youtube_dl/extractor/cwtv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     parse_iso8601,
   8 )
   9
  10
  11 class CWTVIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?cw(?:tv(?:pr)?|seed)\.com/(?:shows/)?(?:[^/]+/)+[^?]*\?.*\b(?:play|watch)=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})'
  13     _TESTS = [{
  14         'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?play=6b15e985-9345-4f60-baf8-56e96be57c63',
  15         'info_dict': {
  16             'id': '6b15e985-9345-4f60-baf8-56e96be57c63',
  17             'ext': 'mp4',
  18             'title': 'Legends of Yesterday',
  19             'description': 'Oliver and Barry Allen take Kendra Saunders and Carter Hall to a remote location to keep them hidden from Vandal Savage while they figure out how to defeat him.',
  20             'duration': 2665,
  21             'series': 'Arrow',
  22             'season_number': 4,
  23             'season': '4',
  24             'episode_number': 8,
  25             'upload_date': '20151203',
  26             'timestamp': 1449122100,
  27         },
  28         'params': {
  29             # m3u8 download
  30             'skip_download': True,
  31         }
  32     }, {
  33         'url': 'http://www.cwseed.com/shows/whose-line-is-it-anyway/jeff-davis-4/?play=24282b12-ead2-42f2-95ad-26770c2c6088',
  34         'info_dict': {
  35             'id': '24282b12-ead2-42f2-95ad-26770c2c6088',
  36             'ext': 'mp4',
  37             'title': 'Jeff Davis 4',
  38             'description': 'Jeff Davis is back to make you laugh.',
  39             'duration': 1263,
  40             'series': 'Whose Line Is It Anyway?',
  41             'season_number': 11,
  42             'season': '11',
  43             'episode_number': 20,
  44             'upload_date': '20151006',
  45             'timestamp': 1444107300,
  46         },
  47         'params': {
  48             # m3u8 download
  49             'skip_download': True,
  50         }
  51     }, {
  52         'url': 'http://cwtv.com/thecw/chroniclesofcisco/?play=8adebe35-f447-465f-ab52-e863506ff6d6',
  53         'only_matching': True,
  54     }, {
  55         'url': 'http://cwtvpr.com/the-cw/video?watch=9eee3f60-ef4e-440b-b3b2-49428ac9c54e',
  56         'only_matching': True,
  57     }, {
  58         'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?watch=6b15e985-9345-4f60-baf8-56e96be57c63',
  59         'only_matching': True,
  60     }]
  61
  62     def _real_extract(self, url):
  63         video_id = self._match_id(url)
  64         video_data = self._download_json(
  65             'http://metaframe.digitalsmiths.tv/v2/CWtv/assets/%s/partner/132?format=json' % video_id, video_id)
  66
  67         formats = self._extract_m3u8_formats(
  68             video_data['videos']['variantplaylist']['uri'], video_id, 'mp4')
  69         self._sort_formats(formats)
  70
  71         thumbnails = [{
  72             'url': image['uri'],
  73             'width': image.get('width'),
  74             'height': image.get('height'),
  75         } for image_id, image in video_data['images'].items() if image.get('uri')] if video_data.get('images') else None
  76
  77         video_metadata = video_data['assetFields']
  78
  79         subtitles = {
  80             'en': [{
  81                 'url': video_metadata['UnicornCcUrl'],
  82             }],
  83         } if video_metadata.get('UnicornCcUrl') else None
  84
  85         return {
  86             'id': video_id,
  87             'title': video_metadata['title'],
  88             'description': video_metadata.get('description'),
  89             'duration': int_or_none(video_metadata.get('duration')),
  90             'series': video_metadata.get('seriesName'),
  91             'season_number': int_or_none(video_metadata.get('seasonNumber')),
  92             'season': video_metadata.get('seasonName'),
  93             'episode_number': int_or_none(video_metadata.get('episodeNumber')),
  94             'timestamp': parse_iso8601(video_data.get('startTime')),
  95             'thumbnails': thumbnails,
  96             'formats': formats,
  97             'subtitles': subtitles,
  98         }