mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 18:41:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

[metacafe] Modernize

Browse source
This commit is contained in:
Sergey M․ 2014-03-23 05:05:31 +07:00
parent 0320ddc192
commit be3b8fa30f
1 changed files with 80 additions and 79 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

159
youtube_dl/extractor/metacafe.py
View file

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