1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-23 12:23:21 +08:00
youtube-dl/youtube_dl/extractor/youporn.py
Sergey M? 5c2266df4b 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
2015-11-23 21:56:23 +06:00

172 lines
6.7 KiB
Python

from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
sanitized_Request,
str_to_int,
unescapeHTML,
unified_strdate,
)
from ..aes import aes_decrypt_text
class YouPornIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
'md5': '71ec5fcfddacf80f495efa8b6a8d9a89',
'info_dict': {
'id': '505835',
'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
'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': 're:^https?://.*\.jpg$',
'uploader': 'Ask Dan And Jennifer',
'upload_date': '20101221',
'average_rating': int,
'view_count': int,
'comment_count': int,
'categories': list,
'tags': list,
'age_limit': 18,
},
}, {
# Anonymous User uploader
'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
'info_dict': {
'id': '561726',
'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show',
'ext': 'mp4',
'title': 'Big Tits Awesome Brunette On amazing webcam show',
'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'Anonymous User',
'upload_date': '20111125',
'average_rating': int,
'view_count': int,
'comment_count': int,
'categories': list,
'tags': list,
'age_limit': 18,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
request = sanitized_Request(url)
request.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(request, display_id)
title = self._search_regex(
[r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P<title>.+?)\1',
r'<h1[^>]+class=["\']heading\d?["\'][^>]*>([^<])<'],
webpage, 'title', group='title')
links = []
sources = self._search_regex(
r'sources\s*:\s*({.+?})', webpage, 'sources', default=None)
if sources:
for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources):
links.append(link)
# Fallback #1
for _, link in re.findall(
r'(?:videoUrl|videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage):
links.append(link)
# Fallback #2, 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 #3, encrypted links
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'))
formats = []
for video_url in set(unescapeHTML(link) for link in links):
f = {
'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
# 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[^>]+class=["\']video-description["\'][^>]*>(.+?)</div>',
webpage, 'description', default=None)
thumbnail = self._search_regex(
r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
webpage, 'thumbnail', fatal=False, group='thumbnail')
uploader = self._html_search_regex(
r'(?s)<div[^>]+class=["\']videoInfoBy["\'][^>]*>\s*By:\s*</div>(.+?)</(?:a|div)>',
webpage, 'uploader', fatal=False)
upload_date = unified_strdate(self._html_search_regex(
r'(?s)<div[^>]+class=["\']videoInfoTime["\'][^>]*>(.+?)</div>',
webpage, 'upload date', fatal=False))
age_limit = self._rta_search(webpage)
average_rating = int_or_none(self._search_regex(
r'<div[^>]+class=["\']videoInfoRating["\'][^>]*>\s*<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
webpage, 'average rating', fatal=False))
view_count = str_to_int(self._search_regex(
r'(?s)<div[^>]+class=["\']videoInfoViews["\'][^>]*>.*?([\d,.]+)\s*</div>',
webpage, 'view count', fatal=False))
comment_count = str_to_int(self._search_regex(
r'>All [Cc]omments? \(([\d,.]+)\)',
webpage, 'comment count', fatal=False))
def extract_tag_box(title):
tag_box = self._search_regex(
(r'<div[^>]+class=["\']tagBoxTitle["\'][^>]*>\s*%s\b.*?</div>\s*'
'<div[^>]+class=["\']tagBoxContent["\']>(.+?)</div>') % re.escape(title),
webpage, '%s tag box' % title, default=None)
if not tag_box:
return []
return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
categories = extract_tag_box('Category')
tags = extract_tag_box('Tags')
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,
'comment_count': comment_count,
'categories': categories,
'tags': tags,
'age_limit': age_limit,
'formats': formats,
}