modified: src/you_get/extractors/__init__.py

new file:   src/you_get/extractors/freebuf.py
	modified:   tests/test.py

src/you_get/common.py

@@ -21,6 +21,7 @@ SITES = {
     'facebook'         : 'facebook',
     'fc2'              : 'fc2video',
     'flickr'           : 'flickr',
+    'freebuf'          : 'freebuf',
     'freesound'        : 'freesound',
     'fun'              : 'funshion',
     'google'           : 'google',

src/you_get/extractors/__init__.py

@@ -17,6 +17,7 @@ from .ehow import *
 from .facebook import *
 from .fc2video import *
 from .flickr import *
+from .freebuf import *
 from .freesound import *
 from .funshion import *
 from .google import *

src/you_get/extractors/freebuf.py

@@ -0,0 +1,65 @@
+#!/usr/bin/env python
+
+__all__ = ['freebuf_download']
+
+from ..common import *
+from .le import letvcloud_download_by_vu
+from .qq import qq_download
+from .youku import youku_download_by_vid
+from .tudou import tudou_download_by_id
+
+import json, re
+
+def freebuf_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
+    html = get_content(url)
+    title=''
+    source=''
+    vid=''
+    videolink=''
+    if re.match(r'^http://www.freebuf.com/.*',url):
+        title=match1(html,r'<div class="title">[^<>]+<h2>[ ]*([^<>]+)[ ]*<')
+        videolink=match1(html,r'<iframe[^<>]+src="([^"]+)"') or \
+                  match1(html,r'<embed[^<>]+src="([^"]+)"')
+        vid=match1(videolink,r'vid=([0-9a-zA-Z]+)') or \
+            match1(videolink, r'player\.youku\.com/embed/([a-zA-Z0-9=]+)') or \
+            match1(videolink,r'http://www.tudou.com/v/([^/]+)/')
+        source=getSourceByLink(videolink)
+    elif re.match(r'http://open.freebuf.com/.*',url):
+        title=match1(html,r'class="entry-title"[^>]*>([^<>]+)<')
+        uu=match1(html,r'"uu":"([0-9a-zA-Z]+)"')
+        vu=match1(html,r'"vu":"([0-9a-zA-Z]+)"')
+        if uu and vu:
+            source='letv'
+        else:
+            videolink=match1(html,r'<iframe[^<>]+src="([^"]+)"')
+            source=getSourceByLink(videolink)
+            vid=match1(videolink,r'vid=([0-9a-zA-Z]+)') or \
+                match1(videolink, r'player\.youku\.com/embed/([a-zA-Z0-9=]+)')
+    else:
+        raise NotImplementedError("url not included")
+    if source=='qq':
+        qq_download(videolink, output_dir=output_dir, merge=merge, info_only=info_only, **kwargs)
+    elif source=='letv':
+        letvcloud_download_by_vu(vu, uu, title=title, output_dir=output_dir, merge=merge, info_only=info_only)
+    elif source=='youku':
+        youku_download_by_vid(vid, title=title, output_dir=output_dir, merge=merge, info_only=info_only, **kwargs)
+    elif source=='tudou':
+        tudou_download_by_id(vid, title=title, output_dir=output_dir, merge=merge, info_only=info_only)
+    else:
+        raise NotImplementedError(source)
+
+def getSourceByLink(link):
+    source='None'
+    tail=1
+    while source!='qq' and source!='youku' and source!='tudou' and tail<4:
+        try:
+            source=re.search(r'http://(\w+)\.(\w+)\.(\w+)',link).group(tail)
+        except:
+            return source
+        tail+=1
+    return source
+
+site_info = "FREEBUF.com"
+download = freebuf_download
+download_playlist = playlist_not_supported('freebuf')
+

tests/test.py

@@ -8,23 +8,29 @@ from you_get.common import *
 
 class YouGetTests(unittest.TestCase):
 
-    def test_freesound(self):
+    # def test_freesound(self):
-        freesound.download("http://www.freesound.org/people/Corsica_S/sounds/184419/", info_only=True)
+    #     freesound.download("http://www.freesound.org/people/Corsica_S/sounds/184419/", info_only=True)
-
+    #
-    def test_imgur(self):
+    # def test_imgur(self):
-        imgur.download("http://imgur.com/WVLk5nD", info_only=True)
+    #     imgur.download("http://imgur.com/WVLk5nD", info_only=True)
-        imgur.download("http://imgur.com/gallery/WVLk5nD", info_only=True)
+    #     imgur.download("http://imgur.com/gallery/WVLk5nD", info_only=True)
-
+    #
-    def test_magisto(self):
+    # def test_magisto(self):
-        magisto.download("http://www.magisto.com/album/video/f3x9AAQORAkfDnIFDA", info_only=True)
+    #     magisto.download("http://www.magisto.com/album/video/f3x9AAQORAkfDnIFDA", info_only=True)
-
+    #
-    def test_mixcloud(self):
+    # def test_mixcloud(self):
-        mixcloud.download("http://www.mixcloud.com/DJVadim/north-america-are-you-ready/", info_only=True)
+    #     mixcloud.download("http://www.mixcloud.com/DJVadim/north-america-are-you-ready/", info_only=True)
-
+    #
-    def test_vimeo(self):
+    # def test_vimeo(self):
-        vimeo.download("http://vimeo.com/56810854", info_only=True)
+    #     vimeo.download("http://vimeo.com/56810854", info_only=True)
-
+    #
-    def test_youtube(self):
+    # def test_youtube(self):
-        youtube.download("http://www.youtube.com/watch?v=pzKerr0JIPA", info_only=True)
+    #     youtube.download("http://www.youtube.com/watch?v=pzKerr0JIPA", info_only=True)
-        youtube.download("http://youtu.be/pzKerr0JIPA", info_only=True)
+    #     youtube.download("http://youtu.be/pzKerr0JIPA", info_only=True)
-        youtube.download("http://www.youtube.com/attribution_link?u=/watch?v%3DldAKIzq7bvs%26feature%3Dshare", info_only=True)
+    #     youtube.download("http://www.youtube.com/attribution_link?u=/watch?v%3DldAKIzq7bvs%26feature%3Dshare", info_only=True)
+    def test_freebuf(self):
+        freebuf.download("http://www.freebuf.com/news/topnews/83364.html",info_only=True)
+        freebuf.download("http://open.freebuf.com/inland/648.html",info_only=True)
+        freebuf.download("http://open.freebuf.com/oversea/783.html",info_only=True)
+        freebuf.download("http://open.freebuf.com/original/752.html",info_only=True)
+        freebuf.download("http://www.freebuf.com/news/others/840.html",info_only=True)