diff options
| author | Philipp Hagemeister <phihag@phihag.de> | 2012-07-18 21:17:51 +0200 |
|---|---|---|
| committer | Philipp Hagemeister <phihag@phihag.de> | 2012-07-18 21:17:51 +0200 |
| commit | 3210735c499e6a7d0b4df4b8120e17bd7ba8927b (patch) | |
| tree | 248d6aeb3f56753452472c43255be42d9b17b0a6 | |
| parent | cca4828ac94e6d2e4e1918405d0fcbc8e6ac92d0 (diff) | |
Fix EscapistMagazine IE
| -rw-r--r-- | youtube_dl/InfoExtractors.py | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index baf859ea8..499d9b1ae 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -2193,12 +2193,14 @@ class EscapistIE(InfoExtractor): self.report_extraction(showName) 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: self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err)) return - webPage = webPageBytes.decode('utf-8') descMatch = re.search('<meta name="description" content="([^"]*)"', webPage) description = unescapeHTML(descMatch.group(1)) imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage) |