_ Git - youtube-dl/blob - youtube_dl/extractor/foxnews.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     parse_iso8601,
   8     int_or_none,
   9 )
  10
  11
  12 class FoxNewsIE(InfoExtractor):
  13     IE_DESC = 'Fox News and Fox Business Video'
  14     _VALID_URL = r'https?://(?P<host>video\.fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
  15     _TESTS = [
  16         {
  17             'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips',
  18             'md5': '32aaded6ba3ef0d1c04e238d01031e5e',
  19             'info_dict': {
  20                 'id': '3937480',
  21                 'ext': 'flv',
  22                 'title': 'Frozen in Time',
  23                 'description': 'Doctors baffled by 16-year-old girl that is the size of a toddler',
  24                 'duration': 265,
  25                 'timestamp': 1304411491,
  26                 'upload_date': '20110503',
  27                 'thumbnail': 're:^https?://.*\.jpg$',
  28             },
  29         },
  30         {
  31             'url': 'http://video.foxnews.com/v/3922535568001/rep-luis-gutierrez-on-if-obamas-immigration-plan-is-legal/#sp=show-clips',
  32             'md5': '5846c64a1ea05ec78175421b8323e2df',
  33             'info_dict': {
  34                 'id': '3922535568001',
  35                 'ext': 'mp4',
  36                 'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal",
  37                 'description': "Congressman discusses the president's executive action",
  38                 'duration': 292,
  39                 'timestamp': 1417662047,
  40                 'upload_date': '20141204',
  41                 'thumbnail': 're:^https?://.*\.jpg$',
  42             },
  43         },
  44         {
  45             'url': 'http://video.foxnews.com/v/video-embed.html?video_id=3937480&d=video.foxnews.com',
  46             'only_matching': True,
  47         },
  48         {
  49             'url': 'http://video.foxbusiness.com/v/4442309889001',
  50             'only_matching': True,
  51         },
  52     ]
  53
  54     def _real_extract(self, url):
  55         mobj = re.match(self._VALID_URL, url)
  56         video_id = mobj.group('id')
  57         host = mobj.group('host')
  58
  59         video = self._download_json(
  60             'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id), video_id)
  61
  62         item = video['channel']['item']
  63         title = item['title']
  64         description = item['description']
  65         timestamp = parse_iso8601(item['dc-date'])
  66
  67         media_group = item['media-group']
  68         duration = None
  69         formats = []
  70         for media in media_group['media-content']:
  71             attributes = media['@attributes']
  72             video_url = attributes['url']
  73             if video_url.endswith('.f4m'):
  74                 formats.extend(self._extract_f4m_formats(video_url + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', video_id))
  75             elif video_url.endswith('.m3u8'):
  76                 formats.extend(self._extract_m3u8_formats(video_url, video_id, 'flv'))
  77             elif not video_url.endswith('.smil'):
  78                 duration = int_or_none(attributes.get('duration'))
  79                 formats.append({
  80                     'url': video_url,
  81                     'format_id': media['media-category']['@attributes']['label'],
  82                     'preference': 1,
  83                     'vbr': int_or_none(attributes.get('bitrate')),
  84                     'filesize': int_or_none(attributes.get('fileSize'))
  85                 })
  86         self._sort_formats(formats)
  87
  88         media_thumbnail = media_group['media-thumbnail']['@attributes']
  89         thumbnails = [{
  90             'url': media_thumbnail['url'],
  91             'width': int_or_none(media_thumbnail.get('width')),
  92             'height': int_or_none(media_thumbnail.get('height')),
  93         }] if media_thumbnail else []
  94
  95         return {
  96             'id': video_id,
  97             'title': title,
  98             'description': description,
  99             'duration': duration,
 100             'timestamp': timestamp,
 101             'formats': formats,
 102             'thumbnails': thumbnails,
 103         }