youtube_dl/extractor/cnn.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from .turner import TurnerBaseIE
   7 from ..utils import url_basename
   8
   9
  10 class CNNIE(TurnerBaseIE):
  11     _VALID_URL = r'''(?x)https?://(?:(?P<sub_domain>edition|www|money)\.)?cnn\.com/(?:video/(?:data/.+?|\?)/)?videos?/
  12         (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z\-]+)|(?=&)))'''
  13
  14     _TESTS = [{
  15         'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
  16         'md5': '3e6121ea48df7e2259fe73a0628605c4',
  17         'info_dict': {
  18             'id': 'sports/2013/06/09/nadal-1-on-1.cnn',
  19             'ext': 'mp4',
  20             'title': 'Nadal wins 8th French Open title',
  21             'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
  22             'duration': 135,
  23             'upload_date': '20130609',
  24         },
  25         'expected_warnings': ['Failed to download m3u8 information'],
  26     }, {
  27         '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',
  28         'md5': 'b5cc60c60a3477d185af8f19a2a26f4e',
  29         'info_dict': {
  30             'id': 'us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology',
  31             'ext': 'mp4',
  32             'title': "Student's epic speech stuns new freshmen",
  33             'description': "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
  34             'upload_date': '20130821',
  35         },
  36         'expected_warnings': ['Failed to download m3u8 information'],
  37     }, {
  38         'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html',
  39         'md5': 'f14d02ebd264df951feb2400e2c25a1b',
  40         'info_dict': {
  41             'id': 'living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln',
  42             'ext': 'mp4',
  43             'title': 'Nashville Ep. 1: Hand crafted skateboards',
  44             'description': 'md5:e7223a503315c9f150acac52e76de086',
  45             'upload_date': '20141222',
  46         },
  47         'expected_warnings': ['Failed to download m3u8 information'],
  48     }, {
  49         'url': 'http://money.cnn.com/video/news/2016/08/19/netflix-stunning-stats.cnnmoney/index.html',
  50         'md5': '52a515dc1b0f001cd82e4ceda32be9d1',
  51         'info_dict': {
  52             'id': '/video/news/2016/08/19/netflix-stunning-stats.cnnmoney',
  53             'ext': 'mp4',
  54             'title': '5 stunning stats about Netflix',
  55             '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.',
  56             'upload_date': '20160819',
  57         },
  58         'params': {
  59             # m3u8 download
  60             'skip_download': True,
  61         },
  62     }, {
  63         'url': 'http://cnn.com/video/?/video/politics/2015/03/27/pkg-arizona-senator-church-attendance-mandatory.ktvk',
  64         'only_matching': True,
  65     }, {
  66         'url': 'http://cnn.com/video/?/video/us/2015/04/06/dnt-baker-refuses-anti-gay-order.wkmg',
  67         'only_matching': True,
  68     }, {
  69         'url': 'http://edition.cnn.com/videos/arts/2016/04/21/olympic-games-cultural-a-z-brazil.cnn',
  70         'only_matching': True,
  71     }]
  72
  73     _CONFIG = {
  74         # http://edition.cnn.com/.element/apps/cvp/3.0/cfg/spider/cnn/expansion/config.xml
  75         'edition': {
  76             'data_src': 'http://edition.cnn.com/video/data/3.0/video/%s/index.xml',
  77             'media_src': 'http://pmd.cdn.turner.com/cnn/big',
  78         },
  79         # http://money.cnn.com/.element/apps/cvp2/cfg/config.xml
  80         'money': {
  81             'data_src': 'http://money.cnn.com/video/data/4.0/video/%s.xml',
  82             'media_src': 'http://ht3.cdn.turner.com/money/big',
  83         },
  84     }
  85
  86     def _extract_timestamp(self, video_data):
  87         # TODO: fix timestamp extraction
  88         return None
  89
  90     def _real_extract(self, url):
  91         sub_domain, path, page_title = re.match(self._VALID_URL, url).groups()
  92         if sub_domain not in ('money', 'edition'):
  93             sub_domain = 'edition'
  94         config = self._CONFIG[sub_domain]
  95         return self._extract_cvp_info(
  96             config['data_src'] % path, page_title, {
  97                 'default': {
  98                     'media_src': config['media_src'],
  99                 }
 100             })
 101
 102
 103 class CNNBlogsIE(InfoExtractor):
 104     _VALID_URL = r'https?://[^\.]+\.blogs\.cnn\.com/.+'
 105     _TEST = {
 106         'url': 'http://reliablesources.blogs.cnn.com/2014/02/09/criminalizing-journalism/',
 107         'md5': '3e56f97b0b6ffb4b79f4ea0749551084',
 108         'info_dict': {
 109             'id': 'bestoftv/2014/02/09/criminalizing-journalism.cnn',
 110             'ext': 'mp4',
 111             'title': 'Criminalizing journalism?',
 112             'description': 'Glenn Greenwald responds to comments made this week on Capitol Hill that journalists could be criminal accessories.',
 113             'upload_date': '20140209',
 114         },
 115         'expected_warnings': ['Failed to download m3u8 information'],
 116         'add_ie': ['CNN'],
 117     }
 118
 119     def _real_extract(self, url):
 120         webpage = self._download_webpage(url, url_basename(url))
 121         cnn_url = self._html_search_regex(r'data-url="(.+?)"', webpage, 'cnn url')
 122         return {
 123             '_type': 'url',
 124             'url': cnn_url,
 125             'ie_key': CNNIE.ie_key(),
 126         }
 127
 128
 129 class CNNArticleIE(InfoExtractor):
 130     _VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!videos?/)'
 131     _TEST = {
 132         'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/',
 133         'md5': '689034c2a3d9c6dc4aa72d65a81efd01',
 134         'info_dict': {
 135             'id': 'bestoftv/2014/12/21/ip-north-korea-obama.cnn',
 136             'ext': 'mp4',
 137             'title': 'Obama: Cyberattack not an act of war',
 138             'description': 'md5:0a802a40d2376f60e6b04c8d5bcebc4b',
 139             'upload_date': '20141221',
 140         },
 141         'expected_warnings': ['Failed to download m3u8 information'],
 142         'add_ie': ['CNN'],
 143     }
 144
 145     def _real_extract(self, url):
 146         webpage = self._download_webpage(url, url_basename(url))
 147         cnn_url = self._html_search_regex(r"video:\s*'([^']+)'", webpage, 'cnn url')
 148         return {
 149             '_type': 'url',
 150             'url': 'http://cnn.com/video/?/video/' + cnn_url,
 151             'ie_key': CNNIE.ie_key(),
 152         }