etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-29 03:23:02 +00:00
Code Issues Projects Releases Wiki Activity

Fix EscapistMagazine IE

Browse source
This commit is contained in:
Philipp Hagemeister 2012-07-18 21:17:51 +02:00
parent cca4828ac9
commit 3210735c49
1 changed files with 4 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
youtube_dl/InfoExtractors.py
View file

@ -2193,12 +2193,14 @@ def _real_extract(self, url):
self.report_extraction(showName) self.report_extraction(showName)
try: try:
webPageBytes = urllib2.urlopen(url).read() webPage = urllib2.urlopen(url)
webPageBytes = webPage.read()
m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type'])
webPage = webPageBytes.decode(m.group(1) if m else 'utf-8')
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err)) self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err))
return return
webPage = webPageBytes.decode('utf-8')
descMatch = re.search('<meta name="description" content="([^"]*)"', webPage) descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
description = unescapeHTML(descMatch.group(1)) description = unescapeHTML(descMatch.group(1))
imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage) imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)