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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import base64
   5 import json
   6
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_urlparse,
  10     compat_str,
  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?://einthusan\.tv/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
  37     # reversed from jsoncrypto.prototype.decrypt() in einthusan-PGMovieWatcher.js
  38     def _decrypt(self, encrypted_data, video_id):
  39         return self._parse_json(base64.b64decode((
  40             encrypted_data[:10] + encrypted_data[-1] + encrypted_data[12:-1]
  41         ).encode('ascii')).decode('utf-8'), video_id)
  42
  43     def _real_extract(self, url):
  44         video_id = self._match_id(url)
  45
  46         webpage = self._download_webpage(url, video_id)
  47
  48         title = self._html_search_regex(r'<h3>([^<]+)</h3>', webpage, 'title')
  49
  50         player_params = extract_attributes(self._search_regex(
  51             r'(<section[^>]+id="UIVideoPlayer"[^>]+>)', webpage, 'player parameters'))
  52
  53         page_id = self._html_search_regex(
  54             '<html[^>]+data-pageid="([^"]+)"', webpage, 'page ID')
  55         video_data = self._download_json(
  56             'https://einthusan.tv/ajax/movie/watch/%s/' % video_id, video_id,
  57             data=urlencode_postdata({
  58                 'xEvent': 'UIVideoPlayer.PingOutcome',
  59                 'xJson': json.dumps({
  60                     'EJOutcomes': player_params['data-ejpingables'],
  61                     'NativeHLS': False
  62                 }),
  63                 'arcVersion': 3,
  64                 'appVersion': 59,
  65                 'gorilla.csrf.Token': page_id,
  66             }))['Data']
  67
  68         if isinstance(video_data, compat_str) and video_data.startswith('/ratelimited/'):
  69             raise ExtractorError(
  70                 'Download rate reached. Please try again later.', expected=True)
  71
  72         ej_links = self._decrypt(video_data['EJLinks'], video_id)
  73
  74         formats = []
  75
  76         m3u8_url = ej_links.get('HLSLink')
  77         if m3u8_url:
  78             formats.extend(self._extract_m3u8_formats(
  79                 m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native'))
  80
  81         mp4_url = ej_links.get('MP4Link')
  82         if mp4_url:
  83             formats.append({
  84                 'url': mp4_url,
  85             })
  86
  87         self._sort_formats(formats)
  88
  89         description = get_elements_by_class('synopsis', webpage)[0]
  90         thumbnail = self._html_search_regex(
  91             r'''<img[^>]+src=(["'])(?P<url>(?!\1).+?/moviecovers/(?!\1).+?)\1''',
  92             webpage, 'thumbnail url', fatal=False, group='url')
  93         if thumbnail is not None:
  94             thumbnail = compat_urlparse.urljoin(url, thumbnail)
  95
  96         return {
  97             'id': video_id,
  98             'title': title,
  99             'formats': formats,
 100             'thumbnail': thumbnail,
 101             'description': description,
 102         }