diff options
| -rwxr-xr-x | youtube-dl | 27 |
1 files changed, 25 insertions, 2 deletions
diff --git a/youtube-dl b/youtube-dl index ba760da47..2cddafcf5 100755 --- a/youtube-dl +++ b/youtube-dl @@ -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 |