[turner] keep video id intact

This commit is contained in:
Remita Amine 2016-08-30 10:46:48 +01:00
parent da30a20a4d
commit 3c77a54d5d
3 changed files with 14 additions and 11 deletions

View file

@ -15,7 +15,7 @@ class CNNIE(TurnerBaseIE):
'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn', 'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
'md5': '3e6121ea48df7e2259fe73a0628605c4', 'md5': '3e6121ea48df7e2259fe73a0628605c4',
'info_dict': { 'info_dict': {
'id': 'nadal-1-on-1', 'id': 'sports/2013/06/09/nadal-1-on-1.cnn',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Nadal wins 8th French Open title', 'title': 'Nadal wins 8th French Open title',
'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.', 'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
@ -27,7 +27,7 @@ class CNNIE(TurnerBaseIE):
'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', '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', 'md5': 'b5cc60c60a3477d185af8f19a2a26f4e',
'info_dict': { 'info_dict': {
'id': 'sot-student-gives-epic-speech', 'id': 'us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology',
'ext': 'mp4', 'ext': 'mp4',
'title': "Student's epic speech stuns new freshmen", '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.\"", 'description': "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
@ -38,7 +38,7 @@ class CNNIE(TurnerBaseIE):
'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html', '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', 'md5': 'f14d02ebd264df951feb2400e2c25a1b',
'info_dict': { 'info_dict': {
'id': 'growing-america-nashville-salemtown-board-episode-1', 'id': 'living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Nashville Ep. 1: Hand crafted skateboards', 'title': 'Nashville Ep. 1: Hand crafted skateboards',
'description': 'md5:e7223a503315c9f150acac52e76de086', 'description': 'md5:e7223a503315c9f150acac52e76de086',
@ -49,7 +49,7 @@ class CNNIE(TurnerBaseIE):
'url': 'http://money.cnn.com/video/news/2016/08/19/netflix-stunning-stats.cnnmoney/index.html', 'url': 'http://money.cnn.com/video/news/2016/08/19/netflix-stunning-stats.cnnmoney/index.html',
'md5': '52a515dc1b0f001cd82e4ceda32be9d1', 'md5': '52a515dc1b0f001cd82e4ceda32be9d1',
'info_dict': { 'info_dict': {
'id': 'netflix-stunning-stats', 'id': '/video/news/2016/08/19/netflix-stunning-stats.cnnmoney',
'ext': 'mp4', 'ext': 'mp4',
'title': '5 stunning stats about Netflix', 'title': '5 stunning stats about Netflix',
'description': 'Did you know that Netflix has more than 80 million members? Here are five facts about the online video distributor that you probably didn\'t know.', 'description': 'Did you know that Netflix has more than 80 million members? Here are five facts about the online video distributor that you probably didn\'t know.',
@ -106,7 +106,7 @@ class CNNBlogsIE(InfoExtractor):
'url': 'http://reliablesources.blogs.cnn.com/2014/02/09/criminalizing-journalism/', 'url': 'http://reliablesources.blogs.cnn.com/2014/02/09/criminalizing-journalism/',
'md5': '3e56f97b0b6ffb4b79f4ea0749551084', 'md5': '3e56f97b0b6ffb4b79f4ea0749551084',
'info_dict': { 'info_dict': {
'id': 'criminalizing-journalism', 'id': 'bestoftv/2014/02/09/criminalizing-journalism.cnn',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Criminalizing journalism?', 'title': 'Criminalizing journalism?',
'description': 'Glenn Greenwald responds to comments made this week on Capitol Hill that journalists could be criminal accessories.', 'description': 'Glenn Greenwald responds to comments made this week on Capitol Hill that journalists could be criminal accessories.',
@ -132,7 +132,7 @@ class CNNArticleIE(InfoExtractor):
'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/', 'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/',
'md5': '689034c2a3d9c6dc4aa72d65a81efd01', 'md5': '689034c2a3d9c6dc4aa72d65a81efd01',
'info_dict': { 'info_dict': {
'id': 'ip-north-korea-obama', 'id': 'bestoftv/2014/12/21/ip-north-korea-obama.cnn',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Obama: Cyberattack not an act of war', 'title': 'Obama: Cyberattack not an act of war',
'description': 'md5:0a802a40d2376f60e6b04c8d5bcebc4b', 'description': 'md5:0a802a40d2376f60e6b04c8d5bcebc4b',

View file

@ -39,18 +39,19 @@ class NBAIE(TurnerBaseIE):
'url': 'http://watch.nba.com/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba', 'url': 'http://watch.nba.com/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba',
'md5': 'b2b39b81cf28615ae0c3360a3f9668c4', 'md5': 'b2b39b81cf28615ae0c3360a3f9668c4',
'info_dict': { 'info_dict': {
'id': '0041400301-cle-atl-recap', 'id': 'channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Hawks vs. Cavaliers Game 1', 'title': 'Hawks vs. Cavaliers Game 1',
'description': 'md5:8094c3498d35a9bd6b1a8c396a071b4d', 'description': 'md5:8094c3498d35a9bd6b1a8c396a071b4d',
'duration': 228, 'duration': 228,
'timestamp': 1432134543, 'timestamp': 1432134543,
'upload_date': '20150520', 'upload_date': '20150520',
} },
'expected_warnings': ['Unable to download f4m manifest'],
}, { }, {
'url': 'http://www.nba.com/clippers/news/doc-rivers-were-not-trading-blake', 'url': 'http://www.nba.com/clippers/news/doc-rivers-were-not-trading-blake',
'info_dict': { 'info_dict': {
'id': '1455672027478-Doc_Feb16_720', 'id': 'teams/clippers/2016/02/17/1455672027478-Doc_Feb16_720.mov-297324',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Practice: Doc Rivers - 2/16/16', 'title': 'Practice: Doc Rivers - 2/16/16',
'description': 'Head Coach Doc Rivers addresses the media following practice.', 'description': 'Head Coach Doc Rivers addresses the media following practice.',
@ -61,6 +62,7 @@ class NBAIE(TurnerBaseIE):
# m3u8 download # m3u8 download
'skip_download': True, 'skip_download': True,
}, },
'expected_warnings': ['Unable to download f4m manifest'],
}, { }, {
'url': 'http://www.nba.com/timberwolves/wiggins-shootaround#', 'url': 'http://www.nba.com/timberwolves/wiggins-shootaround#',
'info_dict': { 'info_dict': {
@ -75,7 +77,7 @@ class NBAIE(TurnerBaseIE):
}, { }, {
'url': 'http://www.nba.com/timberwolves/wiggins-shootaround#', 'url': 'http://www.nba.com/timberwolves/wiggins-shootaround#',
'info_dict': { 'info_dict': {
'id': 'Wigginsmp4-3462601', 'id': 'teams/timberwolves/2014/12/12/Wigginsmp4-3462601',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Shootaround Access - Dec. 12 | Andrew Wiggins', 'title': 'Shootaround Access - Dec. 12 | Andrew Wiggins',
'description': 'Wolves rookie Andrew Wiggins addresses the media after Friday\'s shootaround.', 'description': 'Wolves rookie Andrew Wiggins addresses the media after Friday\'s shootaround.',
@ -87,6 +89,7 @@ class NBAIE(TurnerBaseIE):
# m3u8 download # m3u8 download
'skip_download': True, 'skip_download': True,
}, },
'expected_warnings': ['Unable to download f4m manifest'],
}] }]
_PAGE_SIZE = 30 _PAGE_SIZE = 30

View file

@ -22,7 +22,7 @@ def _extract_timestamp(self, video_data):
def _extract_cvp_info(self, data_src, video_id, path_data={}): def _extract_cvp_info(self, data_src, video_id, path_data={}):
video_data = self._download_xml(data_src, video_id) video_data = self._download_xml(data_src, video_id)
video_id = video_data.attrib['id'].split('/')[-1].split('.')[0] video_id = video_data.attrib['id']
title = xpath_text(video_data, 'headline', fatal=True) title = xpath_text(video_data, 'headline', fatal=True)
# rtmp_src = xpath_text(video_data, 'akamai/src') # rtmp_src = xpath_text(video_data, 'akamai/src')
# if rtmp_src: # if rtmp_src: