yt_dlp/extractor/einthusan.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_b64decode,
   9     compat_str,
  10     compat_urlparse,
  11 )
  12 from ..utils import (
  13     extract_attributes,
  14     ExtractorError,
  15     get_elements_by_class,
  16     urlencode_postdata,
  17 )
  18
  19
  20 class EinthusanIE(InfoExtractor):
  21     _VALID_URL = r'https?://(?P<host>einthusan\.(?:tv|com|ca))/movie/watch/(?P<id>[^/?#&]+)'
  22     _TESTS = [{
  23         'url': 'https://einthusan.tv/movie/watch/9097/',
  24         'md5': 'ff0f7f2065031b8a2cf13a933731c035',
  25         'info_dict': {
  26             'id': '9097',
  27             'ext': 'mp4',
  28             'title': 'Ae Dil Hai Mushkil',
  29             'description': 'md5:33ef934c82a671a94652a9b4e54d931b',
  30             'thumbnail': r're:^https?://.*\.jpg$',
  31         }
  32     }, {
  33         'url': 'https://einthusan.tv/movie/watch/51MZ/?lang=hindi',
  34         'only_matching': True,
  35     }, {
  36         'url': 'https://einthusan.com/movie/watch/9097/',
  37         'only_matching': True,
  38     }, {
  39         'url': 'https://einthusan.ca/movie/watch/4E9n/?lang=hindi',
  40         'only_matching': True,
  41     }]
  42
  43     # reversed from jsoncrypto.prototype.decrypt() in einthusan-PGMovieWatcher.js
  44     def _decrypt(self, encrypted_data, video_id):
  45         return self._parse_json(compat_b64decode((
  46             encrypted_data[:10] + encrypted_data[-1] + encrypted_data[12:-1]
  47         )).decode('utf-8'), video_id)
  48
  49     def _real_extract(self, url):
  50         mobj = self._match_valid_url(url)
  51         host = mobj.group('host')
  52         video_id = mobj.group('id')
  53
  54         webpage = self._download_webpage(url, video_id)
  55
  56         title = self._html_search_regex(r'<h3>([^<]+)</h3>', webpage, 'title')
  57
  58         player_params = extract_attributes(self._search_regex(
  59             r'(<section[^>]+id="UIVideoPlayer"[^>]+>)', webpage, 'player parameters'))
  60
  61         page_id = self._html_search_regex(
  62             '<html[^>]+data-pageid="([^"]+)"', webpage, 'page ID')
  63         video_data = self._download_json(
  64             'https://%s/ajax/movie/watch/%s/' % (host, video_id), video_id,
  65             data=urlencode_postdata({
  66                 'xEvent': 'UIVideoPlayer.PingOutcome',
  67                 'xJson': json.dumps({
  68                     'EJOutcomes': player_params['data-ejpingables'],
  69                     'NativeHLS': False
  70                 }),
  71                 'arcVersion': 3,
  72                 'appVersion': 59,
  73                 'gorilla.csrf.Token': page_id,
  74             }))['Data']
  75
  76         if isinstance(video_data, compat_str) and video_data.startswith('/ratelimited/'):
  77             raise ExtractorError(
  78                 'Download rate reached. Please try again later.', expected=True)
  79
  80         ej_links = self._decrypt(video_data['EJLinks'], video_id)
  81
  82         formats = []
  83
  84         m3u8_url = ej_links.get('HLSLink')
  85         if m3u8_url:
  86             formats.extend(self._extract_m3u8_formats(
  87                 m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native'))
  88
  89         mp4_url = ej_links.get('MP4Link')
  90         if mp4_url:
  91             formats.append({
  92                 'url': mp4_url,
  93             })
  94
  95         self._sort_formats(formats)
  96
  97         description = get_elements_by_class('synopsis', webpage)[0]
  98         thumbnail = self._html_search_regex(
  99             r'''<img[^>]+src=(["'])(?P<url>(?!\1).+?/moviecovers/(?!\1).+?)\1''',
 100             webpage, 'thumbnail url', fatal=False, group='url')
 101         if thumbnail is not None:
 102             thumbnail = compat_urlparse.urljoin(url, thumbnail)
 103
 104         return {
 105             'id': video_id,
 106             'title': title,
 107             'formats': formats,
 108             'thumbnail': thumbnail,
 109             'description': description,
 110         }