From 159736c1b81e2897e91369f399eceacaa09192b4 Mon Sep 17 00:00:00 2001 From: "M.Yasoob Khalid" Date: Sat, 13 Jul 2013 09:17:48 +0500 Subject: [PATCH 1/2] added an IE for criterion.com --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/criterion.py | 31 +++++++++++++++++++++++++++++++ 2 files changed, 32 insertions(+) create mode 100644 youtube_dl/extractor/criterion.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index c00d5a352..494b1b9d3 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -8,6 +8,7 @@ from .breakcom import BreakIE from .brightcove import BrightcoveIE from .collegehumor import CollegeHumorIE from .comedycentral import ComedyCentralIE +from .criterion import CriterionIE from .cspan import CSpanIE from .dailymotion import DailymotionIE from .depositfiles import DepositFilesIE diff --git a/youtube_dl/extractor/criterion.py b/youtube_dl/extractor/criterion.py new file mode 100644 index 000000000..d1fe7fc3c --- /dev/null +++ b/youtube_dl/extractor/criterion.py @@ -0,0 +1,31 @@ +# -*- coding: utf-8 -*- + +import re + +from .common import InfoExtractor + +class CriterionIE(InfoExtractor): + _VALID_URL = r'http://www.criterion.com/films/(.*)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group(1).split('-')[0] + webpage = self._download_webpage(url, video_id) + + final_url = self._search_regex(r'so.addVariable\("videoURL", "(.+?)"\)\;', + webpage, 'video url') + title = self._search_regex(r'', + webpage, 'video title') + description = self._search_regex(r'', + webpage, 'video description') + thumbnail = self._search_regex(r'so.addVariable\("thumbnailURL", "(.+?)"\)\;', + webpage, 'thumbnail url') + ext = final_url.split('.')[-1] + + return {'id': video_id, + 'url' : final_url, + 'title': title, + 'ext': ext, + 'description': description, + 'thumbnail': thumbnail, + } From 2d5a8b55129b1dc10f9e789875b46742c8f303af Mon Sep 17 00:00:00 2001 From: "M.Yasoob Khalid" Date: Sat, 13 Jul 2013 09:18:03 +0500 Subject: [PATCH 2/2] added test for criterion.com --- youtube_dl/extractor/criterion.py | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/youtube_dl/extractor/criterion.py b/youtube_dl/extractor/criterion.py index d1fe7fc3c..a149d2900 100644 --- a/youtube_dl/extractor/criterion.py +++ b/youtube_dl/extractor/criterion.py @@ -6,6 +6,15 @@ from .common import InfoExtractor class CriterionIE(InfoExtractor): _VALID_URL = r'http://www.criterion.com/films/(.*)' + _TEST = { + u'url': u'http://www.criterion.com/films/184-le-samourai', + u'file': u'184.mp4', + u'md5': u'bc51beba55685509883a9a7830919ec3', + u'info_dict': { + u"title": u"Le Samouraï", + u"description" : u"In a career-defining performance, Alain Delon plays a contract killer with samurai instincts. A razor-sharp cocktail of 1940s American gangster cinema and 1960s French pop culture, maverick director Jean-Pierre Melville's masterpiece _Le Samouraï_ defines cool. " + } + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url)