_ 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     _NETRC_MACHINE = 'hidive'
  21     _LOGGED_IN = False
  22     _LOGIN_URL = 'https://www.hidive.com/account/login'
  23
  24     _TESTS = [{
  25         'url': 'https://www.hidive.com/stream/the-comic-artist-and-his-assistants/s01e001',
  26         'info_dict': {
  27             'id': 'the-comic-artist-and-his-assistants/s01e001',
  28             'ext': 'mp4',
  29             'title': 'the-comic-artist-and-his-assistants/s01e001',
  30             'series': 'the-comic-artist-and-his-assistants',
  31             'season_number': 1,
  32             'episode_number': 1,
  33         },
  34         'params': {
  35             'skip_download': True,
  36         },
  37         'skip': 'Requires Authentication',
  38     }]
  39
  40     def _real_initialize(self):
  41         if self._LOGGED_IN:
  42             return
  43
  44         (email, password) = self._get_login_info()
  45         if email is None:
  46             return
  47
  48         webpage = self._download_webpage(self._LOGIN_URL, None)
  49         form = self._search_regex(
  50             r'(?s)<form[^>]+action="/account/login"[^>]*>(.+?)</form>',
  51             webpage, 'login form')
  52         data = self._hidden_inputs(form)
  53         data.update({
  54             'Email': email,
  55             'Password': password,
  56         })
  57         self._download_webpage(
  58             self._LOGIN_URL, None, 'Logging in', data=urlencode_postdata(data))
  59         self._LOGGED_IN = True
  60
  61     def _real_extract(self, url):
  62         mobj = re.match(self._VALID_URL, url)
  63         title, key = mobj.group('title', 'key')
  64         video_id = '%s/%s' % (title, key)
  65
  66         settings = self._download_json(
  67             'https://www.hidive.com/play/settings', video_id,
  68             data=urlencode_postdata({
  69                 'Title': title,
  70                 'Key': key,
  71                 'PlayerId': 'f4f895ce1ca713ba263b91caeb1daa2d08904783',
  72             }))
  73
  74         restriction = settings.get('restrictionReason')
  75         if restriction == 'RegionRestricted':
  76             self.raise_geo_restricted()
  77
  78         if restriction and restriction != 'None':
  79             raise ExtractorError(
  80                 '%s said: %s' % (self.IE_NAME, restriction), expected=True)
  81
  82         formats = []
  83         subtitles = {}
  84         for rendition_id, rendition in settings['renditions'].items():
  85             bitrates = rendition.get('bitrates')
  86             if not isinstance(bitrates, dict):
  87                 continue
  88             m3u8_url = bitrates.get('hls')
  89             if not isinstance(m3u8_url, compat_str):
  90                 continue
  91             formats.extend(self._extract_m3u8_formats(
  92                 m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
  93                 m3u8_id='%s-hls' % rendition_id, fatal=False))
  94             cc_files = rendition.get('ccFiles')
  95             if not isinstance(cc_files, list):
  96                 continue
  97             for cc_file in cc_files:
  98                 if not isinstance(cc_file, list) or len(cc_file) < 3:
  99                     continue
 100                 cc_lang = cc_file[0]
 101                 cc_url = cc_file[2]
 102                 if not isinstance(cc_lang, compat_str) or not isinstance(
 103                         cc_url, compat_str):
 104                     continue
 105                 subtitles.setdefault(cc_lang, []).append({
 106                     'url': cc_url,
 107                 })
 108         self._sort_formats(formats)
 109
 110         season_number = int_or_none(self._search_regex(
 111             r's(\d+)', key, 'season number', default=None))
 112         episode_number = int_or_none(self._search_regex(
 113             r'e(\d+)', key, 'episode number', default=None))
 114
 115         return {
 116             'id': video_id,
 117             'title': video_id,
 118             'subtitles': subtitles,
 119             'formats': formats,
 120             'series': title,
 121             'season_number': season_number,
 122             'episode_number': episode_number,
 123         }