Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/einthusan.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_b64decode,
  10     compat_str,
  11     compat_urlparse,
  12 )
  13 from ..utils import (
  14     extract_attributes,
  15     ExtractorError,
  16     get_elements_by_class,
  17     urlencode_postdata,
  18 )
  19
  20
  21 class EinthusanIE(InfoExtractor):
  22     _VALID_URL = r'https?://(?P<host>einthusan\.(?:tv|com|ca))/movie/watch/(?P<id>[^/?#&]+)'
  23     _TESTS = [{
  24         'url': 'https://einthusan.tv/movie/watch/9097/',
  25         'md5': 'ff0f7f2065031b8a2cf13a933731c035',
  26         'info_dict': {
  27             'id': '9097',
  28             'ext': 'mp4',
  29             'title': 'Ae Dil Hai Mushkil',
  30             'description': 'md5:33ef934c82a671a94652a9b4e54d931b',
  31             'thumbnail': r're:^https?://.*\.jpg$',
  32         }
  33     }, {
  34         'url': 'https://einthusan.tv/movie/watch/51MZ/?lang=hindi',
  35         'only_matching': True,
  36     }, {
  37         'url': 'https://einthusan.com/movie/watch/9097/',
  38         'only_matching': True,
  39     }, {
  40         'url': 'https://einthusan.ca/movie/watch/4E9n/?lang=hindi',
  41         'only_matching': True,
  42     }]
  43
  44     # reversed from jsoncrypto.prototype.decrypt() in einthusan-PGMovieWatcher.js
  45     def _decrypt(self, encrypted_data, video_id):
  46         return self._parse_json(compat_b64decode((
  47             encrypted_data[:10] + encrypted_data[-1] + encrypted_data[12:-1]
  48         )).decode('utf-8'), video_id)
  49
  50     def _real_extract(self, url):
  51         mobj = re.match(self._VALID_URL, url)
  52         host = mobj.group('host')
  53         video_id = mobj.group('id')
  54
  55         webpage = self._download_webpage(url, video_id)
  56
  57         title = self._html_search_regex(r'<h3>([^<]+)</h3>', webpage, 'title')
  58
  59         player_params = extract_attributes(self._search_regex(
  60             r'(<section[^>]+id="UIVideoPlayer"[^>]+>)', webpage, 'player parameters'))
  61
  62         page_id = self._html_search_regex(
  63             '<html[^>]+data-pageid="([^"]+)"', webpage, 'page ID')
  64         video_data = self._download_json(
  65             'https://%s/ajax/movie/watch/%s/' % (host, video_id), video_id,
  66             data=urlencode_postdata({
  67                 'xEvent': 'UIVideoPlayer.PingOutcome',
  68                 'xJson': json.dumps({
  69                     'EJOutcomes': player_params['data-ejpingables'],
  70                     'NativeHLS': False
  71                 }),
  72                 'arcVersion': 3,
  73                 'appVersion': 59,
  74                 'gorilla.csrf.Token': page_id,
  75             }))['Data']
  76
  77         if isinstance(video_data, compat_str) and video_data.startswith('/ratelimited/'):
  78             raise ExtractorError(
  79                 'Download rate reached. Please try again later.', expected=True)
  80
  81         ej_links = self._decrypt(video_data['EJLinks'], video_id)
  82
  83         formats = []
  84
  85         m3u8_url = ej_links.get('HLSLink')
  86         if m3u8_url:
  87             formats.extend(self._extract_m3u8_formats(
  88                 m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native'))
  89
  90         mp4_url = ej_links.get('MP4Link')
  91         if mp4_url:
  92             formats.append({
  93                 'url': mp4_url,
  94             })
  95
  96         self._sort_formats(formats)
  97
  98         description = get_elements_by_class('synopsis', webpage)[0]
  99         thumbnail = self._html_search_regex(
 100             r'''<img[^>]+src=(["'])(?P<url>(?!\1).+?/moviecovers/(?!\1).+?)\1''',
 101             webpage, 'thumbnail url', fatal=False, group='url')
 102         if thumbnail is not None:
 103             thumbnail = compat_urlparse.urljoin(url, thumbnail)
 104
 105         return {
 106             'id': video_id,
 107             'title': title,
 108             'formats': formats,
 109             'thumbnail': thumbnail,
 110             'description': description,
 111         }