[generic] Use default opener for HEAD request (Fixes #3528)

This commit is contained in:
Philipp Hagemeister 2014-08-24 06:58:11 +02:00
parent a71d1414eb
commit ebab4520ff
1 changed files with 6 additions and 58 deletions

View File

@ -356,58 +356,6 @@ class GenericIE(InfoExtractor):
"""Report information extraction.""" """Report information extraction."""
self._downloader.to_screen('[redirect] Following redirect to %s' % new_url) self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
def _send_head(self, url):
"""Check if it is a redirect, like url shorteners, in case return the new url."""
class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
"""
Subclass the HTTPRedirectHandler to make it use our
HEADRequest also on the redirected URL
"""
def redirect_request(self, req, fp, code, msg, headers, newurl):
if code in (301, 302, 303, 307):
newurl = newurl.replace(' ', '%20')
newheaders = dict((k,v) for k,v in req.headers.items()
if k.lower() not in ("content-length", "content-type"))
try:
# This function was deprecated in python 3.3 and removed in 3.4
origin_req_host = req.get_origin_req_host()
except AttributeError:
origin_req_host = req.origin_req_host
return HEADRequest(newurl,
headers=newheaders,
origin_req_host=origin_req_host,
unverifiable=True)
else:
raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)
class HTTPMethodFallback(compat_urllib_request.BaseHandler):
"""
Fallback to GET if HEAD is not allowed (405 HTTP error)
"""
def http_error_405(self, req, fp, code, msg, headers):
fp.read()
fp.close()
newheaders = dict((k,v) for k,v in req.headers.items()
if k.lower() not in ("content-length", "content-type"))
return self.parent.open(compat_urllib_request.Request(req.get_full_url(),
headers=newheaders,
origin_req_host=req.get_origin_req_host(),
unverifiable=True))
# Build our opener
opener = compat_urllib_request.OpenerDirector()
for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler,
HTTPMethodFallback, HEADRedirectHandler,
compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
opener.add_handler(handler())
response = opener.open(HEADRequest(url))
if response is None:
raise ExtractorError('Invalid URL protocol')
return response
def _extract_rss(self, url, video_id, doc): def _extract_rss(self, url, video_id, doc):
playlist_title = doc.find('./channel/title').text playlist_title = doc.find('./channel/title').text
playlist_desc_el = doc.find('./channel/description') playlist_desc_el = doc.find('./channel/description')
@ -511,9 +459,13 @@ class GenericIE(InfoExtractor):
self.to_screen('%s: Requesting header' % video_id) self.to_screen('%s: Requesting header' % video_id)
try: head_req = HEADRequest(url)
response = self._send_head(url) response = self._request_webpage(
head_req, video_id,
note=False, errnote='Could not send HEAD request to %s' % url,
fatal=False)
if response is not False:
# Check for redirect # Check for redirect
new_url = response.geturl() new_url = response.geturl()
if url != new_url: if url != new_url:
@ -541,10 +493,6 @@ class GenericIE(InfoExtractor):
'upload_date': upload_date, 'upload_date': upload_date,
} }
except compat_urllib_error.HTTPError:
# This may be a stupid server that doesn't like HEAD, our UA, or so
pass
try: try:
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
except ValueError: except ValueError: