Merge pull request #522 from art-zhitnik/master

--(match|reject)-title utf8 fix

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 9df521d0233d806a83e3f5abf648f2e3a22b690f..cfaef29045d95d45fbf7a8baf0b70874e881d0d7 100644 (file)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -603,7 +603,7 @@ class MetacafeIE(InfoExtractor):
                        return
                video_title = mobj.group(1).decode('utf-8')
 
-               mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage)
+               mobj = re.search(r'submitter=(.*?);', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
                        return
@@ -694,7 +694,12 @@ class DailymotionIE(InfoExtractor):
                video_uploader = u'NA'
                mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage)
                if mobj is None:
-                       self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
+                       # lookin for official user
+                       mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage)
+                       if mobj_official is None:
+                               self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
+                       else:
+                               video_uploader = mobj_official.group(1)
                else:
                        video_uploader = mobj.group(1)
 

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index a64937b4c12077fef92c95d0ddd36e30de0e8917..56d0461456fe7e96a259100d7e60bdf2f1dc87a2 100644 (file)
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -83,7 +83,7 @@ class IDParser(HTMLParser.HTMLParser):
                HTMLParser.HTMLParser.__init__(self)
 
        def error(self, message):
-               print >> sys.stderr, self.getpos()
+               #print >> sys.stderr, self.getpos()
                if self.error_count > 10 or self.started:
                        raise HTMLParser.HTMLParseError(message, self.getpos())
                self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line