youtube_dl/extractor/cbsnews.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import zlib
   6
   7 from .common import InfoExtractor
   8 from .cbs import CBSIE
   9 from ..compat import (
  10     compat_b64decode,
  11     compat_urllib_parse_unquote,
  12 )
  13 from ..utils import (
  14     parse_duration,
  15 )
  16
  17
  18 class CBSNewsEmbedIE(CBSIE):
  19     IE_NAME = 'cbsnews:embed'
  20     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/embed/video[^#]*#(?P<id>.+)'
  21     _TESTS = [{
  22         'url': 'https://www.cbsnews.com/embed/video/?v=1.c9b5b61492913d6660db0b2f03579ef25e86307a#1Vb7b9s2EP5XBAHbT6Gt98PAMKTJ0se6LVjWYWtdGBR1stlIpEBSTtwi%2F%2FvuJNkNhmHdGxgM2NL57vjd6zt%2B8PngdN%2Fyg79qeGvhzN%2FLGrS%2F%2BuBLB531V28%2B%2BO7Qg7%2Fy97r2z3xZ42NW8yLhDbA0S0KWlHnIijwKWJBHZZnHBa8Cgbpdf%2F89NM9Hi9fXifhpr8sr%2FlP848tn%2BTdXycX25zh4cdX%2FvHl6PmmPqnWQv9w8Ed%2B9GjYRim07bFEqdG%2BZVHuwTm65A7bVRrYtR5lAyMox7pigF6W4k%2By91mjspGsJ%2BwVae4%2BsvdnaO1p73HkXs%2FVisUDTGm7R8IcdnOROeq%2B19qT1amhA1VJtPenoTUgrtfKc9m7Rq8dP7nnjwOB7wg7ADdNt7VX64DWAWlKhPtmDEq22g4GF99x6Dk9E8OSsankHXqPNKDxC%2FdK7MLKTircTDgsI3mmj4OBdSq64dy7fd1x577RU1rt4cvMtOaulFYOd%2FLewRWvDO9lIgXFpZSnkZmjbv5SxKTPoQXClFbpsf%2Fhbbpzs0IB3vb8KkyzJQ%2BywOAgCrMpgRrz%2BKk4fvb7kFbR4XJCu0gAdtNO7woCwZTu%2BBUs9bam%2Fds71drVerpeisgrubLjAB4nnOSkWQnfr5W6o1ku5Xpr1MgrCbL0M0vUyDtfLLK15WiYp47xKWSLyjFVpwVmVJSLIoCjSOFkv3W7oKsVliwZJcB9nwXpZ5GEQQwY8jNKqKCBrgjTLeFxgdCIpazojDgnRtn43J6kG7nZ6cAbxh0EeFFk4%2B1u867cY5u4344n%2FxXjCqAjucdTHgLKojNKmSfO8KRsOFY%2FzKEYCKEJBzv90QA9nfm9gL%2BHulaFqUkz9ULUYxl62B3U%2FRVNLA8IhggaPycOoBuwOCESciDQVSSUgiOMsROB%2FhKfwCKOzEk%2B4k6rWd4uuT%2FwTDz7K7t3d3WLO8ISD95jSPQbayBacthbz86XVgxHwhex5zawzgDOmtp%2F3GPcXn0VXHdSS029%2Fj99UC%2FwJUvyKQ%2FzKyixIEVlYJOn4RxxuaH43Ty9fbJ5OObykHH435XAzJTHeOF4hhEUXD8URe%2FQ%2FBT%2BMpf8d5GN02Ox%2FfiGsl7TA7POu1xZ5%2BbTzcAVKMe48mqcC21hkacVEVScM26liVVBnrKkC4CLKyzAvHu0lhEaTKMFwI3a4SN9MsrfYzdBLq2vkwRD1gVviLT8kY9h2CHH6Y%2Bix6609weFtey4ESp60WtyeWMy%2BsmBuhsoKIyuoT%2Bq2R%2FrW5qi3g%2FvzS2j40DoixDP8%2BKP0yUdpXJ4l6Vla%2Bg9vce%2BC4yM5YlUcbA%2F0jLKdpmTwvsdN5z88nAIe08%2F0HgxeG1iv%2B6Hlhjh7uiW0SDzYNI92L401uha3JKYk268UVRzdOzNQvAaJqoXzAc80dAV440NZ1WVVAAMRYQ2KrGJFmDUsq8saWSnjvIj8t78y%2FRa3JRnbHVfyFpfwoDiGpPgjzekyUiKNlU3OMlwuLMmzgvEojllYVE2Z1HhImvsnk%2BuhusTEoB21PAtSFodeFK3iYhXEH9WOG2%2FkOE833sfeG%2Ff5cfHtEFNXgYes0%2FXj7aGivUgJ9XpusCtoNcNYVVnJVrrDo0OmJAutHCpuZul4W9lLcfy7BnuLPT02%2ByXsCTk%2B9zhzswIN04YueNSK%2BPtM0jS88QdLqSLJDTLsuGZJNolm2yO0PXh3UPnz9Ix5bfIAqxPjvETQsDCEiPG4QbqNyhBZISxybLnZYCrW5H3Axp690%2F0BJdXtDZ5ITuM4xj3f4oUHGzc5JeJmZKpp%2FjwKh4wMV%2FV1yx3emLoR0MwbG4K%2F%2BZgVep3PnzXGDHZ6a3i%2Fk%2BJrONDN13%2Bnq6tBTYk4o7cLGhBtqCC4KwacGHpEVuoH5JNro%2FE6JfE6d5RydbiR76k%2BW5wioDHBIjw1euhHjUGRB0y5A97KoaPx6MlL%2BwgboUVtUFRI%2FLemgTpdtF59ii7pab08kuPcfWzs0l%2FRI5takWnFpka0zOgWRtYcuf9aIxZMxlwr6IiGpsb6j2DQUXPl%2FimXI599Ev7fWjoPD78A',
  23         'only_matching': True,
  24     }]
  25
  26     def _real_extract(self, url):
  27         item = self._parse_json(zlib.decompress(compat_b64decode(
  28             compat_urllib_parse_unquote(self._match_id(url))),
  29             -zlib.MAX_WBITS), None)['video']['items'][0]
  30         return self._extract_video_info(item['mpxRefId'], 'cbsnews')
  31
  32
  33 class CBSNewsIE(CBSIE):
  34     IE_NAME = 'cbsnews'
  35     IE_DESC = 'CBS News'
  36     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|video)/(?P<id>[\da-z_-]+)'
  37
  38     _TESTS = [
  39         {
  40             # 60 minutes
  41             'url': 'http://www.cbsnews.com/news/artificial-intelligence-positioned-to-be-a-game-changer/',
  42             'info_dict': {
  43                 'id': 'Y_nf_aEg6WwO9OLAq0MpKaPgfnBUxfW4',
  44                 'ext': 'flv',
  45                 'title': 'Artificial Intelligence, real-life applications',
  46                 'description': 'md5:a7aaf27f1b4777244de8b0b442289304',
  47                 'thumbnail': r're:^https?://.*\.jpg$',
  48                 'duration': 317,
  49                 'uploader': 'CBSI-NEW',
  50                 'timestamp': 1476046464,
  51                 'upload_date': '20161009',
  52             },
  53             'params': {
  54                 # rtmp download
  55                 'skip_download': True,
  56             },
  57         },
  58         {
  59             'url': 'https://www.cbsnews.com/video/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
  60             'info_dict': {
  61                 'id': 'SNJBOYzXiWBOvaLsdzwH8fmtP1SCd91Y',
  62                 'ext': 'mp4',
  63                 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
  64                 'description': 'md5:4a6983e480542d8b333a947bfc64ddc7',
  65                 'upload_date': '20140404',
  66                 'timestamp': 1396650660,
  67                 'uploader': 'CBSI-NEW',
  68                 'thumbnail': r're:^https?://.*\.jpg$',
  69                 'duration': 205,
  70                 'subtitles': {
  71                     'en': [{
  72                         'ext': 'ttml',
  73                     }],
  74                 },
  75             },
  76             'params': {
  77                 # m3u8 download
  78                 'skip_download': True,
  79             },
  80         },
  81         {
  82             # 48 hours
  83             'url': 'http://www.cbsnews.com/news/maria-ridulph-murder-will-the-nations-oldest-cold-case-to-go-to-trial-ever-get-solved/',
  84             'info_dict': {
  85                 'title': 'Cold as Ice',
  86                 'description': 'Can a childhood memory solve the 1957 murder of 7-year-old Maria Ridulph?',
  87             },
  88             'playlist_mincount': 7,
  89         },
  90     ]
  91
  92     def _real_extract(self, url):
  93         display_id = self._match_id(url)
  94
  95         webpage = self._download_webpage(url, display_id)
  96
  97         entries = []
  98         for embed_url in re.findall(r'<iframe[^>]+data-src="(https?://(?:www\.)?cbsnews\.com/embed/video/[^#]*#[^"]+)"', webpage):
  99             entries.append(self.url_result(embed_url, CBSNewsEmbedIE.ie_key()))
 100         if entries:
 101             return self.playlist_result(
 102                 entries, playlist_title=self._html_search_meta(['og:title', 'twitter:title'], webpage),
 103                 playlist_description=self._html_search_meta(['og:description', 'twitter:description', 'description'], webpage))
 104
 105         item = self._parse_json(self._html_search_regex(
 106             r'CBSNEWS\.defaultPayload\s*=\s*({.+})',
 107             webpage, 'video JSON info'), display_id)['items'][0]
 108         return self._extract_video_info(item['mpxRefId'], 'cbsnews')
 109
 110
 111 class CBSNewsLiveVideoIE(InfoExtractor):
 112     IE_NAME = 'cbsnews:livevideo'
 113     IE_DESC = 'CBS News Live Videos'
 114     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[^/?#]+)'
 115
 116     # Live videos get deleted soon. See http://www.cbsnews.com/live/ for the latest examples
 117     _TEST = {
 118         'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
 119         'info_dict': {
 120             'id': 'clinton-sanders-prepare-to-face-off-in-nh',
 121             'ext': 'mp4',
 122             'title': 'Clinton, Sanders Prepare To Face Off In NH',
 123             'duration': 334,
 124         },
 125         'skip': 'Video gone',
 126     }
 127
 128     def _real_extract(self, url):
 129         display_id = self._match_id(url)
 130
 131         video_info = self._download_json(
 132             'http://feeds.cbsn.cbsnews.com/rundown/story', display_id, query={
 133                 'device': 'desktop',
 134                 'dvr_slug': display_id,
 135             })
 136
 137         formats = self._extract_akamai_formats(video_info['url'], display_id)
 138         self._sort_formats(formats)
 139
 140         return {
 141             'id': display_id,
 142             'display_id': display_id,
 143             'title': video_info['headline'],
 144             'thumbnail': video_info.get('thumbnail_url_hd') or video_info.get('thumbnail_url_sd'),
 145             'duration': parse_duration(video_info.get('segmentDur')),
 146             'formats': formats,
 147         }