diff options
Diffstat (limited to 'youtube_dl/extractor/common.py')
| -rw-r--r-- | youtube_dl/extractor/common.py | 13 | 
1 files changed, 10 insertions, 3 deletions
| diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index da50abfc1..12169b2bb 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -47,7 +47,8 @@ class InfoExtractor(object):      uploader_id:    Nickname or id of the video uploader.      location:       Physical location of the video.      player_url:     SWF Player URL (used for rtmpdump). -    subtitles:      The subtitle file contents. +    subtitles:      The subtitle file contents as a dictionary in the format +                    {language: subtitles}.      view_count:     How many users have watched the video on the platform.      urlhandle:      [internal] The urlHandle to be used to download the file,                      like returned by urllib.request.urlopen @@ -77,7 +78,13 @@ class InfoExtractor(object):      @classmethod      def suitable(cls, url):          """Receives a URL and returns True if suitable for this IE.""" -        return re.match(cls._VALID_URL, url) is not None + +        # This does not use has/getattr intentionally - we want to know whether +        # we have cached the regexp for *this* class, whereas getattr would also +        # match the superclass +        if '_VALID_URL_RE' not in cls.__dict__: +            cls._VALID_URL_RE = re.compile(cls._VALID_URL) +        return cls._VALID_URL_RE.match(url) is not None      @classmethod      def working(cls): @@ -122,7 +129,7 @@ class InfoExtractor(object):          except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:              if errnote is None:                  errnote = u'Unable to download webpage' -            raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2]) +            raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2], cause=err)      def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):          """ Returns a tuple (page content as string, URL handle) """ | 
