Merge remote-tracking branch 'origin/master'

This commit is contained in:
Philipp Hagemeister 2013-10-28 10:44:13 +01:00
commit ebc14f251c
16 changed files with 409 additions and 89 deletions

39
devscripts/check-porn.py Normal file
View file

@ -0,0 +1,39 @@
#!/usr/bin/env python
"""
This script employs a VERY basic heuristic ('porn' in webpage.lower()) to check
if we are not 'age_limit' tagging some porn site
"""
# Allow direct execution
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import get_testcases
from youtube_dl.utils import compat_urllib_request
for test in get_testcases():
try:
webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read()
except:
print('\nFail: {0}'.format(test['name']))
continue
webpage = webpage.decode('utf8', 'replace')
if 'porn' in webpage.lower() and ('info_dict' not in test
or 'age_limit' not in test['info_dict']
or test['info_dict']['age_limit'] != 18):
print('\nPotential missing age_limit check: {0}'.format(test['name']))
elif 'porn' not in webpage.lower() and ('info_dict' in test and
'age_limit' in test['info_dict'] and
test['info_dict']['age_limit'] == 18):
print('\nPotential false negative: {0}'.format(test['name']))
else:
sys.stdout.write('.')
sys.stdout.flush()
print()

View file

@ -8,6 +8,7 @@
try: try:
from setuptools import setup from setuptools import setup
setuptools_available = True
except ImportError: except ImportError:
from distutils.core import setup from distutils.core import setup
@ -43,13 +44,16 @@
params = py2exe_params params = py2exe_params
else: else:
params = { params = {
'scripts': ['bin/youtube-dl'],
'data_files': [ # Installing system-wide would require sudo... 'data_files': [ # Installing system-wide would require sudo...
('etc/bash_completion.d', ['youtube-dl.bash-completion']), ('etc/bash_completion.d', ['youtube-dl.bash-completion']),
('share/doc/youtube_dl', ['README.txt']), ('share/doc/youtube_dl', ['README.txt']),
('share/man/man1/', ['youtube-dl.1']) ('share/man/man1/', ['youtube-dl.1'])
] ]
} }
if setuptools_available:
params['entry_points'] = {'console_scripts': ['youtube-dl = youtube_dl:main']}
else:
params['scripts'] = ['bin/youtube-dl']
# Get the version from youtube_dl/version.py without importing the package # Get the version from youtube_dl/version.py without importing the package
exec(compile(open('youtube_dl/version.py').read(), exec(compile(open('youtube_dl/version.py').read(),

View file

@ -462,7 +462,7 @@ def process_video_result(self, info_dict, download=True):
info_dict['playlist_index'] = None info_dict['playlist_index'] = None
# This extractors handle format selection themselves # This extractors handle format selection themselves
if info_dict['extractor'] in [u'youtube', u'Youku', u'YouPorn', u'mixcloud']: if info_dict['extractor'] in [u'youtube', u'Youku', u'mixcloud']:
if download: if download:
self.process_info(info_dict) self.process_info(info_dict)
return info_dict return info_dict

View file

@ -72,6 +72,7 @@
from .jukebox import JukeboxIE from .jukebox import JukeboxIE
from .justintv import JustinTVIE from .justintv import JustinTVIE
from .kankan import KankanIE from .kankan import KankanIE
from .keezmovies import KeezMoviesIE
from .kickstarter import KickStarterIE from .kickstarter import KickStarterIE
from .keek import KeekIE from .keek import KeekIE
from .liveleak import LiveLeakIE from .liveleak import LiveLeakIE
@ -94,6 +95,7 @@
from .orf import ORFIE from .orf import ORFIE
from .pbs import PBSIE from .pbs import PBSIE
from .photobucket import PhotobucketIE from .photobucket import PhotobucketIE
from .pornhub import PornHubIE
from .pornotube import PornotubeIE from .pornotube import PornotubeIE
from .rbmaradio import RBMARadioIE from .rbmaradio import RBMARadioIE
from .redtube import RedTubeIE from .redtube import RedTubeIE
@ -109,6 +111,7 @@
from .sohu import SohuIE from .sohu import SohuIE
from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE
from .southparkstudios import SouthParkStudiosIE from .southparkstudios import SouthParkStudiosIE
from .spankwire import SpankwireIE
from .spiegel import SpiegelIE from .spiegel import SpiegelIE
from .stanfordoc import StanfordOpenClassroomIE from .stanfordoc import StanfordOpenClassroomIE
from .statigram import StatigramIE from .statigram import StatigramIE
@ -121,6 +124,7 @@
from .thisav import ThisAVIE from .thisav import ThisAVIE
from .traileraddict import TrailerAddictIE from .traileraddict import TrailerAddictIE
from .trilulilu import TriluliluIE from .trilulilu import TriluliluIE
from .tube8 import Tube8IE
from .tudou import TudouIE from .tudou import TudouIE
from .tumblr import TumblrIE from .tumblr import TumblrIE
from .tutv import TutvIE from .tutv import TutvIE

View file

@ -17,8 +17,8 @@ class AddAnimeIE(InfoExtractor):
IE_NAME = u'AddAnime' IE_NAME = u'AddAnime'
_TEST = { _TEST = {
u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9', u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
u'file': u'24MR3YO5SAS9.flv', u'file': u'24MR3YO5SAS9.mp4',
u'md5': u'1036a0e0cd307b95bd8a8c3a5c8cfaf1', u'md5': u'72954ea10bc979ab5e2eb288b21425a0',
u'info_dict': { u'info_dict': {
u"description": u"One Piece 606", u"description": u"One Piece 606",
u"title": u"One Piece 606" u"title": u"One Piece 606"
@ -60,8 +60,10 @@ def _real_extract(self, url):
note=u'Confirming after redirect') note=u'Confirming after redirect')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(r"var normal_video_file = '(.*?)';", video_url = self._search_regex(r"var (?:hq|normal)_video_file = '(.*?)';",
webpage, u'video file URL') webpage, u'video file URL')
video_extension = video_url[-3:] # mp4 or flv ?
video_title = self._og_search_title(webpage) video_title = self._og_search_title(webpage)
video_description = self._og_search_description(webpage) video_description = self._og_search_description(webpage)
@ -69,7 +71,7 @@ def _real_extract(self, url):
'_type': 'video', '_type': 'video',
'id': video_id, 'id': video_id,
'url': video_url, 'url': video_url,
'ext': 'flv', 'ext': video_extension,
'title': video_title, 'title': video_title,
'description': video_description 'description': video_description
} }

View file

@ -330,10 +330,10 @@ def _og_search_description(self, html, **kargs):
def _og_search_title(self, html, **kargs): def _og_search_title(self, html, **kargs):
return self._og_search_property('title', html, **kargs) return self._og_search_property('title', html, **kargs)
def _og_search_video_url(self, html, name='video url', **kargs): def _og_search_video_url(self, html, name='video url', secure=True, **kargs):
return self._html_search_regex([self._og_regex('video:secure_url'), regexes = [self._og_regex('video')]
self._og_regex('video')], if secure: regexes.insert(0, self._og_regex('video:secure_url'))
html, name, **kargs) return self._html_search_regex(regexes, html, name, **kargs)
def _rta_search(self, html): def _rta_search(self, html):
# See http://www.rtalabel.org/index.php?content=howtofaq#single # See http://www.rtalabel.org/index.php?content=howtofaq#single

View file

@ -11,14 +11,14 @@ class ExfmIE(InfoExtractor):
_SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud.com/tracks/([^/]+)/stream' _SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud.com/tracks/([^/]+)/stream'
_TESTS = [ _TESTS = [
{ {
u'url': u'http://ex.fm/song/1bgtzg', u'url': u'http://ex.fm/song/eh359',
u'file': u'95223130.mp3', u'file': u'44216187.mp3',
u'md5': u'8a7967a3fef10e59a1d6f86240fd41cf', u'md5': u'e45513df5631e6d760970b14cc0c11e7',
u'info_dict': { u'info_dict': {
u"title": u"We Can't Stop - Miley Cyrus", u"title": u"Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive",
u"uploader": u"Miley Cyrus", u"uploader": u"deadjournalist",
u'upload_date': u'20130603', u'upload_date': u'20120424',
u'description': u'Download "We Can\'t Stop" \r\niTunes: http://smarturl.it/WeCantStop?IQid=SC\r\nAmazon: http://smarturl.it/WeCantStopAMZ?IQid=SC', u'description': u'Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive',
}, },
u'note': u'Soundcloud song', u'note': u'Soundcloud song',
}, },

View file

@ -26,7 +26,7 @@ def _real_extract(self, url):
return [{ return [{
'id': video_id, 'id': video_id,
'url': self._og_search_video_url(webpage), 'url': self._og_search_video_url(webpage, secure=False),
'ext': 'mp4', 'ext': 'mp4',
'title': u'Video by %s' % uploader_id, 'title': u'Video by %s' % uploader_id,
'thumbnail': self._og_search_thumbnail(webpage), 'thumbnail': self._og_search_thumbnail(webpage),

View file

@ -0,0 +1,61 @@
import os
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urllib_parse,
)
from ..aes import (
aes_decrypt_text
)
class KeezMoviesIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>keezmovies\.com/video/.+?(?P<videoid>[0-9]+))'
_TEST = {
u'url': u'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
u'file': u'1214711.mp4',
u'md5': u'6e297b7e789329923fcf83abb67c9289',
u'info_dict': {
u"title": u"Petite Asian Lady Mai Playing In Bathtub",
u"age_limit": 18,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
url = 'http://www.' + mobj.group('url')
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
# embedded video
mobj = re.search(r'href="([^"]+)"></iframe>', webpage)
if mobj:
embedded_url = mobj.group(1)
return self.url_result(embedded_url)
video_title = self._html_search_regex(r'<h1 [^>]*>([^<]+)', webpage, u'title')
video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&amp;', webpage, u'video_url'))
if webpage.find('encrypted=true')!=-1:
password = self._html_search_regex(r'video_title=(.+?)&amp;', webpage, u'password')
video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
path = compat_urllib_parse_urlparse( video_url ).path
extension = os.path.splitext( path )[1][1:]
format = path.split('/')[4].split('_')[:2]
format = "-".join( format )
age_limit = self._rta_search(webpage)
return {
'id': video_id,
'title': video_title,
'url': video_url,
'ext': extension,
'format': format,
'format_id': format,
'age_limit': age_limit,
}

View file

@ -0,0 +1,69 @@
import os
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urllib_parse,
unescapeHTML,
)
from ..aes import (
aes_decrypt_text
)
class PornHubIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9]+))'
_TEST = {
u'url': u'http://www.pornhub.com/view_video.php?viewkey=648719015',
u'file': u'648719015.mp4',
u'md5': u'882f488fa1f0026f023f33576004a2ed',
u'info_dict': {
u"uploader": u"BABES-COM",
u"title": u"Seductive Indian beauty strips down and fingers her pink pussy",
u"age_limit": 18
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
url = 'http://www.' + mobj.group('url')
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, u'title')
video_uploader = self._html_search_regex(r'<b>From: </b>(?:\s|<[^>]*>)*(.+?)<', webpage, u'uploader', fatal=False)
thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, u'thumbnail', fatal=False)
if thumbnail:
thumbnail = compat_urllib_parse.unquote(thumbnail)
video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
if webpage.find('"encrypted":true') != -1:
password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password').replace('+', ' ')
video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
formats = []
for video_url in video_urls:
path = compat_urllib_parse_urlparse( video_url ).path
extension = os.path.splitext( path )[1][1:]
format = path.split('/')[5].split('_')[:2]
format = "-".join( format )
formats.append({
'url': video_url,
'ext': extension,
'format': format,
'format_id': format,
})
formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-'))))
return {
'id': video_id,
'uploader': video_uploader,
'title': video_title,
'thumbnail': thumbnail,
'formats': formats,
'age_limit': 18,
}

View file

@ -16,7 +16,8 @@ class PornotubeIE(InfoExtractor):
u'md5': u'374dd6dcedd24234453b295209aa69b6', u'md5': u'374dd6dcedd24234453b295209aa69b6',
u'info_dict': { u'info_dict': {
u"upload_date": u"20090708", u"upload_date": u"20090708",
u"title": u"Marilyn-Monroe-Bathing" u"title": u"Marilyn-Monroe-Bathing",
u"age_limit": 18
} }
} }

View file

@ -0,0 +1,74 @@
import os
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urllib_parse,
unescapeHTML,
)
from ..aes import (
aes_decrypt_text
)
class SpankwireIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)'
_TEST = {
u'url': u'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
u'file': u'103545.mp4',
u'md5': u'1b3f55e345500552dbc252a3e9c1af43',
u'info_dict': {
u"uploader": u"oreusz",
u"title": u"Buckcherry`s X Rated Music Video Crazy Bitch",
u"description": u"Crazy Bitch X rated music video.",
u"age_limit": 18,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
url = 'http://www.' + mobj.group('url')
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
video_title = self._html_search_regex(r'<h1>([^<]+)', webpage, u'title')
video_uploader = self._html_search_regex(r'by:\s*<a [^>]*>(.+?)</a>', webpage, u'uploader', fatal=False)
thumbnail = self._html_search_regex(r'flashvars\.image_url = "([^"]+)', webpage, u'thumbnail', fatal=False)
description = self._html_search_regex(r'>\s*Description:</div>\s*<[^>]*>([^<]+)', webpage, u'description', fatal=False)
if len(description) == 0:
description = None
video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage)))
if webpage.find('flashvars\.encrypted = "true"') != -1:
password = self._html_search_regex(r'flashvars\.video_title = "([^"]+)', webpage, u'password').replace('+', ' ')
video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
formats = []
for video_url in video_urls:
path = compat_urllib_parse_urlparse( video_url ).path
extension = os.path.splitext( path )[1][1:]
format = path.split('/')[4].split('_')[:2]
format = "-".join( format )
formats.append({
'url': video_url,
'ext': extension,
'format': format,
'format_id': format,
})
formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-'))))
age_limit = self._rta_search(webpage)
return {
'id': video_id,
'uploader': video_uploader,
'title': video_title,
'thumbnail': thumbnail,
'description': description,
'formats': formats,
'age_limit': age_limit,
}

View file

@ -0,0 +1,65 @@
import os
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urllib_parse,
unescapeHTML,
)
from ..aes import (
aes_decrypt_text
)
class Tube8IE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>tube8\.com/[^/]+/[^/]+/(?P<videoid>[0-9]+)/?)'
_TEST = {
u'url': u'http://www.tube8.com/teen/kasia-music-video/229795/',
u'file': u'229795.mp4',
u'md5': u'e9e0b0c86734e5e3766e653509475db0',
u'info_dict': {
u"description": u"hot teen Kasia grinding",
u"uploader": u"unknown",
u"title": u"Kasia music video",
u"age_limit": 18,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
url = 'http://www.' + mobj.group('url')
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
video_title = self._html_search_regex(r'videotitle ="([^"]+)', webpage, u'title')
video_description = self._html_search_regex(r'>Description:</strong>(.+?)<', webpage, u'description', fatal=False)
video_uploader = self._html_search_regex(r'>Submitted by:</strong>(?:\s|<[^>]*>)*(.+?)<', webpage, u'uploader', fatal=False)
thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, u'thumbnail', fatal=False)
if thumbnail:
thumbnail = thumbnail.replace('\\/', '/')
video_url = self._html_search_regex(r'"video_url":"([^"]+)', webpage, u'video_url')
if webpage.find('"encrypted":true')!=-1:
password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password')
video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
path = compat_urllib_parse_urlparse( video_url ).path
extension = os.path.splitext( path )[1][1:]
format = path.split('/')[4].split('_')[:2]
format = "-".join( format )
return {
'id': video_id,
'uploader': video_uploader,
'title': video_title,
'thumbnail': thumbnail,
'description': video_description,
'url': video_url,
'ext': extension,
'format': format,
'format_id': format,
'age_limit': 18,
}

View file

@ -36,20 +36,24 @@ class XHamsterIE(InfoExtractor):
}] }]
def _real_extract(self,url): def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url) def extract_video_url(webpage):
video_id = mobj.group('id')
seo = mobj.group('seo')
mrss_url = 'http://xhamster.com/movies/%s/%s.html?hd' % (video_id, seo)
webpage = self._download_webpage(mrss_url, video_id)
mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage) mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
if mobj is None: if mobj is None:
raise ExtractorError(u'Unable to extract media URL') raise ExtractorError(u'Unable to extract media URL')
if len(mobj.group('server')) == 0: if len(mobj.group('server')) == 0:
video_url = compat_urllib_parse.unquote(mobj.group('file')) return compat_urllib_parse.unquote(mobj.group('file'))
else: else:
video_url = mobj.group('server')+'/key='+mobj.group('file') return mobj.group('server')+'/key='+mobj.group('file')
def is_hd(webpage):
return webpage.find('<div class=\'icon iconHD\'>') != -1
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
seo = mobj.group('seo')
mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo)
webpage = self._download_webpage(mrss_url, video_id)
video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
webpage, u'title') webpage, u'title')
@ -76,14 +80,32 @@ def _real_extract(self,url):
age_limit = self._rta_search(webpage) age_limit = self._rta_search(webpage)
return [{ video_url = extract_video_url(webpage)
'id': video_id, hd = is_hd(webpage)
formats = [{
'url': video_url, 'url': video_url,
'ext': determine_ext(video_url), 'ext': determine_ext(video_url),
'format': 'hd' if hd else 'sd',
'format_id': 'hd' if hd else 'sd',
}]
if not hd:
webpage = self._download_webpage(mrss_url+'?hd', video_id)
if is_hd(webpage):
video_url = extract_video_url(webpage)
formats.append({
'url': video_url,
'ext': determine_ext(video_url),
'format': 'hd',
'format_id': 'hd',
})
return {
'id': video_id,
'title': video_title, 'title': video_title,
'formats': formats,
'description': video_description, 'description': video_description,
'upload_date': video_upload_date, 'upload_date': video_upload_date,
'uploader_id': video_uploader_id, 'uploader_id': video_uploader_id,
'thumbnail': video_thumbnail, 'thumbnail': video_thumbnail,
'age_limit': age_limit, 'age_limit': age_limit,
}] }

View file

@ -13,7 +13,8 @@ class YouJizzIE(InfoExtractor):
u'file': u'2189178.flv', u'file': u'2189178.flv',
u'md5': u'07e15fa469ba384c7693fd246905547c', u'md5': u'07e15fa469ba384c7693fd246905547c',
u'info_dict': { u'info_dict': {
u"title": u"Zeichentrick 1" u"title": u"Zeichentrick 1",
u"age_limit": 18,
} }
} }
@ -25,6 +26,8 @@ def _real_extract(self, url):
# Get webpage content # Get webpage content
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
age_limit = self._rta_search(webpage)
# Get the video title # Get the video title
video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>', video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',
webpage, u'title').strip() webpage, u'title').strip()
@ -60,6 +63,7 @@ def _real_extract(self, url):
'title': video_title, 'title': video_title,
'ext': 'flv', 'ext': 'flv',
'format': 'flv', 'format': 'flv',
'player_url': embed_page_url} 'player_url': embed_page_url,
'age_limit': age_limit}
return [info] return [info]

View file

@ -17,7 +17,7 @@
) )
class YouPornIE(InfoExtractor): class YouPornIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)' _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))'
_TEST = { _TEST = {
u'url': u'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/', u'url': u'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
u'file': u'505835.mp4', u'file': u'505835.mp4',
@ -31,23 +31,10 @@ class YouPornIE(InfoExtractor):
} }
} }
def _print_formats(self, formats):
"""Print all available formats"""
print(u'Available formats:')
print(u'ext\t\tformat')
print(u'---------------------------------')
for format in formats:
print(u'%s\t\t%s' % (format['ext'], format['format']))
def _specific(self, req_format, formats):
for x in formats:
if x["format"] == req_format:
return x
return None
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid') video_id = mobj.group('videoid')
url = 'http://www.' + mobj.group('url')
req = compat_urllib_request.Request(url) req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1') req.add_header('Cookie', 'age_verified=1')
@ -71,27 +58,22 @@ def _real_extract(self, url):
except KeyError: except KeyError:
raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1]) raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
# Get all of the formats available # Get all of the links from the page
DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>' DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
download_list_html = self._search_regex(DOWNLOAD_LIST_RE, download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
webpage, u'download list').strip() webpage, u'download list').strip()
LINK_RE = r'<a href="([^"]+)">'
# Get all of the links from the page
LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
links = re.findall(LINK_RE, download_list_html) links = re.findall(LINK_RE, download_list_html)
# Get link of hd video if available # Get all encrypted links
mobj = re.search(r'var encryptedQuality720URL = \'(?P<encrypted_video_url>[a-zA-Z0-9+/]+={0,2})\';', webpage) encrypted_links = re.findall(r'var encryptedQuality[0-9]{3}URL = \'([a-zA-Z0-9+/]+={0,2})\';', webpage)
if mobj != None: for encrypted_link in encrypted_links:
encrypted_video_url = mobj.group(u'encrypted_video_url') link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
video_url = aes_decrypt_text(encrypted_video_url, video_title, 32).decode('utf-8') links.append(link)
links = [video_url] + links
if not links: if not links:
raise ExtractorError(u'ERROR: no known formats available for video') raise ExtractorError(u'ERROR: no known formats available for video')
self.to_screen(u'Links found: %d' % len(links))
formats = [] formats = []
for link in links: for link in links:
@ -103,39 +85,32 @@ def _real_extract(self, url):
path = compat_urllib_parse_urlparse( video_url ).path path = compat_urllib_parse_urlparse( video_url ).path
extension = os.path.splitext( path )[1][1:] extension = os.path.splitext( path )[1][1:]
format = path.split('/')[4].split('_')[:2] format = path.split('/')[4].split('_')[:2]
# size = format[0] # size = format[0]
# bitrate = format[1] # bitrate = format[1]
format = "-".join( format ) format = "-".join( format )
# title = u'%s-%s-%s' % (video_title, size, bitrate) # title = u'%s-%s-%s' % (video_title, size, bitrate)
formats.append({ formats.append({
'id': video_id,
'url': video_url, 'url': video_url,
'ext': extension,
'format': format,
'format_id': format,
})
# Sort and remove doubles
formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-'))))
for i in range(len(formats)-1,0,-1):
if formats[i]['format_id'] == formats[i-1]['format_id']:
del formats[i]
return {
'id': video_id,
'uploader': video_uploader, 'uploader': video_uploader,
'upload_date': upload_date, 'upload_date': upload_date,
'title': video_title, 'title': video_title,
'ext': extension,
'format': format,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'description': video_description, 'description': video_description,
'age_limit': age_limit, 'age_limit': age_limit,
}) 'formats': formats,
}
if self._downloader.params.get('listformats', None):
self._print_formats(formats)
return
req_format = self._downloader.params.get('format', 'best')
self.to_screen(u'Format: %s' % req_format)
if req_format is None or req_format == 'best':
return [formats[0]]
elif req_format == 'worst':
return [formats[-1]]
elif req_format in ('-1', 'all'):
return formats
else:
format = self._specific( req_format, formats )
if format is None:
raise ExtractorError(u'Requested format not available')
return [format]