1 from __future__ import unicode_literals
5 from .common import InfoExtractor
13 class CNNIE(InfoExtractor):
14 _VALID_URL = r'''(?x)https?://(?:(?P<sub_domain>edition|www|money)\.)?cnn\.com/(?:video/(?:data/.+?|\?)/)?videos?/
15 (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z\-]+)|(?=&)))'''
18 'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
19 'md5': '3e6121ea48df7e2259fe73a0628605c4',
21 'id': 'sports/2013/06/09/nadal-1-on-1.cnn',
23 'title': 'Nadal wins 8th French Open title',
24 'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
26 'upload_date': '20130609',
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',
30 'md5': 'b5cc60c60a3477d185af8f19a2a26f4e',
32 'id': 'us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology',
34 'title': "Student's epic speech stuns new freshmen",
35 'description': "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
36 'upload_date': '20130821',
39 'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html',
40 'md5': 'f14d02ebd264df951feb2400e2c25a1b',
42 'id': 'living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln',
44 'title': 'Nashville Ep. 1: Hand crafted skateboards',
45 'description': 'md5:e7223a503315c9f150acac52e76de086',
46 'upload_date': '20141222',
49 'url': 'http://money.cnn.com/video/news/2016/08/19/netflix-stunning-stats.cnnmoney/index.html',
50 'md5': '52a515dc1b0f001cd82e4ceda32be9d1',
52 'id': '/video/news/2016/08/19/netflix-stunning-stats.cnnmoney',
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',
59 'url': 'http://cnn.com/video/?/video/politics/2015/03/27/pkg-arizona-senator-church-attendance-mandatory.ktvk',
60 'only_matching': True,
62 'url': 'http://cnn.com/video/?/video/us/2015/04/06/dnt-baker-refuses-anti-gay-order.wkmg',
63 'only_matching': True,
65 'url': 'http://edition.cnn.com/videos/arts/2016/04/21/olympic-games-cultural-a-z-brazil.cnn',
66 'only_matching': True,
70 # http://edition.cnn.com/.element/apps/cvp/3.0/cfg/spider/cnn/expansion/config.xml
72 'data_src': 'http://edition.cnn.com/video/data/3.0/video/%s/index.xml',
73 'media_src': 'http://pmd.cdn.turner.com/cnn/big',
75 # http://money.cnn.com/.element/apps/cvp2/cfg/config.xml
77 'data_src': 'http://money.cnn.com/video/data/4.0/video/%s.xml',
78 'media_src': 'http://ht3.cdn.turner.com/money/big',
82 def _real_extract(self, url):
83 sub_domain, path, page_title = re.match(self._VALID_URL, url).groups()
84 if sub_domain not in ('money', 'edition'):
85 sub_domain = 'edition'
86 config = self._CONFIG[sub_domain]
87 info_url = config['data_src'] % path
88 info = self._download_xml(info_url, page_title)
91 rex = re.compile(r'''(?x)
92 (?P<width>[0-9]+)x(?P<height>[0-9]+)
93 (?:_(?P<bitrate>[0-9]+)k)?
95 for f in info.findall('files/file'):
96 video_url = config['media_src'] + f.text.strip()
98 'format_id': f.attrib['bitrate'],
102 mf = rex.match(f.attrib['bitrate'])
104 fdct['width'] = int(mf.group('width'))
105 fdct['height'] = int(mf.group('height'))
106 fdct['tbr'] = int_or_none(mf.group('bitrate'))
108 mf = rex.search(f.text)
110 fdct['width'] = int(mf.group('width'))
111 fdct['height'] = int(mf.group('height'))
112 fdct['tbr'] = int_or_none(mf.group('bitrate'))
114 mi = re.match(r'ios_(audio|[0-9]+)$', f.attrib['bitrate'])
116 if mi.group(1) == 'audio':
117 fdct['vcodec'] = 'none'
120 fdct['tbr'] = int(mi.group(1))
124 self._sort_formats(formats)
127 'height': int(t.attrib['height']),
128 'width': int(t.attrib['width']),
130 } for t in info.findall('images/image')]
132 metas_el = info.find('metas')
134 metas_el.attrib.get('version') if metas_el is not None else None)
136 duration_el = info.find('length')
137 duration = parse_duration(duration_el.text)
140 'id': info.attrib['id'],
141 'title': info.find('headline').text,
143 'thumbnails': thumbnails,
144 'description': info.find('description').text,
145 'duration': duration,
146 'upload_date': upload_date,
150 class CNNBlogsIE(InfoExtractor):
151 _VALID_URL = r'https?://[^\.]+\.blogs\.cnn\.com/.+'
153 'url': 'http://reliablesources.blogs.cnn.com/2014/02/09/criminalizing-journalism/',
154 'md5': '3e56f97b0b6ffb4b79f4ea0749551084',
156 'id': 'bestoftv/2014/02/09/criminalizing-journalism.cnn',
158 'title': 'Criminalizing journalism?',
159 'description': 'Glenn Greenwald responds to comments made this week on Capitol Hill that journalists could be criminal accessories.',
160 'upload_date': '20140209',
165 def _real_extract(self, url):
166 webpage = self._download_webpage(url, url_basename(url))
167 cnn_url = self._html_search_regex(r'data-url="(.+?)"', webpage, 'cnn url')
171 'ie_key': CNNIE.ie_key(),
175 class CNNArticleIE(InfoExtractor):
176 _VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!videos?/)'
178 'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/',
179 'md5': '689034c2a3d9c6dc4aa72d65a81efd01',
181 'id': 'bestoftv/2014/12/21/ip-north-korea-obama.cnn',
183 'title': 'Obama: Cyberattack not an act of war',
184 'description': 'md5:51ce6750450603795cad0cdfbd7d05c5',
185 'upload_date': '20141221',
190 def _real_extract(self, url):
191 webpage = self._download_webpage(url, url_basename(url))
192 cnn_url = self._html_search_regex(r"video:\s*'([^']+)'", webpage, 'cnn url')
195 'url': 'http://cnn.com/video/?/video/' + cnn_url,
196 'ie_key': CNNIE.ie_key(),