Add WeiboIE (closes #1039)

It just embed video from other sites.
Modified the _VALID_URL of Youku to catch embed urls.

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 30d55d446051d51f98eccb7e019347d23dceb0b1..749fa65584067b6e74c9f534555e4e58f283d9ad 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -73,6 +73,7 @@ from .vimeo import VimeoIE
 from .vine import VineIE
 from .c56 import C56IE
 from .wat import WatIE
+from .weibo import WeiboIE
 from .wimp import WimpIE
 from .worldstarhiphop import WorldStarHipHopIE
 from .xhamster import XHamsterIE

diff --git a/youtube_dl/extractor/weibo.py b/youtube_dl/extractor/weibo.py
new file mode 100644 (file)
index 0000000..efcb591
--- /dev/null
+++ b/youtube_dl/extractor/weibo.py
@@ -0,0 +1,37 @@
+# coding: utf-8
+
+import re
+
+from .common import InfoExtractor
+
+class WeiboIE(InfoExtractor):
+    """
+    The videos in Weibo come from different sites, this IE just finds the link
+    to the external video and returns it.
+    """
+    _VALID_URL = r'https?://video\.weibo\.com/v/weishipin/t_(?P<id>.+?)\.htm'
+
+    _TEST = {
+        u'url': u'http://video.weibo.com/v/weishipin/t_zjUw2kZ.htm',
+        u'file': u'98322879.flv',
+        u'info_dict': {
+            u'title': u'魔声耳机最新广告“All Eyes On Us”',
+        },
+        u'note': u'Sina video',
+        u'params': {
+            u'skip_download': True,
+        },
+    }
+
+    # Additional example videos from different sites
+    # Youku: http://video.weibo.com/v/weishipin/t_zQGDWQ8.htm
+    # 56.com: http://video.weibo.com/v/weishipin/t_zQ44HxN.htm
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+        player_url = self._search_regex(r'var defaultPlayer="(.+?)"', webpage,
+                                        u'player url')
+        return self.url_result(player_url)
+

diff --git a/youtube_dl/extractor/youku.py b/youtube_dl/extractor/youku.py
index eb98298019c04334276688a7d9c6a5db8bd90664..996d384784cb827ed4baa3304b61782542ea0767 100644 (file)
--- a/youtube_dl/extractor/youku.py
+++ b/youtube_dl/extractor/youku.py
@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class YoukuIE(InfoExtractor):
-    _VALID_URL =  r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html'
+    _VALID_URL =  r'(?:http://)?(v|player)\.youku\.com/(v_show/id_|player\.php/sid/)(?P<ID>[A-Za-z0-9]+)(\.html|/v.swf)'
     _TEST =   {
         u"url": u"http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html",
         u"file": u"XNDgyMDQ2NTQw_part00.flv",