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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import os
   6
   7 from .common import InfoExtractor
   8 from ..aes import aes_cbc_decrypt
   9 from ..compat import (
  10     compat_b64decode,
  11     compat_ord,
  12 )
  13 from ..utils import (
  14     bytes_to_intlist,
  15     ExtractorError,
  16     float_or_none,
  17     intlist_to_bytes,
  18     srt_subtitles_timecode,
  19     strip_or_none,
  20     urljoin,
  21 )
  22
  23
  24 class ADNIE(InfoExtractor):
  25     IE_DESC = 'Anime Digital Network'
  26     _VALID_URL = r'https?://(?:www\.)?animedigitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
  27     _TEST = {
  28         'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
  29         'md5': 'e497370d847fd79d9d4c74be55575c7a',
  30         'info_dict': {
  31             'id': '7778',
  32             'ext': 'mp4',
  33             'title': 'Blue Exorcist - Kyôto Saga - Épisode 1',
  34             'description': 'md5:2f7b5aa76edbc1a7a92cedcda8a528d5',
  35         }
  36     }
  37     _BASE_URL = 'http://animedigitalnetwork.fr'
  38
  39     def _get_subtitles(self, sub_path, video_id):
  40         if not sub_path:
  41             return None
  42
  43         enc_subtitles = self._download_webpage(
  44             urljoin(self._BASE_URL, sub_path),
  45             video_id, fatal=False, headers={
  46                 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:53.0) Gecko/20100101 Firefox/53.0',
  47             })
  48         if not enc_subtitles:
  49             return None
  50
  51         # http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
  52         dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
  53             bytes_to_intlist(compat_b64decode(enc_subtitles[24:])),
  54             bytes_to_intlist(b'\x1b\xe0\x29\x61\x38\x94\x24\x00\x12\xbd\xc5\x80\xac\xce\xbe\xb0'),
  55             bytes_to_intlist(compat_b64decode(enc_subtitles[:24]))
  56         ))
  57         subtitles_json = self._parse_json(
  58             dec_subtitles[:-compat_ord(dec_subtitles[-1])].decode(),
  59             None, fatal=False)
  60         if not subtitles_json:
  61             return None
  62
  63         subtitles = {}
  64         for sub_lang, sub in subtitles_json.items():
  65             srt = ''
  66             for num, current in enumerate(sub):
  67                 start, end, text = (
  68                     float_or_none(current.get('startTime')),
  69                     float_or_none(current.get('endTime')),
  70                     current.get('text'))
  71                 if start is None or end is None or text is None:
  72                     continue
  73                 srt += os.linesep.join(
  74                     (
  75                         '%d' % num,
  76                         '%s --> %s' % (
  77                             srt_subtitles_timecode(start),
  78                             srt_subtitles_timecode(end)),
  79                         text,
  80                         os.linesep,
  81                     ))
  82
  83             if sub_lang == 'vostf':
  84                 sub_lang = 'fr'
  85             subtitles.setdefault(sub_lang, []).extend([{
  86                 'ext': 'json',
  87                 'data': json.dumps(sub),
  88             }, {
  89                 'ext': 'srt',
  90                 'data': srt,
  91             }])
  92         return subtitles
  93
  94     def _real_extract(self, url):
  95         video_id = self._match_id(url)
  96         webpage = self._download_webpage(url, video_id)
  97         player_config = self._parse_json(self._search_regex(
  98             r'playerConfig\s*=\s*({.+});', webpage, 'player config'), video_id)
  99
 100         video_info = {}
 101         video_info_str = self._search_regex(
 102             r'videoInfo\s*=\s*({.+});', webpage,
 103             'video info', fatal=False)
 104         if video_info_str:
 105             video_info = self._parse_json(
 106                 video_info_str, video_id, fatal=False) or {}
 107
 108         options = player_config.get('options') or {}
 109         metas = options.get('metas') or {}
 110         title = metas.get('title') or video_info['title']
 111         links = player_config.get('links') or {}
 112         error = None
 113         if not links:
 114             links_url = player_config['linksurl']
 115             links_data = self._download_json(urljoin(
 116                 self._BASE_URL, links_url), video_id)
 117             links = links_data.get('links') or {}
 118             error = links_data.get('error')
 119
 120         formats = []
 121         for format_id, qualities in links.items():
 122             if not isinstance(qualities, dict):
 123                 continue
 124             for load_balancer_url in qualities.values():
 125                 load_balancer_data = self._download_json(
 126                     load_balancer_url, video_id, fatal=False) or {}
 127                 m3u8_url = load_balancer_data.get('location')
 128                 if not m3u8_url:
 129                     continue
 130                 m3u8_formats = self._extract_m3u8_formats(
 131                     m3u8_url, video_id, 'mp4', 'm3u8_native',
 132                     m3u8_id=format_id, fatal=False)
 133                 if format_id == 'vf':
 134                     for f in m3u8_formats:
 135                         f['language'] = 'fr'
 136                 formats.extend(m3u8_formats)
 137         if not error:
 138             error = options.get('error')
 139         if not formats and error:
 140             raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
 141         self._sort_formats(formats)
 142
 143         return {
 144             'id': video_id,
 145             'title': title,
 146             'description': strip_or_none(metas.get('summary') or video_info.get('resume')),
 147             'thumbnail': video_info.get('image'),
 148             'formats': formats,
 149             'subtitles': self.extract_subtitles(player_config.get('subtitles'), video_id),
 150             'episode': metas.get('subtitle') or video_info.get('videoTitle'),
 151             'series': video_info.get('playlistTitle'),
 152         }