from ..utils import (
compat_urllib_error,
compat_urllib_parse,
- compat_urllib_parse_urlparse,
compat_urllib_request,
+ compat_urlparse,
ExtractorError,
)
return new_url
def _real_extract(self, url):
+ parsed_url = compat_urlparse.urlparse(url)
+ if not parsed_url.scheme:
+ self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
+ return self.url_result('http://' + url)
+
try:
new_url = self._test_redirect(url)
if new_url:
raise ExtractorError(u'Invalid URL: %s' % url)
self.report_extraction(video_id)
- # Look for BrigthCove:
+ # Look for BrightCove:
m_brightcove = re.search(r'<object.+?class=([\'"]).*?BrightcoveExperience.*?\1.+?</object>', webpage, re.DOTALL)
if m_brightcove is not None:
self.to_screen(u'Brightcove video detected.')
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)
+ mobj = re.search(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
if mobj.group(1) is None:
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
- video_id = os.path.basename(video_url)
+ video_url = mobj.group(1)
+ video_url = compat_urlparse.urljoin(url, video_url)
+ video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
# here's a fun little line of code for you:
video_extension = os.path.splitext(video_id)[1][1:]