanceof StreamInfoItem) { + //shitty String to convert code + /* + String dur = ((StreamInfoItem)avi).duration; + int minutes = Integer.parseInt(dur.substring(0, dur.indexOf(":"))); + int seconds = Integer.parseInt(dur.substring(dur.indexOf(":")+1, dur.length())); + */ + this.duration = ((StreamInfoItem)avi).duration; + } + } + + public void addException(Exception e) { + errors.add(e); + } + + /**Fills out the video info fields which are common to all services. + * Probably needs to be overridden by subclasses*/ + public static StreamInfo getVideoInfo(StreamExtractor extractor) + throws ExtractionException, IOException { + StreamInfo streamInfo = new StreamInfo(); + + streamInfo = extractImportantData(streamInfo, extractor); + streamInfo = extractStreams(streamInfo, extractor); + streamInfo = extractOptionalData(streamInfo, extractor); + + return streamInfo; + } + + private static StreamInfo extractImportantData( + StreamInfo streamInfo, StreamExtractor extractor) + throws ExtractionException, IOException { + /* ---- important data, withoug the video can't be displayed goes here: ---- */ + // if one of these is not available an exception is meant to be thrown directly into the frontend. + + UrlIdHandler uiconv = extractor.getUrlIdHandler(); + + streamInfo.service_id = extractor.getServiceId(); + streamInfo.webpage_url = extractor.getPageUrl(); + streamInfo.stream_type = extractor.getStreamType(); + streamInfo.id = uiconv.getId(extractor.getPageUrl()); + streamInfo.title = extractor.getTitle(); + streamInfo.age_limit = extractor.getAgeLimit(); + + if((streamInfo.stream_type == StreamType.NONE) + || (streamInfo.webpage_url == null || streamInfo.webpage_url.isEmpty()) + || (streamInfo.id == null || streamInfo.id.isEmpty()) + || (streamInfo.title == null /* streamInfo.title can be empty of course */) + || (streamInfo.age_limit == -1)) { + throw new ExtractionException("Some importand stream information was not given."); + } + + return streamInfo; + } + + private static StreamInfo extractStreams( + StreamInfo streamInfo, StreamExtractor extractor) + throws ExtractionException, IOException { + /* ---- stream extraction goes here ---- */ + // At least one type of stream has to be available, + // otherwise an exception will be thrown directly into the frontend. + + try { + streamInfo.dashMpdUrl = extractor.getDashMpdUrl(); + } catch(Exception e) { + streamInfo.addException(new ExtractionException("Couldn't get Dash manifest", e)); + } + + /* Load and extract audio */ + try { + streamInfo.audio_streams = extractor.getAudioStreams(); + } catch(Exception e) { + streamInfo.addException(new ExtractionException("Couldn't get audio streams", e)); + } + // also try to get streams from the dashMpd + if(streamInfo.dashMpdUrl != null && !streamInfo.dashMpdUrl.isEmpty()) { + if(streamInfo.audio_streams == null) { + streamInfo.audio_streams = new Vector<>(); + } + //todo: make this quick and dirty solution a real fallback + // same as the quick and dirty above + try { + streamInfo.audio_streams.addAll( + DashMpdParser.getAudioStreams(streamInfo.dashMpdUrl)); + } catch(Exception e) { + streamInfo.addException( + new ExtractionException("Couldn't get audio streams from dash mpd", e)); + } + } + /* Extract video stream url*/ + try { + streamInfo.video_streams = extractor.getVideoStreams(); + } catch (Exception e) { + streamInfo.addException( + new ExtractionException("Couldn't get video streams", e)); + } + /* Extract video only stream url*/ + try { + streamInfo.video_only_streams = extractor.getVideoOnlyStreams(); + } catch(Exception e) { + streamInfo.addException( + new ExtractionException("Couldn't get video only streams", e)); + } + + // either dash_mpd audio_only or video has to be available, otherwise we didn't get a stream, + // and therefore failed. (Since video_only_streams are just optional they don't caunt). + if((streamInfo.video_streams == null || streamInfo.video_streams.isEmpty()) + && (streamInfo.audio_streams == null || streamInfo.audio_streams.isEmpty()) + && (streamInfo.dashMpdUrl == null || streamInfo.dashMpdUrl.isEmpty())) { + throw new StreamExctractException( + "Could not get any stream. See error variable to get further details."); + } + + return streamInfo; + } + + private static StreamInfo extractOptionalData( + StreamInfo streamInfo, StreamExtractor extractor) { + /* ---- optional data goes here: ---- */ + // If one of these fails, the frontend needs to handle that they are not available. + // Exceptions are therefore not thrown into the frontend, but stored into the error List, + // so the frontend can afterwards check where errors happened. + + try { + streamInfo.thumbnail_url = extractor.getThumbnailUrl(); + } catch(Exception e) { + streamInfo.addException(e); + } + try { + streamInfo.duration = extractor.getLength(); + } catch(Exception e) { + streamInfo.addException(e); + } + try { + streamInfo.uploader = extractor.getUploader(); + } catch(Exception e) { + streamInfo.addException(e); + } + try { + streamInfo.channel_url = extractor.getChannelUrl(); + } catch(Exception e) { + streamInfo.addException(e); + } + try { + streamInfo.description = extractor.getDescription(); + } catch(Exception e) { + streamInfo.addException(e); + } + try { + streamInfo.view_count = extractor.getViewCount(); + } catch(Exception e) { + streamInfo.addException(e); + } + try { + streamInfo.upload_date = extractor.getUploadDate(); + } catch(Exception e) { + streamInfo.addException(e); + } + try { + streamInfo.uploader_thumbnail_url = extractor.getUploaderThumbnailUrl(); + } catch(Exception e) { + streamInfo.addException(e); + } + try { + streamInfo.start_position = extractor.getTimeStamp(); + } catch(Exception e) { + streamInfo.addException(e); + } + try { + streamInfo.average_rating = extractor.getAverageRating(); + } catch(Exception e) { + streamInfo.addException(e); + } + try { + streamInfo.like_count = extractor.getLikeCount(); + } catch(Exception e) { + streamInfo.addException(e); + } + try { + streamInfo.dislike_count = extractor.getDislikeCount(); + } catch(Exception e) { + streamInfo.addException(e); + } + try { + // get next video + if(streamInfo.next_video != null) + { + StreamInfoItemCollector c = new StreamInfoItemCollector( + extractor.getUrlIdHandler(), extractor.getServiceId()); + StreamInfoItemExtractor nextVideo = extractor.getNextVideo(); + c.commit(nextVideo); + if(c.getItemList().size() != 0) { + streamInfo.next_video = (StreamInfoItem) c.getItemList().get(0); + } + streamInfo.errors.addAll(c.getErrors()); + } + } + catch(Exception e) { + streamInfo.addException(e); + } + try { + // get related videos + StreamInfoItemCollector c = extractor.getRelatedVideos(); + streamInfo.related_streams = c.getItemList(); + streamInfo.errors.addAll(c.getErrors()); + } catch(Exception e) { + streamInfo.addException(e); + } + + return streamInfo; + } + + public String uploader_thumbnail_url = ""; + public String channel_url = ""; + public String description = ""; + + public List video_streams = null; + public List audio_streams = null; + public List video_only_streams = null; + // video streams provided by the dash mpd do not need to be provided as VideoStream. + // Later on this will also aplly to audio streams. Since dash mpd is standarized, + // crawling such a file is not service dependent. Therefore getting audio only streams by yust + // providing the dash mpd fille will be possible in the future. + public String dashMpdUrl = ""; + public int duration = -1; + + public int age_limit = -1; + public int like_count = -1; + public int dislike_count = -1; + public String average_rating = ""; + public StreamInfoItem next_video = null; + public List related_streams = null; + //in seconds. some metadata is not passed using a StreamInfo object! + public int start_position = 0; + + public List errors = new Vector<>(); +} diff --git a/stream_info/StreamInfoItem.java b/stream_info/StreamInfoItem.java new file mode 100644 index 000000000..8a6db5bc0 --- /dev/null +++ b/stream_info/StreamInfoItem.java @@ -0,0 +1,41 @@ +package org.schabi.newpipe.extractor.stream_info; + +/** + * Created by Christian Schabesberger on 26.08.15. + * + * Copyright (C) Christian Schabesberger 2016 + * StreamInfoItem.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +import org.schabi.newpipe.extractor.AbstractStreamInfo; +import org.schabi.newpipe.extractor.InfoItem; + +/**Info object for previews of unopened videos, eg search results, related videos*/ +public class StreamInfoItem extends AbstractStreamInfo implements InfoItem { + public int duration; + + public InfoType infoType() { + return InfoType.STREAM; + } + + public String getTitle() { + return title; + } + + public String getLink() { + return webpage_url; + } +} \ No newline at end of file diff --git a/stream_info/StreamInfoItemCollector.java b/stream_info/StreamInfoItemCollector.java new file mode 100644 index 000000000..03ff7bd83 --- /dev/null +++ b/stream_info/StreamInfoItemCollector.java @@ -0,0 +1,102 @@ +package org.schabi.newpipe.extractor.stream_info; + +import org.schabi.newpipe.extractor.InfoItemCollector; +import org.schabi.newpipe.extractor.NewPipe; +import org.schabi.newpipe.extractor.UrlIdHandler; +import org.schabi.newpipe.extractor.exceptions.FoundAdException; +import org.schabi.newpipe.extractor.exceptions.ParsingException; + +import java.util.List; +import java.util.Vector; + +/** + * Created by Christian Schabesberger on 28.02.16. + * + * Copyright (C) Christian Schabesberger 2016 + * StreamInfoItemCollector.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class StreamInfoItemCollector extends InfoItemCollector { + + private UrlIdHandler urlIdHandler; + + public StreamInfoItemCollector(UrlIdHandler handler, int serviceId) { + super(serviceId); + urlIdHandler = handler; + } + + private UrlIdHandler getUrlIdHandler() { + return urlIdHandler; + } + + public StreamInfoItem extract(StreamInfoItemExtractor extractor) throws Exception { + if(extractor.isAd()) { + throw new FoundAdException("Found ad"); + } + + StreamInfoItem resultItem = new StreamInfoItem(); + // importand information + resultItem.service_id = getServiceId(); + resultItem.webpage_url = extractor.getWebPageUrl(); + if (getUrlIdHandler() == null) { + throw new ParsingException("Error: UrlIdHandler not set"); + } else if (!resultItem.webpage_url.isEmpty()) { + resultItem.id = NewPipe.getService(getServiceId()) + .getStreamUrlIdHandlerInstance() + .getId(resultItem.webpage_url); + } + resultItem.title = extractor.getTitle(); + resultItem.stream_type = extractor.getStreamType(); + + // optional information + try { + resultItem.duration = extractor.getDuration(); + } catch (Exception e) { + addError(e); + } + try { + resultItem.uploader = extractor.getUploader(); + } catch (Exception e) { + addError(e); + } + try { + resultItem.upload_date = extractor.getUploadDate(); + } catch (Exception e) { + addError(e); + } + try { + resultItem.view_count = extractor.getViewCount(); + } catch (Exception e) { + addError(e); + } + try { + resultItem.thumbnail_url = extractor.getThumbnailUrl(); + } catch (Exception e) { + addError(e); + } + return resultItem; + } + + public void commit(StreamInfoItemExtractor extractor) throws ParsingException { + try { + addItem(extract(extractor)); + } catch(FoundAdException ae) { + //System.out.println("AD_WARNING: " + ae.getMessage()); + } catch (Exception e) { + addError(e); + } + } +} diff --git a/stream_info/StreamInfoItemExtractor.java b/stream_info/StreamInfoItemExtractor.java new file mode 100644 index 000000000..b5432b42d --- /dev/null +++ b/stream_info/StreamInfoItemExtractor.java @@ -0,0 +1,36 @@ +package org.schabi.newpipe.extractor.stream_info; + +import org.schabi.newpipe.extractor.AbstractStreamInfo; +import org.schabi.newpipe.extractor.exceptions.ParsingException; + +/** + * Created by Christian Schabesberger on 28.02.16. + * + * Copyright (C) Christian Schabesberger 2016 + * StreamInfoItemExtractor.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public interface StreamInfoItemExtractor { + AbstractStreamInfo.StreamType getStreamType() throws ParsingException; + String getWebPageUrl() throws ParsingException; + String getTitle() throws ParsingException; + int getDuration() throws ParsingException; + String getUploader() throws ParsingException; + String getUploadDate() throws ParsingException; + long getViewCount() throws ParsingException; + String getThumbnailUrl() throws ParsingException; + boolean isAd() throws ParsingException; +} diff --git a/stream_info/VideoStream.java b/stream_info/VideoStream.java new file mode 100644 index 000000000..c3e12fdbd --- /dev/null +++ b/stream_info/VideoStream.java @@ -0,0 +1,44 @@ +package org.schabi.newpipe.extractor.stream_info; + +/** + * Created by Christian Schabesberger on 04.03.16. + * + * Copyright (C) Christian Schabesberger 2016 + * VideoStream.java is part of NewPipe. + * + * NewPipe is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * NewPipe is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with NewPipe. If not, see . + */ + +public class VideoStream { + //url of the stream + public String url = ""; + public int format = -1; + public String resolution = ""; + + public VideoStream(String url, int format, String res) { + this.url = url; this.format = format; resolution = res; + } + + // reveals wether two streams are the same, but have diferent urls + public boolean equalStats(VideoStream cmp) { + return format == cmp.format + && resolution == cmp.resolution; + } + + // revelas wether two streams are equal + public boolean equals(VideoStream cmp) { + return cmp != null && equalStats(cmp) + && url == cmp.url; + } +}