mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-21 20:46:36 -05:00
[metacafe] Modernize
This commit is contained in:
Sergey M․
parent
0320ddc192
commit
be3b8fa30f
1 changed files with 80 additions and 79 deletions
|
|
@ -1,3 +1,5 @@
|
|||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
|
@ -9,104 +11,104 @@
|
|||
ExtractorError,
|
||||
)
|
||||
|
||||
class MetacafeIE(InfoExtractor):
|
||||
"""Information Extractor for metacafe.com."""
|
||||
|
||||
class MetacafeIE(InfoExtractor):
|
||||
_VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
|
||||
_DISCLAIMER = 'http://www.metacafe.com/family_filter/'
|
||||
_FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
|
||||
IE_NAME = u'metacafe'
|
||||
IE_NAME = 'metacafe'
|
||||
_TESTS = [
|
||||
# Youtube video
|
||||
{
|
||||
u"add_ie": ["Youtube"],
|
||||
u"url": u"http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
|
||||
u"file": u"_aUehQsCQtM.mp4",
|
||||
u"info_dict": {
|
||||
u"upload_date": u"20090102",
|
||||
u"title": u"The Electric Company | \"Short I\" | PBS KIDS GO!",
|
||||
u"description": u"md5:2439a8ef6d5a70e380c22f5ad323e5a8",
|
||||
u"uploader": u"PBS",
|
||||
u"uploader_id": u"PBS"
|
||||
}
|
||||
},
|
||||
# Normal metacafe video
|
||||
{
|
||||
u'url': u'http://www.metacafe.com/watch/11121940/news_stuff_you_wont_do_with_your_playstation_4/',
|
||||
u'md5': u'6e0bca200eaad2552e6915ed6fd4d9ad',
|
||||
u'info_dict': {
|
||||
u'id': u'11121940',
|
||||
u'ext': u'mp4',
|
||||
u'title': u'News: Stuff You Won\'t Do with Your PlayStation 4',
|
||||
u'uploader': u'ign',
|
||||
u'description': u'Sony released a massive FAQ on the PlayStation Blog detailing the PS4\'s capabilities and limitations.',
|
||||
# Youtube video
|
||||
{
|
||||
'add_ie': ['Youtube'],
|
||||
'url': 'http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/',
|
||||
'info_dict': {
|
||||
'id': '_aUehQsCQtM',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20090102',
|
||||
'title': 'The Electric Company | \"Short I\" | PBS KIDS GO!',
|
||||
'description': 'md5:2439a8ef6d5a70e380c22f5ad323e5a8',
|
||||
'uploader': 'PBS',
|
||||
'uploader_id': 'PBS'
|
||||
}
|
||||
},
|
||||
},
|
||||
# AnyClip video
|
||||
{
|
||||
u"url": u"http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/",
|
||||
u"file": u"an-dVVXnuY7Jh77J.mp4",
|
||||
u"info_dict": {
|
||||
u"title": u"The Andromeda Strain (1971): Stop the Bomb Part 3",
|
||||
u"uploader": u"anyclip",
|
||||
u"description": u"md5:38c711dd98f5bb87acf973d573442e67",
|
||||
# Normal metacafe video
|
||||
{
|
||||
'url': 'http://www.metacafe.com/watch/11121940/news_stuff_you_wont_do_with_your_playstation_4/',
|
||||
'md5': '6e0bca200eaad2552e6915ed6fd4d9ad',
|
||||
'info_dict': {
|
||||
'id': '11121940',
|
||||
'ext': 'mp4',
|
||||
'title': 'News: Stuff You Won\'t Do with Your PlayStation 4',
|
||||
'uploader': 'ign',
|
||||
'description': 'Sony released a massive FAQ on the PlayStation Blog detailing the PS4\'s capabilities and limitations.',
|
||||
},
|
||||
},
|
||||
},
|
||||
# age-restricted video
|
||||
{
|
||||
u'url': u'http://www.metacafe.com/watch/5186653/bbc_internal_christmas_tape_79_uncensored_outtakes_etc/',
|
||||
u'md5': u'98dde7c1a35d02178e8ab7560fe8bd09',
|
||||
u'info_dict': {
|
||||
u'id': u'5186653',
|
||||
u'ext': u'mp4',
|
||||
u'title': u'BBC INTERNAL Christmas Tape \'79 - UNCENSORED Outtakes, Etc.',
|
||||
u'uploader': u'Dwayne Pipe',
|
||||
u'description': u'md5:950bf4c581e2c059911fa3ffbe377e4b',
|
||||
u'age_limit': 18,
|
||||
# AnyClip video
|
||||
{
|
||||
'url': 'http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/',
|
||||
'info_dict': {
|
||||
'id': 'an-dVVXnuY7Jh77J',
|
||||
'ext': 'mp4',
|
||||
'title': 'The Andromeda Strain (1971): Stop the Bomb Part 3',
|
||||
'uploader': 'anyclip',
|
||||
'description': 'md5:38c711dd98f5bb87acf973d573442e67',
|
||||
},
|
||||
},
|
||||
},
|
||||
# cbs video
|
||||
{
|
||||
u'url': u'http://www.metacafe.com/watch/cb-0rOxMBabDXN6/samsung_galaxy_note_2_samsungs_next_generation_phablet/',
|
||||
u'info_dict': {
|
||||
u'id': u'0rOxMBabDXN6',
|
||||
u'ext': u'flv',
|
||||
u'title': u'Samsung Galaxy Note 2: Samsung\'s next-generation phablet',
|
||||
u'description': u'md5:54d49fac53d26d5a0aaeccd061ada09d',
|
||||
u'duration': 129,
|
||||
# age-restricted video
|
||||
{
|
||||
'url': 'http://www.metacafe.com/watch/5186653/bbc_internal_christmas_tape_79_uncensored_outtakes_etc/',
|
||||
'md5': '98dde7c1a35d02178e8ab7560fe8bd09',
|
||||
'info_dict': {
|
||||
'id': '5186653',
|
||||
'ext': 'mp4',
|
||||
'title': 'BBC INTERNAL Christmas Tape \'79 - UNCENSORED Outtakes, Etc.',
|
||||
'uploader': 'Dwayne Pipe',
|
||||
'description': 'md5:950bf4c581e2c059911fa3ffbe377e4b',
|
||||
'age_limit': 18,
|
||||
},
|
||||
},
|
||||
u'params': {
|
||||
# rtmp download
|
||||
u'skip_download': True,
|
||||
# cbs video
|
||||
{
|
||||
'url': 'http://www.metacafe.com/watch/cb-0rOxMBabDXN6/samsung_galaxy_note_2_samsungs_next_generation_phablet/',
|
||||
'info_dict': {
|
||||
'id': '0rOxMBabDXN6',
|
||||
'ext': 'flv',
|
||||
'title': 'Samsung Galaxy Note 2: Samsung\'s next-generation phablet',
|
||||
'description': 'md5:54d49fac53d26d5a0aaeccd061ada09d',
|
||||
'duration': 129,
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
def report_disclaimer(self):
|
||||
"""Report disclaimer retrieval."""
|
||||
self.to_screen(u'Retrieving disclaimer')
|
||||
self.to_screen('Retrieving disclaimer')
|
||||
|
||||
def _real_initialize(self):
|
||||
# Retrieve disclaimer
|
||||
self.report_disclaimer()
|
||||
self._download_webpage(self._DISCLAIMER, None, False, u'Unable to retrieve disclaimer')
|
||||
self._download_webpage(self._DISCLAIMER, None, False, 'Unable to retrieve disclaimer')
|
||||
|
||||
# Confirm age
|
||||
disclaimer_form = {
|
||||
'filters': '0',
|
||||
'submit': "Continue - I'm over 18",
|
||||
}
|
||||
}
|
||||
request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
|
||||
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
|
||||
self.report_age_confirmation()
|
||||
self._download_webpage(request, None, False, u'Unable to confirm age')
|
||||
self._download_webpage(request, None, False, 'Unable to confirm age')
|
||||
|
||||
def _real_extract(self, url):
|
||||
# Extract id and simplified title from URL
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
if mobj is None:
|
||||
raise ExtractorError(u'Invalid URL: %s' % url)
|
||||
raise ExtractorError('Invalid URL: %s' % url)
|
||||
|
||||
video_id = mobj.group(1)
|
||||
|
||||
|
|
@ -153,23 +155,24 @@ def _real_extract(self, url):
|
|||
else:
|
||||
mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
|
||||
if mobj is None:
|
||||
raise ExtractorError(u'Unable to extract media URL')
|
||||
raise ExtractorError('Unable to extract media URL')
|
||||
vardict = compat_parse_qs(mobj.group(1))
|
||||
if 'mediaData' not in vardict:
|
||||
raise ExtractorError(u'Unable to extract media URL')
|
||||
mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
|
||||
raise ExtractorError('Unable to extract media URL')
|
||||
mobj = re.search(
|
||||
r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
|
||||
if mobj is None:
|
||||
raise ExtractorError(u'Unable to extract media URL')
|
||||
raise ExtractorError('Unable to extract media URL')
|
||||
mediaURL = mobj.group('mediaURL').replace('\\/', '/')
|
||||
video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
|
||||
video_ext = determine_ext(video_url)
|
||||
|
||||
video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, u'title')
|
||||
video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, 'title')
|
||||
description = self._og_search_description(webpage)
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
video_uploader = self._html_search_regex(
|
||||
r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
|
||||
webpage, u'uploader nickname', fatal=False)
|
||||
webpage, 'uploader nickname', fatal=False)
|
||||
|
||||
if re.search(r'"contentRating":"restricted"', webpage) is not None:
|
||||
age_limit = 18
|
||||
|
|
@ -177,14 +180,12 @@ def _real_extract(self, url):
|
|||
age_limit = 0
|
||||
|
||||
return {
|
||||
'_type': 'video',
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'description': description,
|
||||
'uploader': video_uploader,
|
||||
'upload_date': None,
|
||||
'title': video_title,
|
||||
'title': video_title,
|
||||
'thumbnail':thumbnail,
|
||||
'ext': video_ext,
|
||||
'ext': video_ext,
|
||||
'age_limit': age_limit,
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in a new issue