[youtube] Fix extraction.

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

diff --git a/youtube_dl/extractor/bet.py b/youtube_dl/extractor/bet.py
index c1fc433f77d7aec1dc80d2b7074865d02484a40b..d7ceaa85e45c7da4ffbf3909b1e00f8ffd9ac75c 100644 (file)
--- a/youtube_dl/extractor/bet.py
+++ b/youtube_dl/extractor/bet.py
@@ -1,31 +1,26 @@
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
-from ..utils import (
-    compat_urllib_parse,
-    xpath_text,
-    xpath_with_ns,
-    int_or_none,
-    parse_iso8601,
-)
+from .mtv import MTVServicesInfoExtractor
+from ..utils import unified_strdate
 
 
-class BetIE(InfoExtractor):
+class BetIE(MTVServicesInfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html'
     _TESTS = [
         {
             'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
             'info_dict': {
-                'id': '417cd61c-c793-4e8e-b006-e445ecc45add',
+                'id': '07e96bd3-8850-3051-b856-271b457f0ab8',
                 'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
                 'ext': 'flv',
-                'title': 'BET News Presents: A Conversation With President Obama',
-                'description': 'md5:5a88d8ae912c1b33e090290af7ec33c6',
+                'title': 'A Conversation With President Obama',
+                'description': 'President Obama urges persistence in confronting racism and bias.',
                 'duration': 1534,
-                'timestamp': 1418075340,
                 'upload_date': '20141208',
-                'uploader': 'admin',
-                'thumbnail': 're:(?i)^https?://.*\.jpg$',
+                'thumbnail': r're:(?i)^https?://.*\.jpg$',
+                'subtitles': {
+                    'en': 'mincount:2',
+                }
             },
             'params': {
                 # rtmp download
@@ -35,16 +30,17 @@ class BetIE(InfoExtractor):
         {
             'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html',
             'info_dict': {
-                'id': '4160e53b-ad41-43b1-980f-8d85f63121f4',
+                'id': '9f516bf1-7543-39c4-8076-dd441b459ba9',
                 'display_id': 'justice-for-ferguson-a-community-reacts',
                 'ext': 'flv',
                 'title': 'Justice for Ferguson: A Community Reacts',
                 'description': 'A BET News special.',
                 'duration': 1696,
-                'timestamp': 1416942360,
                 'upload_date': '20141125',
-                'uploader': 'admin',
-                'thumbnail': 're:(?i)^https?://.*\.jpg$',
+                'thumbnail': r're:(?i)^https?://.*\.jpg$',
+                'subtitles': {
+                    'en': 'mincount:2',
+                }
             },
             'params': {
                 # rtmp download
@@ -53,56 +49,32 @@ class BetIE(InfoExtractor):
         }
     ]
 
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, display_id)
+    _FEED_URL = "http://feeds.mtvnservices.com/od/feed/bet-mrss-player"
 
-        media_url = compat_urllib_parse.unquote(self._search_regex(
-            [r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"],
-            webpage, 'media URL'))
-
-        mrss = self._download_xml(media_url, display_id)
-
-        item = mrss.find('./channel/item')
-
-        NS_MAP = {
-            'dc': 'http://purl.org/dc/elements/1.1/',
-            'media': 'http://search.yahoo.com/mrss/',
-            'ka': 'http://kickapps.com/karss',
+    def _get_feed_query(self, uri):
+        return {
+            'uuid': uri,
         }
 
-        title = xpath_text(item, './title', 'title')
-        description = xpath_text(
-            item, './description', 'description', fatal=False)
+    def _extract_mgid(self, webpage):
+        return self._search_regex(r'data-uri="([^"]+)', webpage, 'mgid')
 
-        video_id = xpath_text(item, './guid', 'video id', fatal=False)
-
-        timestamp = parse_iso8601(xpath_text(
-            item, xpath_with_ns('./dc:date', NS_MAP),
-            'upload date', fatal=False))
-        uploader = xpath_text(
-            item, xpath_with_ns('./dc:creator', NS_MAP),
-            'uploader', fatal=False)
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
 
-        media_content = item.find(
-            xpath_with_ns('./media:content', NS_MAP))
-        duration = int_or_none(media_content.get('duration'))
-        smil_url = media_content.get('url')
+        webpage = self._download_webpage(url, display_id)
+        mgid = self._extract_mgid(webpage)
+        videos_info = self._get_videos_info(mgid)
 
-        thumbnail = media_content.find(
-            xpath_with_ns('./media:thumbnail', NS_MAP)).get('url')
+        info_dict = videos_info['entries'][0]
 
-        formats = self._extract_smil_formats(smil_url, display_id)
+        upload_date = unified_strdate(self._html_search_meta('date', webpage))
+        description = self._html_search_meta('description', webpage)
 
-        return {
-            'id': video_id,
+        info_dict.update({
             'display_id': display_id,
-            'title': title,
             'description': description,
-            'thumbnail': thumbnail,
-            'timestamp': timestamp,
-            'uploader': uploader,
-            'duration': duration,
-            'formats': formats,
-        }
+            'upload_date': upload_date,
+        })
+
+        return info_dict