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     url_or_none,
  12     urlencode_postdata,
  13 )
  14
  15
  16 class HiDiveIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?hidive\.com/stream/(?P<title>[^/]+)/(?P<key>[^/?#&]+)'
  18     # Using X-Forwarded-For results in 403 HTTP error for HLS fragments,
  19     # so disabling geo bypass completely
  20     _GEO_BYPASS = False
  21     _NETRC_MACHINE = 'hidive'
  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         email, password = self._get_login_info()
  42         if email is None:
  43             return
  44
  45         webpage = self._download_webpage(self._LOGIN_URL, None)
  46         form = self._search_regex(
  47             r'(?s)<form[^>]+action="/account/login"[^>]*>(.+?)</form>',
  48             webpage, 'login form')
  49         data = self._hidden_inputs(form)
  50         data.update({
  51             'Email': email,
  52             'Password': password,
  53         })
  54         self._download_webpage(
  55             self._LOGIN_URL, None, 'Logging in', data=urlencode_postdata(data))
  56
  57     def _real_extract(self, url):
  58         mobj = re.match(self._VALID_URL, url)
  59         title, key = mobj.group('title', 'key')
  60         video_id = '%s/%s' % (title, key)
  61
  62         settings = self._download_json(
  63             'https://www.hidive.com/play/settings', video_id,
  64             data=urlencode_postdata({
  65                 'Title': title,
  66                 'Key': key,
  67                 'PlayerId': 'f4f895ce1ca713ba263b91caeb1daa2d08904783',
  68             }))
  69
  70         restriction = settings.get('restrictionReason')
  71         if restriction == 'RegionRestricted':
  72             self.raise_geo_restricted()
  73
  74         if restriction and restriction != 'None':
  75             raise ExtractorError(
  76                 '%s said: %s' % (self.IE_NAME, restriction), expected=True)
  77
  78         formats = []
  79         subtitles = {}
  80         for rendition_id, rendition in settings['renditions'].items():
  81             bitrates = rendition.get('bitrates')
  82             if not isinstance(bitrates, dict):
  83                 continue
  84             m3u8_url = url_or_none(bitrates.get('hls'))
  85             if not m3u8_url:
  86                 continue
  87             formats.extend(self._extract_m3u8_formats(
  88                 m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
  89                 m3u8_id='%s-hls' % rendition_id, fatal=False))
  90             cc_files = rendition.get('ccFiles')
  91             if not isinstance(cc_files, list):
  92                 continue
  93             for cc_file in cc_files:
  94                 if not isinstance(cc_file, list) or len(cc_file) < 3:
  95                     continue
  96                 cc_lang = cc_file[0]
  97                 cc_url = url_or_none(cc_file[2])
  98                 if not isinstance(cc_lang, compat_str) or not cc_url:
  99                     continue
 100                 subtitles.setdefault(cc_lang, []).append({
 101                     'url': cc_url,
 102                 })
 103         self._sort_formats(formats)
 104
 105         season_number = int_or_none(self._search_regex(
 106             r's(\d+)', key, 'season number', default=None))
 107         episode_number = int_or_none(self._search_regex(
 108             r'e(\d+)', key, 'episode number', default=None))
 109
 110         return {
 111             'id': video_id,
 112             'title': video_id,
 113             'subtitles': subtitles,
 114             'formats': formats,
 115             'series': title,
 116             'season_number': season_number,
 117             'episode_number': episode_number,
 118         }