Merge pull request #1 from e7appew/python3

[youtubedl] / youtube_dl / extractor / allocine.py

diff --git a/youtube_dl/extractor/allocine.py b/youtube_dl/extractor/allocine.py
index 7bd7978841d06747145feeda56624de84747fcc1..190bc2cc8730853a23b9025f1849bf234a32e001 100644 (file)
--- a/youtube_dl/extractor/allocine.py
+++ b/youtube_dl/extractor/allocine.py
@@ -5,15 +5,16 @@ import re
 import json
 
 from .common import InfoExtractor
 import json
 
 from .common import InfoExtractor

+from ..compat import compat_str

 from ..utils import (
 from ..utils import (

-    compat_str,

     qualities,
     qualities,

-    determine_ext,
+    unescapeHTML,
+    xpath_element,

 )
 
 
 class AllocineIE(InfoExtractor):
 )
 
 
 class AllocineIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=)(?P<id>[0-9]+)(?:\.html)?'
+    _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>[0-9]+)(?:\.html)?'

 
     _TESTS = [{
         'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html',
 
     _TESTS = [{
         'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html',


@@ -22,7 +23,7 @@ class AllocineIE(InfoExtractor):
             'id': '19546517',
             'ext': 'mp4',
             'title': 'Astérix - Le Domaine des Dieux Teaser VF',
             'id': '19546517',
             'ext': 'mp4',
             'title': 'Astérix - Le Domaine des Dieux Teaser VF',

-            'description': 'md5:4a754271d9c6f16c72629a8a993ee884',
+            'description': 'md5:abcd09ce503c6560512c14ebfdb720d2',

             'thumbnail': 're:http://.*\.jpg',
         },
     }, {
             'thumbnail': 're:http://.*\.jpg',
         },
     }, {


@@ -32,7 +33,7 @@ class AllocineIE(InfoExtractor):
             'id': '19540403',
             'ext': 'mp4',
             'title': 'Planes 2 Bande-annonce VF',
             'id': '19540403',
             'ext': 'mp4',
             'title': 'Planes 2 Bande-annonce VF',

-            'description': 'md5:eeaffe7c2d634525e21159b93acf3b1e',
+            'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway',

             'thumbnail': 're:http://.*\.jpg',
         },
     }, {
             'thumbnail': 're:http://.*\.jpg',
         },
     }, {


@@ -42,9 +43,12 @@ class AllocineIE(InfoExtractor):
             'id': '19544709',
             'ext': 'mp4',
             'title': 'Dragons 2 - Bande annonce finale VF',
             'id': '19544709',
             'ext': 'mp4',
             'title': 'Dragons 2 - Bande annonce finale VF',

-            'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac',
+            'description': 'md5:601d15393ac40f249648ef000720e7e3',

             'thumbnail': 're:http://.*\.jpg',
         },
             'thumbnail': 're:http://.*\.jpg',
         },

+    }, {
+        'url': 'http://www.allocine.fr/video/video-19550147/',
+        'only_matching': True,

     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):


@@ -57,14 +61,18 @@ class AllocineIE(InfoExtractor):
         if typ == 'film':
             video_id = self._search_regex(r'href="/video/player_gen_cmedia=([0-9]+).+"', webpage, 'video id')
         else:
         if typ == 'film':
             video_id = self._search_regex(r'href="/video/player_gen_cmedia=([0-9]+).+"', webpage, 'video id')
         else:

-            player = self._search_regex(r'data-player=\'([^\']+)\'>', webpage, 'data player')
-
-            player_data = json.loads(player)
-            video_id = compat_str(player_data['refMedia'])
+            player = self._search_regex(r'data-player=\'([^\']+)\'>', webpage, 'data player', default=None)
+            if player:
+                player_data = json.loads(player)
+                video_id = compat_str(player_data['refMedia'])
+            else:
+                model = self._search_regex(r'data-model="([^"]+)">', webpage, 'data model')
+                model_data = self._parse_json(unescapeHTML(model), display_id)
+                video_id = compat_str(model_data['id'])

 
         xml = self._download_xml('http://www.allocine.fr/ws/AcVisiondataV4.ashx?media=%s' % video_id, display_id)
 
 
         xml = self._download_xml('http://www.allocine.fr/ws/AcVisiondataV4.ashx?media=%s' % video_id, display_id)
 

-        video = xml.find('.//AcVisionVideo').attrib
+        video = xpath_element(xml, './/AcVisionVideo').attrib

         quality = qualities(['ld', 'md', 'hd'])
 
         formats = []
         quality = qualities(['ld', 'md', 'hd'])
 
         formats = []


@@ -75,9 +83,7 @@ class AllocineIE(InfoExtractor):
                     'format_id': format_id,
                     'quality': quality(format_id),
                     'url': v,
                     'format_id': format_id,
                     'quality': quality(format_id),
                     'url': v,

-                    'ext': determine_ext(v),

                 })
                 })

-

         self._sort_formats(formats)
 
         return {
         self._sort_formats(formats)
 
         return {