diff options
Diffstat (limited to 'youtube_dl/extractor/generic.py')
| -rw-r--r-- | youtube_dl/extractor/generic.py | 20 |
1 files changed, 17 insertions, 3 deletions
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index b633e896c..8488dca05 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -7,12 +7,14 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_error, compat_urllib_parse, + compat_urllib_parse_urlparse, compat_urllib_request, ExtractorError, ) from .brightcove import BrightcoveIE + class GenericIE(InfoExtractor): IE_DESC = u'Generic downloader that works on some sites' _VALID_URL = r'.*' @@ -23,7 +25,7 @@ class GenericIE(InfoExtractor): u'file': u'13601338388002.mp4', u'md5': u'85b90ccc9d73b4acd9138d3af4c27f89', u'info_dict': { - u"uploader": u"www.hodiho.fr", + u"uploader": u"www.hodiho.fr", u"title": u"R\u00e9gis plante sa Jeep" } }, @@ -107,8 +109,13 @@ class GenericIE(InfoExtractor): return new_url def _real_extract(self, url): - new_url = self._test_redirect(url) - if new_url: return [self.url_result(new_url)] + try: + new_url = self._test_redirect(url) + if new_url: + return [self.url_result(new_url)] + except compat_urllib_error.HTTPError: + # This may be a stupid server that doesn't like HEAD, our UA, or so + pass video_id = url.split('/')[-1] try: @@ -145,6 +152,9 @@ class GenericIE(InfoExtractor): if m_video_type is not None: mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage) if mobj is None: + # HTML5 video + mobj = re.search(r'<video[^<]*>.*?<source .*?src="([^"]+)"', webpage, flags=re.DOTALL) + if mobj is None: raise ExtractorError(u'Invalid URL: %s' % url) # It's possible that one of the regexes @@ -153,6 +163,10 @@ class GenericIE(InfoExtractor): raise ExtractorError(u'Invalid URL: %s' % url) video_url = compat_urllib_parse.unquote(mobj.group(1)) + if video_url.startswith('//'): + video_url = compat_urllib_parse_urlparse(url).scheme + ':' + video_url + if '://' not in video_url: + video_url = url + ('' if url.endswith('/') else '/') + video_url video_id = os.path.basename(video_url) # here's a fun little line of code for you: |