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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class InternazionaleIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?internazionale\.it/video/(?P<id>.*)'
   9     _TESTS = [{
  10         'url': 'https://www.internazionale.it/video/2015/02/19/richard-linklater-racconta-una-scena-di-boyhood',
  11         'md5': '11b54a3d3333e455c00684e50a65c58e',
  12         'info_dict': {
  13             'id': '265968',
  14             'ext': 'mp4',
  15             'description': 'md5:efb7e5bbfb1a54ae2ed5a4a015f0e665',
  16             'title': 'Richard Linklater racconta una scena di Boyhood',
  17             'thumbnail': r're:^https?://.*\.jpg$',
  18         }
  19     }]
  20
  21     def _real_extract(self, url):
  22         video_id = self._match_id(url)
  23         webpage = self._download_webpage(url, video_id)
  24
  25         data_job_id = self._html_search_regex(r'data-job-id="([^"]+)"', webpage, 'data-job-id')
  26         data_video_path = self._html_search_regex(r'data-video-path="([^"]+)"', webpage, 'data-video-path')
  27
  28         formats = []
  29
  30         formats.extend(self._extract_m3u8_formats(
  31             'https://video.internazionale.it/%s/%s.m3u8' % (data_video_path, data_job_id),
  32             video_id))
  33
  34         formats.extend(self._extract_mpd_formats(
  35             'https://video.internazionale.it/%s/%s.mpd' % (data_video_path, data_job_id),
  36             video_id))
  37
  38         self._sort_formats(formats)
  39
  40         return {
  41             'id': data_job_id,
  42             'title': self._og_search_title(webpage),
  43             'thumbnail': self._og_search_thumbnail(webpage),
  44             'description': self._og_search_description(webpage),
  45             'formats': formats,
  46         }