yt_dlp/extractor/cnn.py

   1 from __future__ import unicode_literals
   2
   3
   4 from .common import InfoExtractor
   5 from .turner import TurnerBaseIE
   6 from ..utils import url_basename
   7
   8
   9 class CNNIE(TurnerBaseIE):
  10     _VALID_URL = r'''(?x)https?://(?:(?P<sub_domain>edition|www|money)\.)?cnn\.com/(?:video/(?:data/.+?|\?)/)?videos?/
  11         (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z\-]+)|(?=&)))'''
  12
  13     _TESTS = [{
  14         'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
  15         'md5': '3e6121ea48df7e2259fe73a0628605c4',
  16         'info_dict': {
  17             'id': 'sports/2013/06/09/nadal-1-on-1.cnn',
  18             'ext': 'mp4',
  19             'title': 'Nadal wins 8th French Open title',
  20             'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
  21             'duration': 135,
  22             'upload_date': '20130609',
  23         },
  24         'expected_warnings': ['Failed to download m3u8 information'],
  25     }, {
  26         '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',
  27         'md5': 'b5cc60c60a3477d185af8f19a2a26f4e',
  28         'info_dict': {
  29             'id': 'us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology',
  30             'ext': 'mp4',
  31             'title': "Student's epic speech stuns new freshmen",
  32             'description': "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
  33             'upload_date': '20130821',
  34         },
  35         'expected_warnings': ['Failed to download m3u8 information'],
  36     }, {
  37         'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html',
  38         'md5': 'f14d02ebd264df951feb2400e2c25a1b',
  39         'info_dict': {
  40             'id': 'living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln',
  41             'ext': 'mp4',
  42             'title': 'Nashville Ep. 1: Hand crafted skateboards',
  43             'description': 'md5:e7223a503315c9f150acac52e76de086',
  44             'upload_date': '20141222',
  45         },
  46         'expected_warnings': ['Failed to download m3u8 information'],
  47     }, {
  48         'url': 'http://money.cnn.com/video/news/2016/08/19/netflix-stunning-stats.cnnmoney/index.html',
  49         'md5': '52a515dc1b0f001cd82e4ceda32be9d1',
  50         'info_dict': {
  51             'id': '/video/news/2016/08/19/netflix-stunning-stats.cnnmoney',
  52             'ext': 'mp4',
  53             'title': '5 stunning stats about Netflix',
  54             '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.',
  55             'upload_date': '20160819',
  56         },
  57         'params': {
  58             # m3u8 download
  59             'skip_download': True,
  60         },
  61     }, {
  62         'url': 'http://cnn.com/video/?/video/politics/2015/03/27/pkg-arizona-senator-church-attendance-mandatory.ktvk',
  63         'only_matching': True,
  64     }, {
  65         'url': 'http://cnn.com/video/?/video/us/2015/04/06/dnt-baker-refuses-anti-gay-order.wkmg',
  66         'only_matching': True,
  67     }, {
  68         'url': 'http://edition.cnn.com/videos/arts/2016/04/21/olympic-games-cultural-a-z-brazil.cnn',
  69         'only_matching': True,
  70     }]
  71
  72     _CONFIG = {
  73         # http://edition.cnn.com/.element/apps/cvp/3.0/cfg/spider/cnn/expansion/config.xml
  74         'edition': {
  75             'data_src': 'http://edition.cnn.com/video/data/3.0/video/%s/index.xml',
  76             'media_src': 'http://pmd.cdn.turner.com/cnn/big',
  77         },
  78         # http://money.cnn.com/.element/apps/cvp2/cfg/config.xml
  79         'money': {
  80             'data_src': 'http://money.cnn.com/video/data/4.0/video/%s.xml',
  81             'media_src': 'http://ht3.cdn.turner.com/money/big',
  82         },
  83     }
  84
  85     def _extract_timestamp(self, video_data):
  86         # TODO: fix timestamp extraction
  87         return None
  88
  89     def _real_extract(self, url):
  90         sub_domain, path, page_title = self._match_valid_url(url).groups()
  91         if sub_domain not in ('money', 'edition'):
  92             sub_domain = 'edition'
  93         config = self._CONFIG[sub_domain]
  94         return self._extract_cvp_info(
  95             config['data_src'] % path, page_title, {
  96                 'default': {
  97                     'media_src': config['media_src'],
  98                 },
  99                 'f4m': {
 100                     'host': 'cnn-vh.akamaihd.net',
 101                 },
 102             })
 103
 104
 105 class CNNBlogsIE(InfoExtractor):
 106     _VALID_URL = r'https?://[^\.]+\.blogs\.cnn\.com/.+'
 107     _TEST = {
 108         'url': 'http://reliablesources.blogs.cnn.com/2014/02/09/criminalizing-journalism/',
 109         'md5': '3e56f97b0b6ffb4b79f4ea0749551084',
 110         'info_dict': {
 111             'id': 'bestoftv/2014/02/09/criminalizing-journalism.cnn',
 112             'ext': 'mp4',
 113             'title': 'Criminalizing journalism?',
 114             'description': 'Glenn Greenwald responds to comments made this week on Capitol Hill that journalists could be criminal accessories.',
 115             'upload_date': '20140209',
 116         },
 117         'expected_warnings': ['Failed to download m3u8 information'],
 118         'add_ie': ['CNN'],
 119     }
 120
 121     def _real_extract(self, url):
 122         webpage = self._download_webpage(url, url_basename(url))
 123         cnn_url = self._html_search_regex(r'data-url="(.+?)"', webpage, 'cnn url')
 124         return self.url_result(cnn_url, CNNIE.ie_key())
 125
 126
 127 class CNNArticleIE(InfoExtractor):
 128     _VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!videos?/)'
 129     _TEST = {
 130         'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/',
 131         'md5': '689034c2a3d9c6dc4aa72d65a81efd01',
 132         'info_dict': {
 133             'id': 'bestoftv/2014/12/21/ip-north-korea-obama.cnn',
 134             'ext': 'mp4',
 135             'title': 'Obama: Cyberattack not an act of war',
 136             'description': 'md5:0a802a40d2376f60e6b04c8d5bcebc4b',
 137             'upload_date': '20141221',
 138         },
 139         'expected_warnings': ['Failed to download m3u8 information'],
 140         'add_ie': ['CNN'],
 141     }
 142
 143     def _real_extract(self, url):
 144         webpage = self._download_webpage(url, url_basename(url))
 145         cnn_url = self._html_search_regex(r"video:\s*'([^']+)'", webpage, 'cnn url')
 146         return self.url_result('http://cnn.com/video/?/video/' + cnn_url, CNNIE.ie_key())