Merge tag 'upstream/2015.11.27.1'

[youtubedl] / youtube_dl / extractor / rtbf.py

diff --git a/youtube_dl/extractor/rtbf.py b/youtube_dl/extractor/rtbf.py
index 205f8a167601f9f7c6a20ccf721439a7b070516f..e42b319a3e224aa6b078cad7756e5c44b7f620d8 100644 (file)
--- a/youtube_dl/extractor/rtbf.py
+++ b/youtube_dl/extractor/rtbf.py
@@ -1,49 +1,70 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 

-import re
-import json
-

 from .common import InfoExtractor
 from .common import InfoExtractor

+from ..utils import (
+    int_or_none,
+    unescapeHTML,
+)

 
 
 class RTBFIE(InfoExtractor):
 
 
 class RTBFIE(InfoExtractor):

-    _VALID_URL = r'https?://www.rtbf.be/video/[^\?]+\?id=(?P<id>\d+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?rtbf\.be/(?:video/[^?]+\?.*\bid=|ouftivi/(?:[^/]+/)*[^?]+\?.*\bvideoId=)(?P<id>\d+)'
+    _TESTS = [{

         'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274',
         'md5': '799f334ddf2c0a582ba80c44655be570',
         'info_dict': {
             'id': '1921274',
             'ext': 'mp4',
             'title': 'Les Diables au coeur (épisode 2)',
         'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274',
         'md5': '799f334ddf2c0a582ba80c44655be570',
         'info_dict': {
             'id': '1921274',
             'ext': 'mp4',
             'title': 'Les Diables au coeur (épisode 2)',

-            'description': 'Football - Diables Rouges',

             'duration': 3099,
             'duration': 3099,

-            'timestamp': 1398456336,
-            'upload_date': '20140425',

         }
         }

-    }
+    }, {
+        # geo restricted
+        'url': 'http://www.rtbf.be/ouftivi/heros/detail_scooby-doo-mysteres-associes?id=1097&videoId=2057442',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.rtbf.be/ouftivi/niouzz?videoId=2055858',
+        'only_matching': True,
+    }]

 
 

-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+    _QUALITIES = [
+        ('mobile', 'mobile'),
+        ('web', 'SD'),
+        ('url', 'MD'),
+        ('high', 'HD'),
+    ]

 
 

-        page = self._download_webpage('https://www.rtbf.be/video/embed?id=%s' % video_id, video_id)
+    def _real_extract(self, url):
+        video_id = self._match_id(url)

 
 

-        data = json.loads(self._html_search_regex(
-            r'<div class="js-player-embed" data-video="([^"]+)"', page, 'data video'))['data']
+        webpage = self._download_webpage(
+            'http://www.rtbf.be/video/embed?id=%s' % video_id, video_id)

 
 

-        video_url = data.get('downloadUrl') or data.get('url')
+        data = self._parse_json(
+            unescapeHTML(self._search_regex(
+                r'data-media="([^"]+)"', webpage, 'data video')),
+            video_id)

 
 

-        if data['provider'].lower() == 'youtube':
+        if data.get('provider').lower() == 'youtube':
+            video_url = data.get('downloadUrl') or data.get('url')

             return self.url_result(video_url, 'Youtube')
             return self.url_result(video_url, 'Youtube')

+        formats = []
+        for key, format_id in self._QUALITIES:
+            format_url = data['sources'].get(key)
+            if format_url:
+                formats.append({
+                    'format_id': format_id,
+                    'url': format_url,
+                })

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,

-            'url': video_url,
+            'formats': formats,

             'title': data['title'],
             'description': data.get('description') or data.get('subtitle'),
             'title': data['title'],
             'description': data.get('description') or data.get('subtitle'),

-            'thumbnail': data['thumbnail']['large'],
+            'thumbnail': data.get('thumbnail'),

             'duration': data.get('duration') or data.get('realDuration'),
             'duration': data.get('duration') or data.get('realDuration'),

-            'timestamp': data['created'],
-            'view_count': data['viewCount'],
+            'timestamp': int_or_none(data.get('created')),
+            'view_count': int_or_none(data.get('viewCount')),

         }
         }