Fix issue #5

[youtube-dl.git] / youtube-dl

diff --git a/youtube-dl b/youtube-dl
index bf6973480940cb5d3aaacbb571b2b8d92106b24f..2cddafcf54bb9bb2478928d9675080394cc57e0d 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -18,7 +18,7 @@ import time
 import urllib
 import urllib2
 
-std_headers = {        
+std_headers = {
        'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.5) Gecko/2008120122 Firefox/3.0.5',
        'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
        'Accept': 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5',
@@ -435,6 +435,29 @@ class YoutubeIE(InfoExtractor):
        def suitable(url):
                return (re.match(YoutubeIE._VALID_URL, url) is not None)
 
+       @staticmethod
+       def htmlentity_transform(matchobj):
+               """Transforms an HTML entity to a Unicode character."""
+               entity = matchobj.group(1)
+
+               # Known non-numeric HTML entity
+               if entity in htmlentitydefs.name2codepoint:
+                       return unichr(htmlentitydefs.name2codepoint[entity])
+
+               # Unicode character
+               mobj = re.match(ur'(?u)#(x?\d+)', entity)
+               if mobj is not None:
+                       numstr = mobj.group(1)
+                       if numstr.startswith(u'x'):
+                               base = 16
+                               numstr = u'0%s' % numstr
+                       else:
+                               base = 10
+                       return unichr(long(numstr, base))
+
+               # Unknown entity in name, return its literal representation
+               return (u'&%s;' % entity)
+
        def report_lang(self):
                """Report attempt to set language."""
                self.to_stdout(u'[youtube] Setting language')
@@ -458,7 +481,7 @@ class YoutubeIE(InfoExtractor):
        def report_video_url(self, video_id, video_real_url):
                """Report extracted video URL."""
                self.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
-
+       
        def _real_initialize(self):
                if self._downloader is None:
                        return
@@ -585,7 +608,7 @@ class YoutubeIE(InfoExtractor):
                        self.to_stderr(u'ERROR: unable to extract video title')
                        return [None]
                video_title = mobj.group(1).decode('utf-8')
-               video_title = re.sub(ur'(?u)&(.+?);', lambda x: unichr(htmlentitydefs.name2codepoint[x.group(1)]), video_title)
+               video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
                video_title = video_title.replace(os.sep, u'%')
 
                # simplified title
@@ -729,7 +752,7 @@ class YoutubeSearchIE(InfoExtractor):
        _MORE_PAGES_INDICATOR = r'>Next</a>'
        _youtube_ie = None
 
-       def __init__(self, youtube_ie, downloader=None): 
+       def __init__(self, youtube_ie, downloader=None):
                InfoExtractor.__init__(self, downloader)
                self._youtube_ie = youtube_ie
        
@@ -752,11 +775,11 @@ class YoutubeSearchIE(InfoExtractor):
 
                prefix, query = query.split(':')
                prefix = prefix[8:]
-               if prefix == '': 
+               if prefix == '':
                        return self._download_n_results(query, 1)
-               elif prefix == 'all': 
+               elif prefix == 'all':
                        return self._download_n_results(query, -1)
-               else: 
+               else:
                        try:
                                n = int(prefix)
                                if n <= 0: