from .common import InfoExtractor
from .youtube import YoutubeIE
from ..utils import (
- compat_urllib_error,
compat_urllib_parse,
- compat_urllib_request,
compat_urlparse,
compat_xml_parse_error,
+ determine_ext,
ExtractorError,
float_or_none,
HEADRequest,
'uploader': 'www.handjobhub.com',
'title': 'Busty Blonde Siri Tit Fuck While Wank at Handjob Hub',
}
- }
+ },
+ # RSS feed
+ {
+ 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
+ 'info_dict': {
+ 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
+ 'title': 'Zero Punctuation',
+ 'description': 're:'
+ },
+ 'playlist_mincount': 11,
+ },
+ # Multiple brightcove videos
+ # https://github.com/rg3/youtube-dl/issues/2283
+ {
+ 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
+ 'info_dict': {
+ 'id': 'always-never',
+ 'title': 'Always / Never - The New Yorker',
+ },
+ 'playlist_count': 3,
+ 'params': {
+ 'extract_flat': False,
+ 'skip_download': True,
+ }
+ },
+ # MLB embed
+ {
+ 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
+ 'md5': '96f09a37e44da40dd083e12d9a683327',
+ 'info_dict': {
+ 'id': '33322633',
+ 'ext': 'mp4',
+ 'title': 'Ump changes call to ball',
+ 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
+ 'duration': 48,
+ 'timestamp': 1401537900,
+ 'upload_date': '20140531',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ },
+ },
]
def report_download_webpage(self, video_id):
"""Report information extraction."""
self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
- def _send_head(self, url):
- """Check if it is a redirect, like url shorteners, in case return the new url."""
-
- class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
- """
- Subclass the HTTPRedirectHandler to make it use our
- HEADRequest also on the redirected URL
- """
- def redirect_request(self, req, fp, code, msg, headers, newurl):
- if code in (301, 302, 303, 307):
- newurl = newurl.replace(' ', '%20')
- newheaders = dict((k,v) for k,v in req.headers.items()
- if k.lower() not in ("content-length", "content-type"))
- try:
- # This function was deprecated in python 3.3 and removed in 3.4
- origin_req_host = req.get_origin_req_host()
- except AttributeError:
- origin_req_host = req.origin_req_host
- return HEADRequest(newurl,
- headers=newheaders,
- origin_req_host=origin_req_host,
- unverifiable=True)
- else:
- raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)
-
- class HTTPMethodFallback(compat_urllib_request.BaseHandler):
- """
- Fallback to GET if HEAD is not allowed (405 HTTP error)
- """
- def http_error_405(self, req, fp, code, msg, headers):
- fp.read()
- fp.close()
-
- newheaders = dict((k,v) for k,v in req.headers.items()
- if k.lower() not in ("content-length", "content-type"))
- return self.parent.open(compat_urllib_request.Request(req.get_full_url(),
- headers=newheaders,
- origin_req_host=req.get_origin_req_host(),
- unverifiable=True))
-
- # Build our opener
- opener = compat_urllib_request.OpenerDirector()
- for handler in [compat_urllib_request.HTTPHandler, compat_urllib_request.HTTPDefaultErrorHandler,
- HTTPMethodFallback, HEADRedirectHandler,
- compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]:
- opener.add_handler(handler())
-
- response = opener.open(HEADRequest(url))
- if response is None:
- raise ExtractorError('Invalid URL protocol')
- return response
-
def _extract_rss(self, url, video_id, doc):
playlist_title = doc.find('./channel/title').text
playlist_desc_el = doc.find('./channel/description')
self.to_screen('%s: Requesting header' % video_id)
- try:
- response = self._send_head(url)
+ head_req = HEADRequest(url)
+ response = self._request_webpage(
+ head_req, video_id,
+ note=False, errnote='Could not send HEAD request to %s' % url,
+ fatal=False)
+ if response is not False:
# Check for redirect
new_url = response.geturl()
if url != new_url:
'upload_date': upload_date,
}
- except compat_urllib_error.HTTPError:
- # This may be a stupid server that doesn't like HEAD, our UA, or so
- pass
-
try:
webpage = self._download_webpage(url, video_id)
except ValueError:
embedSWF\(?:\s*
)
(["\'])
- (?P<url>(?:https?:)?//(?:www\.)?youtube\.com/
+ (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
(?:embed|v)/.+?)
\1''', webpage)
if matches:
if mobj is not None:
return self.url_result(mobj.group('url'), 'SBS')
+ mobj = re.search(
+ r'<iframe[^>]+?src=(["\'])(?P<url>https?://m\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
+ webpage)
+ if mobj is not None:
+ return self.url_result(mobj.group('url'), 'MLB')
+
# Start with something easy: JW Player in SWFObject
found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
if not found:
\s*{[^}]+? ["']?clip["']?\s*:\s*\{\s*
["']?url["']?\s*:\s*["']([^"']+)["']
''', webpage)
- assert found
if not found:
# Try to find twitter cards info
found = re.findall(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
if m_video_type is not None:
def check_video(vurl):
vpath = compat_urlparse.urlparse(vurl).path
- return '.' in vpath and not vpath.endswith('.swf')
+ vext = determine_ext(vpath)
+ return '.' in vpath and vext not in ('swf', 'png', 'jpg')
found = list(filter(
check_video,
re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)))
if not found:
# HTML5 video
- found = re.findall(r'(?s)<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage)
+ found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]+)? src="([^"]+)"', webpage)
if not found:
found = re.search(
r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'