X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/46113edab215c2211a604c06245c16d5d4e57dcf..c64c42cb1f9487398f8b91a51266ff6e79115b90:/youtube_dl/extractor/cnn.py?ds=sidebyside diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py index 78877b1..53489a1 100644 --- a/youtube_dl/extractor/cnn.py +++ b/youtube_dl/extractor/cnn.py @@ -11,36 +11,53 @@ from ..utils import ( class CNNIE(InfoExtractor): - _VALID_URL = r'''(?x)https?://((edition|www)\.)?cnn\.com/video/(data/.+?|\?)/ - (?P.+?/(?P[^/]+?)(?:\.cnn(-ap)?|(?=&)))''' + _VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/ + (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z\-]+)|(?=&)))''' _TESTS = [{ 'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn', - 'file': 'sports_2013_06_09_nadal-1-on-1.cnn.mp4', 'md5': '3e6121ea48df7e2259fe73a0628605c4', 'info_dict': { + 'id': 'sports/2013/06/09/nadal-1-on-1.cnn', + 'ext': 'mp4', 'title': 'Nadal wins 8th French Open title', 'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.', 'duration': 135, 'upload_date': '20130609', }, - }, - { - "url": "http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29", - "file": "us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4", - "md5": "b5cc60c60a3477d185af8f19a2a26f4e", - "info_dict": { - "title": "Student's epic speech stuns new freshmen", - "description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"", - "upload_date": "20130821", + }, { + 'url': 'http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29', + 'md5': 'b5cc60c60a3477d185af8f19a2a26f4e', + 'info_dict': { + 'id': 'us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology', + 'ext': 'mp4', + 'title': "Student's epic speech stuns new freshmen", + 'description': "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"", + 'upload_date': '20130821', + } + }, { + 'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html', + 'md5': 'f14d02ebd264df951feb2400e2c25a1b', + 'info_dict': { + 'id': 'living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln', + 'ext': 'mp4', + 'title': 'Nashville Ep. 1: Hand crafted skateboards', + 'description': 'md5:e7223a503315c9f150acac52e76de086', + 'upload_date': '20141222', } + }, { + 'url': 'http://cnn.com/video/?/video/politics/2015/03/27/pkg-arizona-senator-church-attendance-mandatory.ktvk', + 'only_matching': True, + }, { + 'url': 'http://cnn.com/video/?/video/us/2015/04/06/dnt-baker-refuses-anti-gay-order.wkmg', + 'only_matching': True, }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) path = mobj.group('path') page_title = mobj.group('title') - info_url = 'http://cnn.com/video/data/3.0/%s/index.xml' % path + info_url = 'http://edition.cnn.com/video/data/3.0/%s/index.xml' % path info = self._download_xml(info_url, page_title) formats = [] @@ -126,3 +143,28 @@ class CNNBlogsIE(InfoExtractor): 'url': cnn_url, 'ie_key': CNNIE.ie_key(), } + + +class CNNArticleIE(InfoExtractor): + _VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!video/)' + _TEST = { + 'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/', + 'md5': '689034c2a3d9c6dc4aa72d65a81efd01', + 'info_dict': { + 'id': 'bestoftv/2014/12/21/ip-north-korea-obama.cnn', + 'ext': 'mp4', + 'title': 'Obama: Cyberattack not an act of war', + 'description': 'md5:51ce6750450603795cad0cdfbd7d05c5', + 'upload_date': '20141221', + }, + 'add_ie': ['CNN'], + } + + def _real_extract(self, url): + webpage = self._download_webpage(url, url_basename(url)) + cnn_url = self._html_search_regex(r"video:\s*'([^']+)'", webpage, 'cnn url') + return { + '_type': 'url', + 'url': 'http://cnn.com/video/?/video/' + cnn_url, + 'ie_key': CNNIE.ie_key(), + }