_ Git - youtube-dl/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             'proxy': '192.99.245.228:3128',
  34         },
  35     }]
  36
  37     def _real_extract(self, url):
  38         mobj = re.match(self._VALID_URL, url)
  39         title, key = mobj.group('title', 'key')
  40         video_id = '%s/%s' % (title, key)
  41
  42         settings = self._download_json(
  43             'https://www.hidive.com/play/settings', video_id,
  44             data=urlencode_postdata({
  45                 'Title': title,
  46                 'Key': key,
  47             }))
  48
  49         restriction = settings.get('restrictionReason')
  50         if restriction == 'RegionRestricted':
  51             self.raise_geo_restricted()
  52
  53         if restriction and restriction != 'None':
  54             raise ExtractorError(
  55                 '%s said: %s' % (self.IE_NAME, restriction), expected=True)
  56
  57         formats = []
  58         subtitles = {}
  59         for rendition_id, rendition in settings['renditions'].items():
  60             bitrates = rendition.get('bitrates')
  61             if not isinstance(bitrates, dict):
  62                 continue
  63             m3u8_url = bitrates.get('hls')
  64             if not isinstance(m3u8_url, compat_str):
  65                 continue
  66             formats.extend(self._extract_m3u8_formats(
  67                 m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
  68                 m3u8_id='%s-hls' % rendition_id, fatal=False))
  69             cc_files = rendition.get('ccFiles')
  70             if not isinstance(cc_files, list):
  71                 continue
  72             for cc_file in cc_files:
  73                 if not isinstance(cc_file, list) or len(cc_file) < 3:
  74                     continue
  75                 cc_lang = cc_file[0]
  76                 cc_url = cc_file[2]
  77                 if not isinstance(cc_lang, compat_str) or not isinstance(
  78                         cc_url, compat_str):
  79                     continue
  80                 subtitles.setdefault(cc_lang, []).append({
  81                     'url': cc_url,
  82                 })
  83
  84         season_number = int_or_none(self._search_regex(
  85             r's(\d+)', key, 'season number', default=None))
  86         episode_number = int_or_none(self._search_regex(
  87             r'e(\d+)', key, 'episode number', default=None))
  88
  89         return {
  90             'id': video_id,
  91             'title': video_id,
  92             'subtitles': subtitles,
  93             'formats': formats,
  94             'series': title,
  95             'season_number': season_number,
  96             'episode_number': episode_number,
  97         }