diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2014-10-26 17:05:44 +0100 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2014-10-26 17:05:44 +0100 |
commit | 23be51d8ce132dbb967f460e1225fdaaa43dff39 (patch) | |
tree | 1a4e5404654e8f63d80bb662836ab05bb80cb340 /youtube_dl/extractor/common.py | |
parent | 488447455d3d90e1d83a7ebc2f9ce552e031e0d8 (diff) |
[generic] Handle audio streams that do not implement HEAD (Fixes #4032)
Diffstat (limited to 'youtube_dl/extractor/common.py')
-rw-r--r-- | youtube_dl/extractor/common.py | 7 |
1 files changed, 5 insertions, 2 deletions
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index cf3781cd6..e1bd6bb49 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -242,7 +242,6 @@ class InfoExtractor(object): def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True): """ Returns a tuple (page content as string, URL handle) """ - # Strip hashes from the URL (#1038) if isinstance(url_or_request, (compat_str, str)): url_or_request = url_or_request.partition('#')[0] @@ -251,6 +250,10 @@ class InfoExtractor(object): if urlh is False: assert not fatal return False + content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal) + return (content, urlh) + + def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True): content_type = urlh.headers.get('Content-Type', '') webpage_bytes = urlh.read() m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type) @@ -309,7 +312,7 @@ class InfoExtractor(object): msg += ' Visit %s for more details' % blocked_iframe raise ExtractorError(msg, expected=True) - return (content, urlh) + return content def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): """ Returns the data of the page as a string """ |