NewPipeExtractor/extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/extractors/YoutubeTrendingExtractor.java

157 lines
7.0 KiB
Java
Raw Normal View History

2022-11-09 04:34:16 +01:00
/*
* Created by Christian Schabesberger on 12.08.17.
*
* Copyright (C) Christian Schabesberger 2018 <chris.schabesberger@mailbox.org>
* YoutubeTrendingExtractor.java is part of NewPipe Extractor.
*
* NewPipe Extractor 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 Extractor 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 Extractor. If not, see <https://www.gnu.org/licenses/>.
*/
package org.schabi.newpipe.extractor.services.youtube.extractors;
2017-08-12 21:10:21 +02:00
2022-07-28 04:19:21 +02:00
import static org.schabi.newpipe.extractor.services.youtube.YoutubeParsingHelper.getJsonPostResponse;
import static org.schabi.newpipe.extractor.services.youtube.YoutubeParsingHelper.getTextAtKey;
import static org.schabi.newpipe.extractor.services.youtube.YoutubeParsingHelper.prepareDesktopJsonBuilder;
import static org.schabi.newpipe.extractor.utils.Utils.isNullOrEmpty;
import com.grack.nanojson.JsonObject;
import com.grack.nanojson.JsonWriter;
2020-04-15 14:09:46 +02:00
import org.schabi.newpipe.extractor.Page;
2018-03-01 01:02:43 +01:00
import org.schabi.newpipe.extractor.StreamingService;
import org.schabi.newpipe.extractor.downloader.Downloader;
2017-08-12 21:10:21 +02:00
import org.schabi.newpipe.extractor.exceptions.ExtractionException;
2017-08-13 00:58:29 +02:00
import org.schabi.newpipe.extractor.exceptions.ParsingException;
2017-08-12 21:10:21 +02:00
import org.schabi.newpipe.extractor.kiosk.KioskExtractor;
import org.schabi.newpipe.extractor.linkhandler.ListLinkHandler;
import org.schabi.newpipe.extractor.localization.TimeAgoParser;
2018-03-01 01:02:43 +01:00
import org.schabi.newpipe.extractor.stream.StreamInfoItem;
2018-02-24 22:20:50 +01:00
import org.schabi.newpipe.extractor.stream.StreamInfoItemsCollector;
2017-08-13 00:58:29 +02:00
2017-08-12 21:10:21 +02:00
import java.io.IOException;
2022-07-28 04:19:21 +02:00
import java.nio.charset.StandardCharsets;
2017-08-12 21:10:21 +02:00
import javax.annotation.Nonnull;
2019-01-28 12:18:16 +01:00
public class YoutubeTrendingExtractor extends KioskExtractor<StreamInfoItem> {
private JsonObject initialData;
2017-08-13 00:58:29 +02:00
public YoutubeTrendingExtractor(final StreamingService service,
final ListLinkHandler linkHandler,
final String kioskId) {
super(service, linkHandler, kioskId);
2017-08-12 21:10:21 +02:00
}
@Override
2022-03-18 15:09:06 +01:00
public void onFetchPage(@Nonnull final Downloader downloader)
throws IOException, ExtractionException {
// @formatter:off
Rebase + some code improvements + fix extraction of age-restricted videos + update clients version Here is now the requests which will be made by the `onFetchPage` method of `YoutubeStreamExtractor`: - the desktop API is fetched. If there is no streaming data, the desktop player API with the embed client screen will be fetched (and also the player code), then the Android mobile API. - if there is no streaming data, a `ContentNotAvailableException` will be thrown by using the message provided in playability status If the video is age restricted, a request to the next endpoint of the desktop player with the embed client screen will be sent. Otherwise, the next endpoint will be fetched normally, if the content is available. If the video is not age-restricted, a request to the player endpoint of the Android mobile API will be made. We can get more streams by using the Android mobile API but some streams may be not available on this API, so the streaming data of the Android mobile API will be first used to get itags and then the streaming data of the desktop internal API will be used. If the parsing of the Android mobile API went wrong, only the streams of the desktop API will be used. Other code changes: - `prepareJsonBuilder` in `YoutubeParsingHelper` was renamed to `prepareDesktopJsonBuilder` - `prepareMobileJsonBuilder` in `YoutubeParsingHelper` was renamed to `prepareAndroidMobileJsonBuilder` - two new methods in `YoutubeParsingHelper` were added: `prepareDesktopEmbedVideoJsonBuilder` and `prepareAndroidMobileEmbedVideoJsonBuilder` - `createPlayerBodyWithSts` is now public and was moved to `YoutubeParsingHelper` - a new method in `YoutubeJavaScriptExtractor` was added: `resetJavaScriptCode`, which was needed for the method `resetDebofuscationCode` of `YoutubeStreamExtractor` - `areHardcodedClientVersionAndKeyValid` in `YoutubeParsingHelper` returns now a `boolean` instead of an `Optional<Boolean>` - the `fetchVideoInfoPage` method of `YoutubeStreamExtractor` was removed because YouTube returns now 404 for every client with the `get_video_info` page - some unused objects and some warnings in `YoutubeStreamExtractor` were removed and fixed Co-authored-by: TiA4f8R <74829229+TiA4f8R@users.noreply.github.com>
2021-07-28 23:55:09 +02:00
final byte[] body = JsonWriter.string(prepareDesktopJsonBuilder(getExtractorLocalization(),
getExtractorContentCountry())
.value("browseId", "FEtrending")
.done())
2022-07-28 04:19:21 +02:00
.getBytes(StandardCharsets.UTF_8);
// @formatter:on
initialData = getJsonPostResponse("browse", body, getExtractorLocalization());
2017-08-12 21:10:21 +02:00
}
2018-02-26 15:55:27 +01:00
@Override
public InfoItemsPage<StreamInfoItem> getPage(final Page page) {
return InfoItemsPage.emptyPage();
2017-08-12 21:10:21 +02:00
}
@Nonnull
@Override
public String getName() throws ParsingException {
2021-02-12 22:22:11 +01:00
final JsonObject header = initialData.getObject("header");
2021-03-24 09:04:43 +01:00
String name = null;
2021-02-12 22:22:11 +01:00
if (header.has("feedTabbedHeaderRenderer")) {
2021-03-24 09:04:43 +01:00
name = getTextAtKey(header.getObject("feedTabbedHeaderRenderer"), "title");
2021-02-12 22:22:11 +01:00
} else if (header.has("c4TabbedHeaderRenderer")) {
2021-03-24 09:04:43 +01:00
name = getTextAtKey(header.getObject("c4TabbedHeaderRenderer"), "title");
2021-02-12 22:22:11 +01:00
}
2021-03-24 09:04:43 +01:00
if (isNullOrEmpty(name)) {
throw new ParsingException("Could not get Trending name");
}
2021-03-24 09:04:43 +01:00
return name;
}
2017-11-25 02:03:30 +01:00
@Nonnull
2017-08-12 21:10:21 +02:00
@Override
public InfoItemsPage<StreamInfoItem> getInitialPage() throws ParsingException {
2022-03-18 15:09:06 +01:00
final StreamInfoItemsCollector collector = new StreamInfoItemsCollector(getServiceId());
final TimeAgoParser timeAgoParser = getTimeAgoParser();
final JsonObject tabContent = getTrendingTabContent();
if (tabContent.has("richGridRenderer")) {
tabContent.getObject("richGridRenderer")
.getArray("contents")
.stream()
.filter(JsonObject.class::isInstance)
.map(JsonObject.class::cast)
// Filter Trending shorts and Recently trending sections
.filter(content -> content.has("richItemRenderer"))
.map(content -> content.getObject("richItemRenderer")
.getObject("content")
.getObject("videoRenderer"))
.forEachOrdered(videoRenderer -> collector.commit(
new YoutubeStreamInfoItemExtractor(videoRenderer, timeAgoParser)));
} else if (tabContent.has("sectionListRenderer")) {
tabContent.getObject("sectionListRenderer")
.getArray("contents")
.stream()
.filter(JsonObject.class::isInstance)
.map(JsonObject.class::cast)
.flatMap(content -> content.getObject("itemSectionRenderer")
.getArray("contents")
.stream())
.filter(JsonObject.class::isInstance)
.map(JsonObject.class::cast)
.map(content -> content.getObject("shelfRenderer"))
// Filter Trending shorts and Recently trending sections which have a title,
// contrary to normal trends
.filter(shelfRenderer -> !shelfRenderer.has("title"))
.flatMap(shelfRenderer -> shelfRenderer.getObject("content")
.getObject("expandedShelfContentsRenderer")
.getArray("items")
.stream())
.filter(JsonObject.class::isInstance)
.map(JsonObject.class::cast)
.map(item -> item.getObject("videoRenderer"))
.forEachOrdered(videoRenderer -> collector.commit(
new YoutubeStreamInfoItemExtractor(videoRenderer, timeAgoParser)));
2017-08-13 00:58:29 +02:00
}
return new InfoItemsPage<>(collector, null);
2017-08-12 21:10:21 +02:00
}
private JsonObject getTrendingTabContent() throws ParsingException {
return initialData.getObject("contents")
.getObject("twoColumnBrowseResultsRenderer")
.getArray("tabs")
.stream()
.filter(JsonObject.class::isInstance)
.map(JsonObject.class::cast)
.map(tab -> tab.getObject("tabRenderer"))
.filter(tabRenderer -> tabRenderer.getBoolean("selected"))
.filter(tabRenderer -> tabRenderer.has("content"))
// There should be at most one tab selected
.findFirst()
.orElseThrow(() -> new ParsingException("Could not get \"Now\" trending tab"))
.getObject("content");
}
2017-08-12 21:10:21 +02:00
}