[youtube] Add ability to authenticate with cookies

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

diff --git a/youtube_dl/extractor/rtbf.py b/youtube_dl/extractor/rtbf.py
index 544539665567bbb197f6c1132ff971fde4edc66f..28cc5522d89083cec2ad7631d51fb0aa0798ccbd 100644 (file)
--- a/youtube_dl/extractor/rtbf.py
+++ b/youtube_dl/extractor/rtbf.py
@@ -1,48 +1,98 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-import json
-
 from .common import InfoExtractor
-from ..utils import clean_html
+from ..utils import (
+    int_or_none,
+    ExtractorError,
+)
+
 
-class RTBFVideoIE(InfoExtractor):
-    _VALID_URL = r'https?://www.rtbf.be/video/(?P<title>[^?]+)\?.*id=(?P<id>[0-9]+)'
-    _TEST = {
+class RTBFIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?rtbf\.be/
+        (?:
+            video/[^?]+\?.*\bid=|
+            ouftivi/(?:[^/]+/)*[^?]+\?.*\bvideoId=|
+            auvio/[^/]+\?.*id=
+        )(?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)',
+            'description': 'Football - Diables Rouges',
             'duration': 3099,
+            'upload_date': '20140425',
+            'timestamp': 1398456336,
+            'uploader': 'rtbfsport',
         }
+    }, {
+        # 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,
+    }, {
+        'url': 'http://www.rtbf.be/auvio/detail_jeudi-en-prime-siegfried-bracke?id=2102996',
+        'only_matching': True,
+    }]
+    _IMAGE_HOST = 'http://ds1.ds.static.rtbf.be'
+    _PROVIDERS = {
+        'YOUTUBE': 'Youtube',
+        'DAILYMOTION': 'Dailymotion',
+        'VIMEO': 'Vimeo',
     }
+    _QUALITIES = [
+        ('mobile', 'SD'),
+        ('web', 'MD'),
+        ('high', 'HD'),
+    ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
+        data = self._download_json(
+            'http://www.rtbf.be/api/media/video?method=getVideoDetail&args[]=%s' % video_id, video_id)
+
+        error = data.get('error')
+        if error:
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
+
+        data = data['data']
 
-        # TODO more code goes here, for example ...
-        webpage = self._download_webpage(url, video_id)
-        title = self._html_search_regex(
-            r'<meta property="og:description" content="([^"]*)"',
-            webpage, 'title', mobj.group('title'))
+        provider = data.get('provider')
+        if provider in self._PROVIDERS:
+            return self.url_result(data['url'], self._PROVIDERS[provider])
 
-        iframe_url = self._html_search_regex(r'<iframe [^>]*src="([^"]+)"',
-            webpage, 'iframe')
-        iframe = self._download_webpage(iframe_url, video_id)
+        formats = []
+        for key, format_id in self._QUALITIES:
+            format_url = data.get(key + 'Url')
+            if format_url:
+                formats.append({
+                    'format_id': format_id,
+                    'url': format_url,
+                })
 
-        data_video_idx = iframe.find('data-video')
-        next_data_idx = iframe.find('data-', data_video_idx + 1)
-        json_data_start = data_video_idx + len('data-video=') + 1
-        json_data_end = next_data_idx - 2
-        video_data = json.loads(clean_html(iframe[json_data_start:json_data_end]))
+        thumbnails = []
+        for thumbnail_id, thumbnail_url in data.get('thumbnail', {}).items():
+            if thumbnail_id != 'default':
+                thumbnails.append({
+                    'url': self._IMAGE_HOST + thumbnail_url,
+                    'id': thumbnail_id,
+                })
 
         return {
             'id': video_id,
-            'title': title,
-            'url': video_data['data']['downloadUrl'],
-            'duration': video_data['data']['duration'],
+            'formats': formats,
+            'title': data['title'],
+            'description': data.get('description') or data.get('subtitle'),
+            'thumbnails': thumbnails,
+            'duration': data.get('duration') or data.get('realDuration'),
+            'timestamp': int_or_none(data.get('created')),
+            'view_count': int_or_none(data.get('viewCount')),
+            'uploader': data.get('channel'),
+            'tags': data.get('tags'),
         }