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