diff options
author | Philipp Hagemeister <[email protected]> | 2014-08-24 06:58:11 +0200 |
---|---|---|
committer | Philipp Hagemeister <[email protected]> | 2014-08-24 06:58:11 +0200 |
commit | ebab4520ff85cb5ccd5a3a6ee8c4bec213adda43 (patch) | |
tree | f834399af60785844e0693503a1725ea3ca64281 | |
parent | a71d1414eb531a84dd19cd8ce5b68b3e947fe48f (diff) | |
download | youtube-dl-ebab4520ff85cb5ccd5a3a6ee8c4bec213adda43.tar.gz youtube-dl-ebab4520ff85cb5ccd5a3a6ee8c4bec213adda43.zip |
[generic] Use default opener for HEAD request (Fixes #3528)
-rw-r--r-- | youtube_dl/extractor/generic.py | 64 |
1 files changed, 6 insertions, 58 deletions
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 5a6fe65bc..8b11f7f7a 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -356,58 +356,6 @@ class GenericIE(InfoExtractor): """Report information extraction.""" 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): playlist_title = doc.find('./channel/title').text playlist_desc_el = doc.find('./channel/description') @@ -511,9 +459,13 @@ class GenericIE(InfoExtractor): self.to_screen('%s: Requesting header' % video_id) - try: - response = self._send_head(url) + head_req = HEADRequest(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 new_url = response.geturl() if url != new_url: @@ -541,10 +493,6 @@ class GenericIE(InfoExtractor): '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: webpage = self._download_webpage(url, video_id) except ValueError: |