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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import base64
   5 import binascii
   6 import json
   7 import os
   8 import random
   9
  10 from .common import InfoExtractor
  11 from ..aes import aes_cbc_decrypt
  12 from ..compat import (
  13     compat_b64decode,
  14     compat_ord,
  15 )
  16 from ..utils import (
  17     bytes_to_intlist,
  18     bytes_to_long,
  19     ExtractorError,
  20     float_or_none,
  21     intlist_to_bytes,
  22     long_to_bytes,
  23     pkcs1pad,
  24     srt_subtitles_timecode,
  25     strip_or_none,
  26     urljoin,
  27 )
  28
  29
  30 class ADNIE(InfoExtractor):
  31     IE_DESC = 'Anime Digital Network'
  32     _VALID_URL = r'https?://(?:www\.)?animedigitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
  33     _TEST = {
  34         'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
  35         'md5': 'e497370d847fd79d9d4c74be55575c7a',
  36         'info_dict': {
  37             'id': '7778',
  38             'ext': 'mp4',
  39             'title': 'Blue Exorcist - Kyôto Saga - Épisode 1',
  40             'description': 'md5:2f7b5aa76edbc1a7a92cedcda8a528d5',
  41         }
  42     }
  43     _BASE_URL = 'http://animedigitalnetwork.fr'
  44     _RSA_KEY = (0xc35ae1e4356b65a73b551493da94b8cb443491c0aa092a357a5aee57ffc14dda85326f42d716e539a34542a0d3f363adf16c5ec222d713d5997194030ee2e4f0d1fb328c01a81cf6868c090d50de8e169c6b13d1675b9eeed1cbc51e1fffca9b38af07f37abd790924cd3bee59d0257cfda4fe5f3f0534877e21ce5821447d1b, 65537)
  45
  46     def _get_subtitles(self, sub_path, video_id):
  47         if not sub_path:
  48             return None
  49
  50         enc_subtitles = self._download_webpage(
  51             urljoin(self._BASE_URL, sub_path),
  52             video_id, fatal=False)
  53         if not enc_subtitles:
  54             return None
  55
  56         # http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
  57         dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
  58             bytes_to_intlist(compat_b64decode(enc_subtitles[24:])),
  59             bytes_to_intlist(binascii.unhexlify(self._K + '9032ad7083106400')),
  60             bytes_to_intlist(compat_b64decode(enc_subtitles[:24]))
  61         ))
  62         subtitles_json = self._parse_json(
  63             dec_subtitles[:-compat_ord(dec_subtitles[-1])].decode(),
  64             None, fatal=False)
  65         if not subtitles_json:
  66             return None
  67
  68         subtitles = {}
  69         for sub_lang, sub in subtitles_json.items():
  70             srt = ''
  71             for num, current in enumerate(sub):
  72                 start, end, text = (
  73                     float_or_none(current.get('startTime')),
  74                     float_or_none(current.get('endTime')),
  75                     current.get('text'))
  76                 if start is None or end is None or text is None:
  77                     continue
  78                 srt += os.linesep.join(
  79                     (
  80                         '%d' % num,
  81                         '%s --> %s' % (
  82                             srt_subtitles_timecode(start),
  83                             srt_subtitles_timecode(end)),
  84                         text,
  85                         os.linesep,
  86                     ))
  87
  88             if sub_lang == 'vostf':
  89                 sub_lang = 'fr'
  90             subtitles.setdefault(sub_lang, []).extend([{
  91                 'ext': 'json',
  92                 'data': json.dumps(sub),
  93             }, {
  94                 'ext': 'srt',
  95                 'data': srt,
  96             }])
  97         return subtitles
  98
  99     def _real_extract(self, url):
 100         video_id = self._match_id(url)
 101         webpage = self._download_webpage(url, video_id)
 102         player_config = self._parse_json(self._search_regex(
 103             r'playerConfig\s*=\s*({.+});', webpage, 'player config'), video_id)
 104
 105         video_info = {}
 106         video_info_str = self._search_regex(
 107             r'videoInfo\s*=\s*({.+});', webpage,
 108             'video info', fatal=False)
 109         if video_info_str:
 110             video_info = self._parse_json(
 111                 video_info_str, video_id, fatal=False) or {}
 112
 113         options = player_config.get('options') or {}
 114         metas = options.get('metas') or {}
 115         links = player_config.get('links') or {}
 116         sub_path = player_config.get('subtitles')
 117         error = None
 118         if not links:
 119             links_url = player_config.get('linksurl') or options['videoUrl']
 120             token = options['token']
 121             self._K = ''.join([random.choice('0123456789abcdef') for _ in range(16)])
 122             message = bytes_to_intlist(json.dumps({
 123                 'k': self._K,
 124                 'e': 60,
 125                 't': token,
 126             }))
 127             padded_message = intlist_to_bytes(pkcs1pad(message, 128))
 128             n, e = self._RSA_KEY
 129             encrypted_message = long_to_bytes(pow(bytes_to_long(padded_message), e, n))
 130             authorization = base64.b64encode(encrypted_message).decode()
 131             links_data = self._download_json(
 132                 urljoin(self._BASE_URL, links_url), video_id, headers={
 133                     'Authorization': 'Bearer ' + authorization,
 134                 })
 135             links = links_data.get('links') or {}
 136             metas = metas or links_data.get('meta') or {}
 137             sub_path = (sub_path or links_data.get('subtitles')) + '&token=' + token
 138             error = links_data.get('error')
 139         title = metas.get('title') or video_info['title']
 140
 141         formats = []
 142         for format_id, qualities in links.items():
 143             if not isinstance(qualities, dict):
 144                 continue
 145             for load_balancer_url in qualities.values():
 146                 load_balancer_data = self._download_json(
 147                     load_balancer_url, video_id, fatal=False) or {}
 148                 m3u8_url = load_balancer_data.get('location')
 149                 if not m3u8_url:
 150                     continue
 151                 m3u8_formats = self._extract_m3u8_formats(
 152                     m3u8_url, video_id, 'mp4', 'm3u8_native',
 153                     m3u8_id=format_id, fatal=False)
 154                 if format_id == 'vf':
 155                     for f in m3u8_formats:
 156                         f['language'] = 'fr'
 157                 formats.extend(m3u8_formats)
 158         if not error:
 159             error = options.get('error')
 160         if not formats and error:
 161             raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
 162         self._sort_formats(formats)
 163
 164         return {
 165             'id': video_id,
 166             'title': title,
 167             'description': strip_or_none(metas.get('summary') or video_info.get('resume')),
 168             'thumbnail': video_info.get('image'),
 169             'formats': formats,
 170             'subtitles': self.extract_subtitles(sub_path, video_id),
 171             'episode': metas.get('subtitle') or video_info.get('videoTitle'),
 172             'series': video_info.get('playlistTitle'),
 173         }