[metacafe] fix info extraction(closes #8539)(closes #3253)

This commit is contained in:
Remita Amine 2016-07-06 02:19:55 +01:00
parent 001fffd004
commit 2817b99cf2
1 changed files with 60 additions and 30 deletions

View File

@ -11,13 +11,14 @@ from ..utils import (
determine_ext, determine_ext,
ExtractorError, ExtractorError,
int_or_none, int_or_none,
sanitized_Request,
urlencode_postdata, urlencode_postdata,
get_element_by_attribute,
mimetype2ext,
) )
class MetacafeIE(InfoExtractor): class MetacafeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*' _VALID_URL = r'https?://(?:www\.)?metacafe\.com/watch/(?P<video_id>[^/]+)/(?P<display_id>[^/?#]+)'
_DISCLAIMER = 'http://www.metacafe.com/family_filter/' _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
_FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user' _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
IE_NAME = 'metacafe' IE_NAME = 'metacafe'
@ -47,6 +48,7 @@ class MetacafeIE(InfoExtractor):
'uploader': 'ign', 'uploader': 'ign',
'description': 'Sony released a massive FAQ on the PlayStation Blog detailing the PS4\'s capabilities and limitations.', 'description': 'Sony released a massive FAQ on the PlayStation Blog detailing the PS4\'s capabilities and limitations.',
}, },
'skip': 'Page is temporarily unavailable.',
}, },
# AnyClip video # AnyClip video
{ {
@ -55,8 +57,8 @@ class MetacafeIE(InfoExtractor):
'id': 'an-dVVXnuY7Jh77J', 'id': 'an-dVVXnuY7Jh77J',
'ext': 'mp4', 'ext': 'mp4',
'title': 'The Andromeda Strain (1971): Stop the Bomb Part 3', 'title': 'The Andromeda Strain (1971): Stop the Bomb Part 3',
'uploader': 'anyclip', 'uploader': 'AnyClip',
'description': 'md5:38c711dd98f5bb87acf973d573442e67', 'description': 'md5:cbef0460d31e3807f6feb4e7a5952e5b',
}, },
}, },
# age-restricted video # age-restricted video
@ -110,28 +112,25 @@ class MetacafeIE(InfoExtractor):
def report_disclaimer(self): def report_disclaimer(self):
self.to_screen('Retrieving disclaimer') self.to_screen('Retrieving disclaimer')
def _real_initialize(self): def _confirm_age(self):
# Retrieve disclaimer # Retrieve disclaimer
self.report_disclaimer() self.report_disclaimer()
self._download_webpage(self._DISCLAIMER, None, False, 'Unable to retrieve disclaimer') self._download_webpage(self._DISCLAIMER, None, False, 'Unable to retrieve disclaimer')
# Confirm age # Confirm age
disclaimer_form = {
'filters': '0',
'submit': "Continue - I'm over 18",
}
request = sanitized_Request(self._FILTER_POST, urlencode_postdata(disclaimer_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
self.report_age_confirmation() self.report_age_confirmation()
self._download_webpage(request, None, False, 'Unable to confirm age') self._download_webpage(
self._FILTER_POST, None, False, 'Unable to confirm age',
data=urlencode_postdata({
'filters': '0',
'submit': "Continue - I'm over 18",
}), headers={
'Content-Type': 'application/x-www-form-urlencoded',
})
def _real_extract(self, url): def _real_extract(self, url):
# Extract id and simplified title from URL # Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url) video_id, display_id = re.match(self._VALID_URL, url).groups()
if mobj is None:
raise ExtractorError('Invalid URL: %s' % url)
video_id = mobj.group(1)
# the video may come from an external site # the video may come from an external site
m_external = re.match('^(\w{2})-(.*)$', video_id) m_external = re.match('^(\w{2})-(.*)$', video_id)
@ -144,15 +143,24 @@ class MetacafeIE(InfoExtractor):
if prefix == 'cb': if prefix == 'cb':
return self.url_result('theplatform:%s' % ext_id, 'ThePlatform') return self.url_result('theplatform:%s' % ext_id, 'ThePlatform')
# Retrieve video webpage to extract further information # self._confirm_age()
req = sanitized_Request('http://www.metacafe.com/watch/%s/' % video_id)
# AnyClip videos require the flashversion cookie so that we get the link # AnyClip videos require the flashversion cookie so that we get the link
# to the mp4 file # to the mp4 file
mobj_an = re.match(r'^an-(.*?)$', video_id) headers = {}
if mobj_an: if video_id.startswith('an-'):
req.headers['Cookie'] = 'flashVersion=0;' headers['Cookie'] = 'flashVersion=0;'
webpage = self._download_webpage(req, video_id)
# Retrieve video webpage to extract further information
webpage = self._download_webpage(url, video_id, headers=headers)
error = get_element_by_attribute(
'class', 'notfound-page-title', webpage)
if error:
raise ExtractorError(error, expected=True)
video_title = self._html_search_meta(
['og:title', 'twitter:title'], webpage, 'title', default=None) or self._search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
# Extract URL, uploader and title from webpage # Extract URL, uploader and title from webpage
self.report_extraction(video_id) self.report_extraction(video_id)
@ -216,20 +224,41 @@ class MetacafeIE(InfoExtractor):
'player_url': player_url, 'player_url': player_url,
'ext': play_path.partition(':')[0], 'ext': play_path.partition(':')[0],
}) })
if video_url is None:
flashvars = self._parse_json(self._search_regex(
r'flashvars\s*=\s*({.*});', webpage, 'flashvars',
default=None), video_id, fatal=False)
if flashvars:
video_url = []
for source in flashvars.get('sources'):
source_url = source.get('src')
if not source_url:
continue
mime_type = source.get('type')
ext = mimetype2ext(mime_type) or determine_ext(source_url)
if mime_type == 'application/x-mpegURL' or ext == 'm3u8':
video_url.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4',
'm3u8_native', m3u8_id='hls', fatal=False))
else:
video_url.append({
'url': source_url,
'ext': ext,
})
if video_url is None: if video_url is None:
raise ExtractorError('Unsupported video type') raise ExtractorError('Unsupported video type')
video_title = self._html_search_regex( description = self._html_search_meta(
r'(?im)<title>(.*) - Video</title>', webpage, 'title') ['og:description', 'twitter:description', 'description'],
description = self._og_search_description(webpage) webpage, 'title', fatal=False)
thumbnail = self._og_search_thumbnail(webpage) thumbnail = self._html_search_meta(
['og:image', 'twitter:image'], webpage, 'title', fatal=False)
video_uploader = self._html_search_regex( video_uploader = self._html_search_regex(
r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);', r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
webpage, 'uploader nickname', fatal=False) webpage, 'uploader nickname', fatal=False)
duration = int_or_none( duration = int_or_none(
self._html_search_meta('video:duration', webpage)) self._html_search_meta('video:duration', webpage, default=None))
age_limit = ( age_limit = (
18 18
if re.search(r'(?:"contentRating":|"rating",)"restricted"', webpage) if re.search(r'(?:"contentRating":|"rating",)"restricted"', webpage)
@ -242,10 +271,11 @@ class MetacafeIE(InfoExtractor):
'url': video_url, 'url': video_url,
'ext': video_ext, 'ext': video_ext,
}] }]
self._sort_formats(formats) self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id,
'description': description, 'description': description,
'uploader': video_uploader, 'uploader': video_uploader,
'title': video_title, 'title': video_title,