Minor documentation change

[youtube-dl.git] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index f276d9caa9e3616599cab3156cfd19212549ba70..496ae036fa7c98ed3166e0dfb16e857f4efad409 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -624,6 +624,7 @@ class MetacafeIE(InfoExtractor):
 
        _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
        _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
+       _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
        _youtube_ie = None
 
        def __init__(self, youtube_ie, downloader=None):
@@ -665,7 +666,7 @@ class MetacafeIE(InfoExtractor):
                        'filters': '0',
                        'submit': "Continue - I'm over 18",
                        }
-               request = urllib2.Request('http://www.metacafe.com/', urllib.urlencode(disclaimer_form), std_headers)
+               request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers)
                try:
                        self.report_age_confirmation()
                        disclaimer = urllib2.urlopen(request).read()
@@ -702,13 +703,13 @@ class MetacafeIE(InfoExtractor):
 
                # Extract URL, uploader and title from webpage
                self.report_extraction(video_id)
-               mobj = re.search(r'(?m)"mediaURL":"(http.*?\.flv)"', webpage)
+               mobj = re.search(r'(?m)&mediaURL=(http.*?\.flv)', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract media URL')
                        return
-               mediaURL = mobj.group(1).replace('\\', '')
+               mediaURL = urllib.unquote(mobj.group(1))
 
-               mobj = re.search(r'(?m)"gdaKey":"(.*?)"', webpage)
+               mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract gdaKey')
                        return
@@ -722,11 +723,11 @@ class MetacafeIE(InfoExtractor):
                        return
                video_title = mobj.group(1).decode('utf-8')
 
-               mobj = re.search(r'(?m)<li id="ChnlUsr">.*?Submitter:<br />(.*?)</li>', webpage)
+               mobj = re.search(r'(?ms)<li id="ChnlUsr">.*?Submitter:.*?<a .*?>(.*?)<', webpage)
                if mobj is None:
                        self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
                        return
-               video_uploader = re.sub(r'<.*?>', '', mobj.group(1))
+               video_uploader = mobj.group(1)
 
                # Process video information
                self._downloader.process_info({
@@ -918,7 +919,7 @@ class PostProcessor(object):
                """Run the PostProcessor.
 
                The "information" argument is a dictionary like the ones
-               returned by InfoExtractors. The only difference is that this
+               composed by InfoExtractors. The only difference is that this
                one has an extra field called "filepath" that points to the
                downloaded file.
 
@@ -996,7 +997,9 @@ if __name__ == '__main__':
                batchurls = []
                if opts.batchfile is not None:
                        try:
-                               batchurls = [line.strip() for line in open(opts.batchfile, 'r')]
+                               batchurls = open(opts.batchfile, 'r').readlines()
+                               batchurls = [x.strip() for x in batchurls]
+                               batchurls = [x for x in batchurls if len(x) > 0]
                        except IOError:
                                sys.exit(u'ERROR: batch file could not be read')
                all_urls = batchurls + args