Fix "invalid escape sequences" error on Python 3.6

[youtube-dl] / youtube_dl / extractor / allocine.py

diff --git a/youtube_dl/extractor/allocine.py b/youtube_dl/extractor/allocine.py
index 7bd7978841d06747145feeda56624de84747fcc1..90f11d39f5393528e75ff641342cfda8c8706e0b 100644 (file)
--- a/youtube_dl/extractor/allocine.py
+++ b/youtube_dl/extractor/allocine.py
@@ -1,88 +1,109 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
-import re
-import json
-
 from .common import InfoExtractor
 from ..utils import (
-    compat_str,
+    remove_end,
     qualities,
-    determine_ext,
+    url_basename,
 )
 
 
 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/(?: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',
         'md5': '0c9fcf59a841f65635fa300ac43d8269',
         'info_dict': {
             'id': '19546517',
+            'display_id': '18635087',
             'ext': 'mp4',
             'title': 'Astérix - Le Domaine des Dieux Teaser VF',
             'description': 'md5:4a754271d9c6f16c72629a8a993ee884',
-            'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': r're:http://.*\.jpg',
         },
     }, {
         'url': 'http://www.allocine.fr/video/player_gen_cmedia=19540403&cfilm=222257.html',
         'md5': 'd0cdce5d2b9522ce279fdfec07ff16e0',
         'info_dict': {
             'id': '19540403',
+            'display_id': '19540403',
             'ext': 'mp4',
             'title': 'Planes 2 Bande-annonce VF',
-            'description': 'md5:eeaffe7c2d634525e21159b93acf3b1e',
-            'thumbnail': 're:http://.*\.jpg',
+            'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway',
+            'thumbnail': r're:http://.*\.jpg',
         },
     }, {
-        'url': 'http://www.allocine.fr/film/fichefilm_gen_cfilm=181290.html',
+        'url': 'http://www.allocine.fr/video/player_gen_cmedia=19544709&cfilm=181290.html',
         'md5': '101250fb127ef9ca3d73186ff22a47ce',
         'info_dict': {
             'id': '19544709',
+            'display_id': '19544709',
             'ext': 'mp4',
             'title': 'Dragons 2 - Bande annonce finale VF',
-            'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac',
-            'thumbnail': 're:http://.*\.jpg',
+            'description': 'md5:6cdd2d7c2687d4c6aafe80a35e17267a',
+            'thumbnail': r're:http://.*\.jpg',
+        },
+    }, {
+        'url': 'http://www.allocine.fr/video/video-19550147/',
+        'md5': '3566c0668c0235e2d224fd8edb389f67',
+        'info_dict': {
+            'id': '19550147',
+            'ext': 'mp4',
+            'title': 'Faux Raccord N°123 - Les gaffes de Cliffhanger',
+            'description': 'md5:bc734b83ffa2d8a12188d9eb48bb6354',
+            'thumbnail': r're:http://.*\.jpg',
         },
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        typ = mobj.group('typ')
-        display_id = mobj.group('id')
+        display_id = self._match_id(url)
 
         webpage = self._download_webpage(url, display_id)
 
-        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')
+        formats = []
+        quality = qualities(['ld', 'md', 'hd'])
 
-            player_data = json.loads(player)
-            video_id = compat_str(player_data['refMedia'])
+        model = self._html_search_regex(
+            r'data-model="([^"]+)"', webpage, 'data model', default=None)
+        if model:
+            model_data = self._parse_json(model, display_id)
 
-        xml = self._download_xml('http://www.allocine.fr/ws/AcVisiondataV4.ashx?media=%s' % video_id, display_id)
+            for video_url in model_data['sources'].values():
+                video_id, format_id = url_basename(video_url).split('_')[:2]
+                formats.append({
+                    'format_id': format_id,
+                    'quality': quality(format_id),
+                    'url': video_url,
+                })
 
-        video = xml.find('.//AcVisionVideo').attrib
-        quality = qualities(['ld', 'md', 'hd'])
+            title = model_data['title']
+        else:
+            video_id = display_id
+            media_data = self._download_json(
+                'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media=%s' % video_id, display_id)
+            for key, value in media_data['video'].items():
+                if not key.endswith('Path'):
+                    continue
 
-        formats = []
-        for k, v in video.items():
-            if re.match(r'.+_path', k):
-                format_id = k.split('_')[0]
+                format_id = key[:-len('Path')]
                 formats.append({
                     'format_id': format_id,
                     'quality': quality(format_id),
-                    'url': v,
-                    'ext': determine_ext(v),
+                    'url': value,
                 })
 
+            title = remove_end(self._html_search_regex(
+                r'(?s)<title>(.+?)</title>', webpage, 'title'
+            ).strip(), ' - AlloCiné')
+
         self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'title': video['videoTitle'],
+            'display_id': display_id,
+            'title': title,
             'thumbnail': self._og_search_thumbnail(webpage),
             'formats': formats,
             'description': self._og_search_description(webpage),