16 changed files with 409 additions and 89 deletions
Unified View
Diff Options
-
39devscripts/check-porn.py
-
6setup.py
-
2youtube_dl/YoutubeDL.py
-
4youtube_dl/extractor/__init__.py
-
10youtube_dl/extractor/addanime.py
-
8youtube_dl/extractor/common.py
-
14youtube_dl/extractor/exfm.py
-
2youtube_dl/extractor/instagram.py
-
61youtube_dl/extractor/keezmovies.py
-
69youtube_dl/extractor/pornhub.py
-
3youtube_dl/extractor/pornotube.py
-
74youtube_dl/extractor/spankwire.py
-
65youtube_dl/extractor/tube8.py
-
52youtube_dl/extractor/xhamster.py
-
8youtube_dl/extractor/youjizz.py
-
81youtube_dl/extractor/youporn.py
@ -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() |
@ -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=(.+?)&', 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 ) |
||||
|
|
||||
|
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, |
||||
|
} |
@ -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, |
||||
|
} |
@ -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, |
||||
|
} |
@ -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, |
||||
|
} |
xxxxxxxxxx