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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import js_to_json
   5
   6
   7 class RottenTomatoesIE(InfoExtractor):
   8     _VALID_URL = r'https?://www\.rottentomatoes\.com/m/[^/]+/trailers/(?P<id>\d+)'
   9
  10     _TEST = {
  11         'url': 'http://www.rottentomatoes.com/m/toy_story_3/trailers/11028566/',
  12         'info_dict': {
  13             'id': '11028566',
  14             'ext': 'mp4',
  15             'title': 'Toy Story 3',
  16             'thumbnail': 're:^https?://.*\.jpg$',
  17         },
  18     }
  19
  20     def _real_extract(self, url):
  21         video_id = self._match_id(url)
  22         webpage = self._download_webpage(url, video_id)
  23
  24         params = self._parse_json(
  25             self._search_regex(r'(?s)RTVideo\(({.+?})\);', webpage, 'player parameters'),
  26             video_id, transform_source=lambda s: js_to_json(s.replace('window.location.href', '""')))
  27
  28         formats = []
  29         if params.get('urlHLS'):
  30             formats.extend(self._extract_m3u8_formats(
  31                 params['urlHLS'], video_id, ext='mp4',
  32                 entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
  33         if params.get('urlMP4'):
  34             formats.append({
  35                 'url': params['urlMP4'],
  36                 'format_id': 'mp4',
  37             })
  38         self._sort_formats(formats)
  39
  40         return {
  41             'id': video_id,
  42             'title': self._og_search_title(webpage),
  43             'formats': formats,
  44             'thumbnail': params.get('thumbnailImg'),
  45         }