yt-dlc/youtube_dl/extractor/youporn.py

193 lines
7.6 KiB
Python
Raw Normal View History

2014-03-21 00:19:54 +01:00
from __future__ import unicode_literals
2013-06-23 22:12:14 +02:00
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 17:18:17 +01:00
sanitized_Request,
str_to_int,
2013-06-23 22:12:14 +02:00
unescapeHTML,
unified_strdate,
2018-07-21 14:08:28 +02:00
url_or_none,
2013-06-23 22:12:14 +02:00
)
from ..aes import aes_decrypt_text
2013-06-23 22:12:14 +02:00
2013-06-23 22:12:14 +02:00
class YouPornIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
2015-10-25 18:12:12 +01:00
_TESTS = [{
2014-03-21 00:19:54 +01:00
'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
2016-06-11 23:49:37 +02:00
'md5': '3744d24c50438cf5b6f6d59feb5055c2',
2014-03-21 00:19:54 +01:00
'info_dict': {
'id': '505835',
'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
2014-03-21 00:19:54 +01:00
'ext': 'mp4',
'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Ask Dan And Jennifer',
2017-06-21 19:47:02 +02:00
'upload_date': '20101217',
'average_rating': int,
'view_count': int,
2015-10-25 18:41:10 +01:00
'comment_count': int,
'categories': list,
'tags': list,
2014-03-21 00:19:54 +01:00
'age_limit': 18,
2015-10-25 18:12:12 +01:00
},
}, {
# Unknown uploader
2015-10-25 18:12:12 +01:00
'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
'info_dict': {
'id': '561726',
'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show',
'ext': 'mp4',
'title': 'Big Tits Awesome Brunette On amazing webcam show',
'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Unknown',
2017-06-21 19:47:02 +02:00
'upload_date': '20110418',
2015-10-25 18:12:12 +01:00
'average_rating': int,
'view_count': int,
2015-10-25 18:41:10 +01:00
'comment_count': int,
2015-10-25 18:12:12 +01:00
'categories': list,
'tags': list,
'age_limit': 18,
},
'params': {
'skip_download': True,
},
}]
2013-06-23 22:12:14 +02:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
2013-06-23 22:12:14 +02:00
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 17:18:17 +01:00
request = sanitized_Request(url)
request.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(request, display_id)
title = self._html_search_regex(
r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>',
webpage, 'title', default=None) or self._og_search_title(
webpage, default=None) or self._html_search_meta(
'title', webpage, fatal=True)
2013-06-23 22:12:14 +02:00
links = []
2017-06-21 19:40:15 +02:00
# Main source
definitions = self._parse_json(
self._search_regex(
r'mediaDefinition\s*=\s*(\[.+?\]);', webpage,
'media definitions', default='[]'),
video_id, fatal=False)
if definitions:
for definition in definitions:
if not isinstance(definition, dict):
continue
2018-07-21 14:08:28 +02:00
video_url = url_or_none(definition.get('videoUrl'))
if video_url:
2017-06-21 19:40:15 +02:00
links.append(video_url)
# Fallback #1, this also contains extra low quality 180p format
for _, link in re.findall(r'<a[^>]+href=(["\'])(http.+?)\1[^>]+title=["\']Download [Vv]ideo', webpage):
links.append(link)
# Fallback #2 (unavailable as at 22.06.2017)
sources = self._search_regex(
2016-03-04 20:51:27 +01:00
r'(?s)sources\s*:\s*({.+?})', webpage, 'sources', default=None)
if sources:
for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources):
links.append(link)
2014-11-23 20:41:03 +01:00
2017-06-21 19:40:15 +02:00
# Fallback #3 (unavailable as at 22.06.2017)
for _, link in re.findall(
2017-06-21 19:40:15 +02:00
r'(?:videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage):
links.append(link)
2017-06-21 19:40:15 +02:00
# Fallback #4, encrypted links (unavailable as at 22.06.2017)
for _, encrypted_link in re.findall(
r'encryptedQuality\d{3,4}URL\s*=\s*(["\'])([\da-zA-Z+/=]+)\1', webpage):
links.append(aes_decrypt_text(encrypted_link, title, 32).decode('utf-8'))
2013-06-23 22:12:14 +02:00
formats = []
for video_url in set(unescapeHTML(link) for link in links):
f = {
2013-06-23 22:12:14 +02:00
'url': video_url,
}
# Video URL's path looks like this:
# /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
# /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
# We will benefit from it by extracting some metadata
mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url)
if mobj:
height = int(mobj.group('height'))
bitrate = int(mobj.group('bitrate'))
f.update({
'format_id': '%dp-%dk' % (height, bitrate),
'height': height,
'tbr': bitrate,
})
formats.append(f)
self._sort_formats(formats)
description = self._html_search_regex(
r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>',
webpage, 'description',
default=None) or self._og_search_description(
webpage, default=None)
thumbnail = self._search_regex(
r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
webpage, 'thumbnail', fatal=False, group='thumbnail')
2015-10-25 18:12:12 +01:00
uploader = self._html_search_regex(
2016-06-11 23:49:37 +02:00
r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
webpage, 'uploader', fatal=False)
upload_date = unified_strdate(self._html_search_regex(
2017-06-21 19:47:02 +02:00
[r'Date\s+[Aa]dded:\s*<span>([^<]+)',
r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>'],
webpage, 'upload date', fatal=False))
age_limit = self._rta_search(webpage)
average_rating = int_or_none(self._search_regex(
2016-06-11 23:49:37 +02:00
r'<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
webpage, 'average rating', fatal=False))
view_count = str_to_int(self._search_regex(
2016-06-11 23:49:37 +02:00
r'(?s)<div[^>]+class=(["\']).*?\bvideoInfoViews\b.*?\1[^>]*>.*?(?P<count>[\d,.]+)<',
webpage, 'view count', fatal=False, group='count'))
2015-10-25 18:41:10 +01:00
comment_count = str_to_int(self._search_regex(
r'>All [Cc]omments? \(([\d,.]+)\)',
webpage, 'comment count', fatal=False))
def extract_tag_box(regex, title):
tag_box = self._search_regex(regex, webpage, title, default=None)
if not tag_box:
return []
return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
categories = extract_tag_box(
r'(?s)Categories:.*?</[^>]+>(.+?)</div>', 'categories')
tags = extract_tag_box(
r'(?s)Tags:.*?</div>\s*<div[^>]+class=["\']tagBoxContent["\'][^>]*>(.+?)</div>',
'tags')
2014-11-23 20:41:03 +01:00
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'upload_date': upload_date,
'average_rating': average_rating,
'view_count': view_count,
2015-10-25 18:41:10 +01:00
'comment_count': comment_count,
'categories': categories,
'tags': tags,
'age_limit': age_limit,
'formats': formats,
}