Merge branch 'upstream'

1 files changed, 99 insertions, 30 deletions

diff --git a/youtube_dl/extractor/youku.py b/youtube_dl/extractor/youku.py
index 37be440..dcce15d 100644
--- a/youtube_dl/extractor/youku.py
+++ b/youtube_dl/extractor/youku.py
@@ -10,7 +10,11 @@ import time
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
-    get_element_by_attribute,
+    get_element_by_class,
+    js_to_json,
+    str_or_none,
+    strip_jsonp,
+    urljoin,
 )
 
 
@@ -19,7 +23,9 @@ class YoukuIE(InfoExtractor):
     IE_DESC = '优酷'
     _VALID_URL = r'''(?x)
         (?:
-            http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
+            https?://(
+                (?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
+                video\.tudou\.com/v/)|
             youku:)
         (?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
     '''
@@ -31,6 +37,12 @@ class YoukuIE(InfoExtractor):
             'id': 'XMTc1ODE5Njcy',
             'title': '★Smile﹗♡ Git Fresh -Booty Music舞蹈.',
             'ext': 'mp4',
+            'duration': 74.73,
+            'thumbnail': r're:^https?://.*',
+            'uploader': '。躲猫猫、',
+            'uploader_id': '36017967',
+            'uploader_url': 'http://i.youku.com/u/UMTQ0MDcxODY4',
+            'tags': list,
         }
     }, {
         'url': 'http://player.youku.com/player.php/sid/XNDgyMDQ2NTQw/v.swf',
@@ -41,6 +53,12 @@ class YoukuIE(InfoExtractor):
             'id': 'XODgxNjg1Mzk2',
             'ext': 'mp4',
             'title': '武媚娘传奇 85',
+            'duration': 1999.61,
+            'thumbnail': r're:^https?://.*',
+            'uploader': '疯狂豆花',
+            'uploader_id': '62583473',
+            'uploader_url': 'http://i.youku.com/u/UMjUwMzMzODky',
+            'tags': list,
         },
     }, {
         'url': 'http://v.youku.com/v_show/id_XMTI1OTczNDM5Mg==.html',
@@ -48,6 +66,12 @@ class YoukuIE(InfoExtractor):
             'id': 'XMTI1OTczNDM5Mg',
             'ext': 'mp4',
             'title': '花千骨 04',
+            'duration': 2363,
+            'thumbnail': r're:^https?://.*',
+            'uploader': '放剧场-花千骨',
+            'uploader_id': '772849359',
+            'uploader_url': 'http://i.youku.com/u/UMzA5MTM5NzQzNg==',
+            'tags': list,
         },
     }, {
         'url': 'http://v.youku.com/v_show/id_XNjA1NzA2Njgw.html',
@@ -56,6 +80,12 @@ class YoukuIE(InfoExtractor):
             'id': 'XNjA1NzA2Njgw',
             'ext': 'mp4',
             'title': '邢義田复旦讲座之想象中的胡人—从“左衽孔子”说起',
+            'duration': 7264.5,
+            'thumbnail': r're:^https?://.*',
+            'uploader': 'FoxJin1006',
+            'uploader_id': '322014285',
+            'uploader_url': 'http://i.youku.com/u/UMTI4ODA1NzE0MA==',
+            'tags': list,
         },
         'params': {
             'videopassword': '100600',
@@ -67,7 +97,29 @@ class YoukuIE(InfoExtractor):
             'id': 'XOTUxMzg4NDMy',
             'ext': 'mp4',
             'title': '我的世界☆明月庄主☆车震猎杀☆杀人艺术Minecraft',
+            'duration': 702.08,
+            'thumbnail': r're:^https?://.*',
+            'uploader': '明月庄主moon',
+            'uploader_id': '38465621',
+            'uploader_url': 'http://i.youku.com/u/UMTUzODYyNDg0',
+            'tags': list,
         },
+    }, {
+        'url': 'http://video.tudou.com/v/XMjIyNzAzMTQ4NA==.html?f=46177805',
+        'info_dict': {
+            'id': 'XMjIyNzAzMTQ4NA',
+            'ext': 'mp4',
+            'title': '卡马乔国足开大脚长传冲吊集锦',
+            'duration': 289,
+            'thumbnail': r're:^https?://.*',
+            'uploader': '阿卜杜拉之星',
+            'uploader_id': '2382249',
+            'uploader_url': 'http://i.youku.com/u/UOTUyODk5Ng==',
+            'tags': list,
+        },
+    }, {
+        'url': 'http://video.tudou.com/v/XMjE4ODI3OTg2MA==.html',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -104,7 +156,7 @@ class YoukuIE(InfoExtractor):
         # request basic data
         basic_data_params = {
             'vid': video_id,
-            'ccode': '0401',
+            'ccode': '0402' if 'tudou.com' in url else '0401',
             'client_ip': '192.168.1.1',
             'utid': cna,
             'client_ts': time.time() / 1000,
@@ -139,7 +191,8 @@ class YoukuIE(InfoExtractor):
                 raise ExtractorError(msg)
 
         # get video title
-        title = data['video']['title']
+        video_data = data['video']
+        title = video_data['title']
 
         formats = [{
             'url': stream['m3u8_url'],
@@ -156,53 +209,69 @@ class YoukuIE(InfoExtractor):
             'id': video_id,
             'title': title,
             'formats': formats,
+            'duration': video_data.get('seconds'),
+            'thumbnail': video_data.get('logo'),
+            'uploader': video_data.get('username'),
+            'uploader_id': str_or_none(video_data.get('userid')),
+            'uploader_url': data.get('uploader', {}).get('homepage'),
+            'tags': video_data.get('tags'),
         }
 
 
 class YoukuShowIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?youku\.com/show_page/id_(?P<id>[0-9a-z]+)\.html'
+    _VALID_URL = r'https?://list\.youku\.com/show/id_(?P<id>[0-9a-z]+)\.html'
     IE_NAME = 'youku:show'
 
     _TEST = {
-        'url': 'http://www.youku.com/show_page/id_zc7c670be07ff11e48b3f.html',
+        'url': 'http://list.youku.com/show/id_zc7c670be07ff11e48b3f.html',
         'info_dict': {
             'id': 'zc7c670be07ff11e48b3f',
             'title': '花千骨 未删减版',
-            'description': 'md5:578d4f2145ae3f9128d9d4d863312910',
+            'description': 'md5:a1ae6f5618571bbeb5c9821f9c81b558',
         },
         'playlist_count': 50,
     }
 
     _PAGE_SIZE = 40
 
-    def _find_videos_in_page(self, webpage):
-        videos = re.findall(
-            r'<li><a[^>]+href="(?P<url>https?://v\.youku\.com/[^"]+)"[^>]+title="(?P<title>[^"]+)"', webpage)
-        return [
-            self.url_result(video_url, YoukuIE.ie_key(), title)
-            for video_url, title in videos]
-
     def _real_extract(self, url):
         show_id = self._match_id(url)
         webpage = self._download_webpage(url, show_id)
 
-        entries = self._find_videos_in_page(webpage)
-
-        playlist_title = self._html_search_regex(
-            r'<span[^>]+class="name">([^<]+)</span>', webpage, 'playlist title', fatal=False)
-        detail_div = get_element_by_attribute('class', 'detail', webpage) or ''
-        playlist_description = self._html_search_regex(
-            r'<span[^>]+style="display:none"[^>]*>([^<]+)</span>',
-            detail_div, 'playlist description', fatal=False)
-
-        for idx in itertools.count(1):
-            episodes_page = self._download_webpage(
-                'http://www.youku.com/show_episode/id_%s.html' % show_id,
-                show_id, query={'divid': 'reload_%d' % (idx * self._PAGE_SIZE + 1)},
-                note='Downloading episodes page %d' % idx)
-            new_entries = self._find_videos_in_page(episodes_page)
+        entries = []
+        page_config = self._parse_json(self._search_regex(
+            r'var\s+PageConfig\s*=\s*({.+});', webpage, 'page config'),
+            show_id, transform_source=js_to_json)
+        for idx in itertools.count(0):
+            if idx == 0:
+                playlist_data_url = 'http://list.youku.com/show/module'
+                query = {'id': page_config['showid'], 'tab': 'point'}
+            else:
+                playlist_data_url = 'http://list.youku.com/show/point'
+                query = {
+                    'id': page_config['showid'],
+                    'stage': 'reload_%d' % (self._PAGE_SIZE * idx + 1),
+                }
+            query['callback'] = 'cb'
+            playlist_data = self._download_json(
+                playlist_data_url, show_id, query=query,
+                note='Downloading playlist data page %d' % (idx + 1),
+                transform_source=lambda s: js_to_json(strip_jsonp(s)))['html']
+            video_urls = re.findall(
+                r'<div[^>]+class="p-thumb"[^<]+<a[^>]+href="([^"]+)"',
+                playlist_data)
+            new_entries = [
+                self.url_result(urljoin(url, video_url), YoukuIE.ie_key())
+                for video_url in video_urls]
             entries.extend(new_entries)
             if len(new_entries) < self._PAGE_SIZE:
                 break
 
-        return self.playlist_result(entries, show_id, playlist_title, playlist_description)
+        desc = self._html_search_meta('description', webpage, fatal=False)
+        playlist_title = desc.split(',')[0] if desc else None
+        detail_li = get_element_by_class('p-intro', webpage)
+        playlist_description = get_element_by_class(
+            'intro-more', detail_li) if detail_li else None
+
+        return self.playlist_result(
+            entries, show_id, playlist_title, playlist_description)