yt-dlp/youtube_dl/extractor/pornhub.py

271 lines
9.4 KiB
Python
Raw Normal View History

# coding: utf-8
2014-01-07 10:25:34 +01:00
from __future__ import unicode_literals
import itertools
2013-10-27 01:04:22 +02:00
import os
import re
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
2013-10-27 01:04:22 +02:00
compat_urllib_parse_urlparse,
)
from ..utils import (
ExtractorError,
int_or_none,
2016-03-27 20:21:08 +02:00
orderedSet,
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,
2013-10-27 01:04:22 +02:00
)
from ..aes import (
aes_decrypt_text
)
2014-01-07 10:25:34 +01:00
2013-10-27 01:04:22 +02:00
class PornHubIE(InfoExtractor):
IE_DESC = 'PornHub and Thumbzilla'
_VALID_URL = r'''(?x)
https?://
(?:
(?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)|
(?:www\.)?thumbzilla\.com/video/
)
(?P<id>[0-9a-z]+)
'''
_TESTS = [{
2014-01-07 10:25:34 +01:00
'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
'md5': '1e19b41231a02eba417839222ac9d58e',
2014-01-07 10:25:34 +01:00
'info_dict': {
'id': '648719015',
'ext': 'mp4',
2016-02-14 10:37:17 +01:00
'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
'uploader': 'Babes',
'duration': 361,
'view_count': int,
'like_count': int,
'dislike_count': int,
'comment_count': int,
'age_limit': 18,
},
}, {
# non-ASCII title
'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002',
'info_dict': {
'id': '1331683002',
'ext': 'mp4',
'title': '重庆婷婷女王足交',
'uploader': 'cj397186295',
'duration': 1753,
'view_count': int,
'like_count': int,
'dislike_count': int,
'comment_count': int,
'age_limit': 18,
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
'only_matching': True,
}, {
# removed at the request of cam4.com
'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862',
'only_matching': True,
}, {
# removed at the request of the copyright owner
'url': 'http://www.pornhub.com/view_video.php?viewkey=788152859',
'only_matching': True,
}, {
# removed by uploader
'url': 'http://www.pornhub.com/view_video.php?viewkey=ph572716d15a111',
'only_matching': True,
}, {
# private video
'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7',
'only_matching': True,
}, {
'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex',
'only_matching': True,
}]
2013-10-27 01:04:22 +02:00
@classmethod
def _extract_url(cls, webpage):
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/\d+)\1', webpage)
if mobj:
return mobj.group('url')
def _extract_count(self, pattern, webpage, name):
return str_to_int(self._search_regex(
pattern, webpage, '%s count' % name, fatal=False))
2013-10-27 01:04:22 +02:00
def _real_extract(self, url):
video_id = self._match_id(url)
2013-10-27 01:04:22 +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
req = sanitized_Request(
2015-06-12 23:24:36 +02:00
'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id)
2013-10-27 01:04:22 +02:00
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
error_msg = self._html_search_regex(
r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
webpage, 'error message', default=None, group='error')
if error_msg:
error_msg = re.sub(r'\s+', ' ', error_msg)
raise ExtractorError(
'PornHub said: %s' % error_msg,
expected=True, video_id=video_id)
# video_title from flashvars contains whitespace instead of non-ASCII (see
# http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
# on that anymore.
title = self._html_search_meta(
'twitter:title', webpage, default=None) or self._search_regex(
(r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)',
r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1',
r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'),
webpage, 'title', group='title')
flashvars = self._parse_json(
self._search_regex(
2016-03-27 21:21:44 +02:00
r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
video_id)
if flashvars:
thumbnail = flashvars.get('image_url')
duration = int_or_none(flashvars.get('video_duration'))
else:
title, thumbnail, duration = [None] * 3
video_uploader = self._html_search_regex(
2015-02-19 17:15:49 +01:00
r'(?s)From:&nbsp;.+?<(?:a href="/users/|a href="/channels/|span class="username)[^>]+>(.+?)<',
webpage, 'uploader', fatal=False)
2013-10-27 01:04:22 +02:00
view_count = self._extract_count(
r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
like_count = self._extract_count(
r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
dislike_count = self._extract_count(
r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
comment_count = self._extract_count(
r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
2015-08-02 22:41:17 +02:00
video_urls = list(map(compat_urllib_parse_unquote, re.findall(r"player_quality_[0-9]{3}p\s*=\s*'([^']+)'", webpage)))
2013-10-27 01:04:22 +02:00
if webpage.find('"encrypted":true') != -1:
password = compat_urllib_parse_unquote_plus(
self._search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
2013-10-27 01:04:22 +02:00
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:]
2013-10-27 01:04:22 +02:00
format = path.split('/')[5].split('_')[:2]
2016-02-14 10:37:17 +01:00
format = '-'.join(format)
2014-01-07 10:25:34 +01:00
2015-08-03 15:37:48 +02:00
m = re.match(r'^(?P<height>[0-9]+)[pP]-(?P<tbr>[0-9]+)[kK]$', format)
2014-01-07 10:25:34 +01:00
if m is None:
height = None
tbr = None
else:
height = int(m.group('height'))
tbr = int(m.group('tbr'))
2013-10-27 01:04:22 +02:00
formats.append({
'url': video_url,
'ext': extension,
'format': format,
'format_id': format,
2014-01-07 10:25:34 +01:00
'tbr': tbr,
'height': height,
2013-10-27 01:04:22 +02:00
})
2014-01-07 10:25:34 +01:00
self._sort_formats(formats)
2013-10-27 01:04:22 +02:00
return {
'id': video_id,
'uploader': video_uploader,
'title': title,
2013-10-27 01:04:22 +02:00
'thumbnail': thumbnail,
'duration': duration,
'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
'comment_count': comment_count,
2013-10-27 01:04:22 +02:00
'formats': formats,
'age_limit': 18,
2013-10-27 01:04:22 +02:00
}
class PornHubPlaylistBaseIE(InfoExtractor):
def _extract_entries(self, webpage):
return [
self.url_result(
'http://www.pornhub.com/%s' % video_url,
PornHubIE.ie_key(), video_title=title)
for video_url, title in orderedSet(re.findall(
r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
webpage))
]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
entries = self._extract_entries(webpage)
playlist = self._parse_json(
self._search_regex(
r'playlistObject\s*=\s*({.+?});', webpage, 'playlist'),
playlist_id)
return self.playlist_result(
entries, playlist_id, playlist.get('title'), playlist.get('description'))
class PornHubPlaylistIE(PornHubPlaylistBaseIE):
_VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.pornhub.com/playlist/6201671',
'info_dict': {
'id': '6201671',
'title': 'P0p4',
},
'playlist_mincount': 35,
}]
class PornHubUserVideosIE(PornHubPlaylistBaseIE):
_VALID_URL = r'https?://(?:www\.)?pornhub\.com/users/(?P<id>[^/]+)/videos'
_TESTS = [{
'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
'info_dict': {
'id': 'zoe_ph',
},
'playlist_mincount': 171,
}, {
'url': 'http://www.pornhub.com/users/rushandlia/videos',
'only_matching': True,
}]
def _real_extract(self, url):
user_id = self._match_id(url)
entries = []
for page_num in itertools.count(1):
try:
webpage = self._download_webpage(
url, user_id, 'Downloading page %d' % page_num,
query={'page': page_num})
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
break
page_entries = self._extract_entries(webpage)
if not page_entries:
break
entries.extend(page_entries)
return self.playlist_result(entries, user_id)