Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/hidive.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_str
   8 from ..utils import (
   9     ExtractorError,
  10     int_or_none,
  11     urlencode_postdata,
  12 )
  13
  14
  15 class HiDiveIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?hidive\.com/stream/(?P<title>[^/]+)/(?P<key>[^/?#&]+)'
  17     # Using X-Forwarded-For results in 403 HTTP error for HLS fragments,
  18     # so disabling geo bypass completely
  19     _GEO_BYPASS = False
  20
  21     _TESTS = [{
  22         'url': 'https://www.hidive.com/stream/the-comic-artist-and-his-assistants/s01e001',
  23         'info_dict': {
  24             'id': 'the-comic-artist-and-his-assistants/s01e001',
  25             'ext': 'mp4',
  26             'title': 'the-comic-artist-and-his-assistants/s01e001',
  27             'series': 'the-comic-artist-and-his-assistants',
  28             'season_number': 1,
  29             'episode_number': 1,
  30         },
  31         'params': {
  32             'skip_download': True,
  33         },
  34     }]
  35
  36     def _real_extract(self, url):
  37         mobj = re.match(self._VALID_URL, url)
  38         title, key = mobj.group('title', 'key')
  39         video_id = '%s/%s' % (title, key)
  40
  41         settings = self._download_json(
  42             'https://www.hidive.com/play/settings', video_id,
  43             data=urlencode_postdata({
  44                 'Title': title,
  45                 'Key': key,
  46             }))
  47
  48         restriction = settings.get('restrictionReason')
  49         if restriction == 'RegionRestricted':
  50             self.raise_geo_restricted()
  51
  52         if restriction and restriction != 'None':
  53             raise ExtractorError(
  54                 '%s said: %s' % (self.IE_NAME, restriction), expected=True)
  55
  56         formats = []
  57         subtitles = {}
  58         for rendition_id, rendition in settings['renditions'].items():
  59             bitrates = rendition.get('bitrates')
  60             if not isinstance(bitrates, dict):
  61                 continue
  62             m3u8_url = bitrates.get('hls')
  63             if not isinstance(m3u8_url, compat_str):
  64                 continue
  65             formats.extend(self._extract_m3u8_formats(
  66                 m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
  67                 m3u8_id='%s-hls' % rendition_id, fatal=False))
  68             cc_files = rendition.get('ccFiles')
  69             if not isinstance(cc_files, list):
  70                 continue
  71             for cc_file in cc_files:
  72                 if not isinstance(cc_file, list) or len(cc_file) < 3:
  73                     continue
  74                 cc_lang = cc_file[0]
  75                 cc_url = cc_file[2]
  76                 if not isinstance(cc_lang, compat_str) or not isinstance(
  77                         cc_url, compat_str):
  78                     continue
  79                 subtitles.setdefault(cc_lang, []).append({
  80                     'url': cc_url,
  81                 })
  82
  83         season_number = int_or_none(self._search_regex(
  84             r's(\d+)', key, 'season number', default=None))
  85         episode_number = int_or_none(self._search_regex(
  86             r'e(\d+)', key, 'episode number', default=None))
  87
  88         return {
  89             'id': video_id,
  90             'title': video_id,
  91             'subtitles': subtitles,
  92             'formats': formats,
  93             'series': title,
  94             'season_number': season_number,
  95             'episode_number': episode_number,
  96         }