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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     remove_end,
   7     qualities,
   8     url_basename,
   9 )
  10
  11
  12 class AllocineIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?:article|video|film)/(?:fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>[0-9]+)(?:\.html)?'
  14
  15     _TESTS = [{
  16         'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html',
  17         'md5': '0c9fcf59a841f65635fa300ac43d8269',
  18         'info_dict': {
  19             'id': '19546517',
  20             'display_id': '18635087',
  21             'ext': 'mp4',
  22             'title': 'Astérix - Le Domaine des Dieux Teaser VF',
  23             'description': 'md5:4a754271d9c6f16c72629a8a993ee884',
  24             'thumbnail': 're:http://.*\.jpg',
  25         },
  26     }, {
  27         'url': 'http://www.allocine.fr/video/player_gen_cmedia=19540403&cfilm=222257.html',
  28         'md5': 'd0cdce5d2b9522ce279fdfec07ff16e0',
  29         'info_dict': {
  30             'id': '19540403',
  31             'display_id': '19540403',
  32             'ext': 'mp4',
  33             'title': 'Planes 2 Bande-annonce VF',
  34             'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway',
  35             'thumbnail': 're:http://.*\.jpg',
  36         },
  37     }, {
  38         'url': 'http://www.allocine.fr/video/player_gen_cmedia=19544709&cfilm=181290.html',
  39         'md5': '101250fb127ef9ca3d73186ff22a47ce',
  40         'info_dict': {
  41             'id': '19544709',
  42             'display_id': '19544709',
  43             'ext': 'mp4',
  44             'title': 'Dragons 2 - Bande annonce finale VF',
  45             'description': 'md5:6cdd2d7c2687d4c6aafe80a35e17267a',
  46             'thumbnail': 're:http://.*\.jpg',
  47         },
  48     }, {
  49         'url': 'http://www.allocine.fr/video/video-19550147/',
  50         'md5': '3566c0668c0235e2d224fd8edb389f67',
  51         'info_dict': {
  52             'id': '19550147',
  53             'ext': 'mp4',
  54             'title': 'Faux Raccord N°123 - Les gaffes de Cliffhanger',
  55             'description': 'md5:bc734b83ffa2d8a12188d9eb48bb6354',
  56             'thumbnail': 're:http://.*\.jpg',
  57         },
  58     }]
  59
  60     def _real_extract(self, url):
  61         display_id = self._match_id(url)
  62
  63         webpage = self._download_webpage(url, display_id)
  64
  65         formats = []
  66         quality = qualities(['ld', 'md', 'hd'])
  67
  68         model = self._html_search_regex(
  69             r'data-model="([^"]+)"', webpage, 'data model', default=None)
  70         if model:
  71             model_data = self._parse_json(model, display_id)
  72
  73             for video_url in model_data['sources'].values():
  74                 video_id, format_id = url_basename(video_url).split('_')[:2]
  75                 formats.append({
  76                     'format_id': format_id,
  77                     'quality': quality(format_id),
  78                     'url': video_url,
  79                 })
  80
  81             title = model_data['title']
  82         else:
  83             video_id = display_id
  84             media_data = self._download_json(
  85                 'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media=%s' % video_id, display_id)
  86             for key, value in media_data['video'].items():
  87                 if not key.endswith('Path'):
  88                     continue
  89
  90                 format_id = key[:-len('Path')]
  91                 formats.append({
  92                     'format_id': format_id,
  93                     'quality': quality(format_id),
  94                     'url': value,
  95                 })
  96
  97             title = remove_end(self._html_search_regex(
  98                 r'(?s)<title>(.+?)</title>', webpage, 'title'
  99             ).strip(), ' - AlloCiné')
 100
 101         self._sort_formats(formats)
 102
 103         return {
 104             'id': video_id,
 105             'display_id': display_id,
 106             'title': title,
 107             'thumbnail': self._og_search_thumbnail(webpage),
 108             'formats': formats,
 109             'description': self._og_search_description(webpage),
 110         }