diff options
author | Sergey M․ <dstftw@gmail.com> | 2015-01-26 00:32:31 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2015-01-26 00:32:31 +0600 |
commit | 96a53167fa64293506f446d0c2bf3e0db6c8df31 (patch) | |
tree | 150087a52ff45113ffe658a4f130c9c0418b796d /youtube_dl/extractor/common.py | |
parent | 6d2749aac407df1e039f5b61a294991c1e810cff (diff) |
[common] Generalize URLs' HTTP errors pre-testing
Diffstat (limited to 'youtube_dl/extractor/common.py')
-rw-r--r-- | youtube_dl/extractor/common.py | 23 |
1 files changed, 23 insertions, 0 deletions
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 388c55e99..478232682 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -14,6 +14,7 @@ import xml.etree.ElementTree from ..compat import ( compat_cookiejar, + compat_HTTPError, compat_http_client, compat_urllib_error, compat_urllib_parse_urlparse, @@ -26,6 +27,7 @@ from ..utils import ( compiled_regex_type, ExtractorError, float_or_none, + HEADRequest, int_or_none, RegexNotFoundError, sanitize_filename, @@ -716,6 +718,27 @@ class InfoExtractor(object): ) formats.sort(key=_formats_key) + def _check_formats(self, formats, video_id): + if formats: + formats[:] = filter( + lambda f: self._is_valid_url( + f['url'], video_id, + item='%s video format' % f.get('format_id') if f.get('format_id') else 'video'), + formats) + + def _is_valid_url(self, url, video_id, item='video'): + try: + self._request_webpage( + HEADRequest(url), video_id, + 'Checking %s URL' % item) + return True + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError): + self.report_warning( + '%s URL is invalid, skipping' % item, video_id) + return False + raise + def http_scheme(self): """ Either "http:" or "https:", depending on the user's preferences """ return ( |