2016-06-14 06:57:59 +09:00
|
|
|
# coding: utf-8
|
2014-01-07 18:25:34 +09:00
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
2016-03-28 03:50:46 +09:00
|
|
|
import itertools
|
2013-10-27 08:04:22 +09:00
|
|
|
import os
|
|
|
|
import re
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
2014-12-13 20:24:42 +09:00
|
|
|
from ..compat import (
|
2016-03-28 03:50:46 +09:00
|
|
|
compat_HTTPError,
|
2015-07-18 02:47:23 +09:00
|
|
|
compat_urllib_parse_unquote,
|
|
|
|
compat_urllib_parse_unquote_plus,
|
2013-10-27 08:04:22 +09:00
|
|
|
compat_urllib_parse_urlparse,
|
2014-12-13 20:24:42 +09:00
|
|
|
)
|
|
|
|
from ..utils import (
|
2015-01-23 07:48:58 +09:00
|
|
|
ExtractorError,
|
2016-02-20 00:42:46 +09:00
|
|
|
int_or_none,
|
2016-09-11 20:22:51 +09:00
|
|
|
js_to_json,
|
2016-03-28 03:21:08 +09:00
|
|
|
orderedSet,
|
2015-11-22 01:18:17 +09:00
|
|
|
sanitized_Request,
|
2014-03-22 23:29:01 +09:00
|
|
|
str_to_int,
|
2013-10-27 08:04:22 +09:00
|
|
|
)
|
|
|
|
from ..aes import (
|
|
|
|
aes_decrypt_text
|
|
|
|
)
|
|
|
|
|
2014-01-07 18:25:34 +09:00
|
|
|
|
2013-10-27 08:04:22 +09:00
|
|
|
class PornHubIE(InfoExtractor):
|
2016-07-02 04:11:07 +09:00
|
|
|
IE_DESC = 'PornHub and Thumbzilla'
|
|
|
|
_VALID_URL = r'''(?x)
|
|
|
|
https?://
|
|
|
|
(?:
|
|
|
|
(?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)|
|
|
|
|
(?:www\.)?thumbzilla\.com/video/
|
|
|
|
)
|
2016-11-06 23:52:00 +09:00
|
|
|
(?P<id>[\da-z]+)
|
2016-07-02 04:11:07 +09:00
|
|
|
'''
|
2015-06-19 01:26:17 +09:00
|
|
|
_TESTS = [{
|
2014-01-07 18:25:34 +09:00
|
|
|
'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
|
2016-02-20 00:42:46 +09:00
|
|
|
'md5': '1e19b41231a02eba417839222ac9d58e',
|
2014-01-07 18:25:34 +09:00
|
|
|
'info_dict': {
|
2014-10-27 08:33:35 +09:00
|
|
|
'id': '648719015',
|
|
|
|
'ext': 'mp4',
|
2016-02-14 18:37:17 +09:00
|
|
|
'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
|
2016-02-20 00:42:46 +09:00
|
|
|
'uploader': 'Babes',
|
|
|
|
'duration': 361,
|
|
|
|
'view_count': int,
|
|
|
|
'like_count': int,
|
|
|
|
'dislike_count': int,
|
|
|
|
'comment_count': int,
|
|
|
|
'age_limit': 18,
|
2016-09-11 20:22:51 +09:00
|
|
|
'tags': list,
|
|
|
|
'categories': list,
|
2016-06-14 06:57:59 +09:00
|
|
|
},
|
|
|
|
}, {
|
|
|
|
# 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,
|
2016-09-11 20:22:51 +09:00
|
|
|
'tags': list,
|
|
|
|
'categories': list,
|
2016-06-14 06:57:59 +09:00
|
|
|
},
|
|
|
|
'params': {
|
|
|
|
'skip_download': True,
|
|
|
|
},
|
2015-06-19 01:26:17 +09:00
|
|
|
}, {
|
|
|
|
'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
|
|
|
|
'only_matching': True,
|
2015-09-16 00:24:01 +09:00
|
|
|
}, {
|
2016-07-01 05:18:27 +09:00
|
|
|
# removed at the request of cam4.com
|
2015-09-16 00:24:01 +09:00
|
|
|
'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862',
|
|
|
|
'only_matching': True,
|
2016-07-01 05:18:27 +09:00
|
|
|
}, {
|
|
|
|
# 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,
|
2016-07-04 05:27:00 +09:00
|
|
|
}, {
|
|
|
|
# private video
|
|
|
|
'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7',
|
|
|
|
'only_matching': True,
|
2016-07-02 04:11:07 +09:00
|
|
|
}, {
|
|
|
|
'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex',
|
|
|
|
'only_matching': True,
|
2015-06-19 01:26:17 +09:00
|
|
|
}]
|
2013-10-27 08:04:22 +09:00
|
|
|
|
2016-11-06 23:52:00 +09:00
|
|
|
@staticmethod
|
|
|
|
def _extract_urls(webpage):
|
|
|
|
return re.findall(
|
|
|
|
r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.com/embed/[\da-z]+)',
|
|
|
|
webpage)
|
2015-06-13 06:36:16 +09:00
|
|
|
|
2014-03-22 23:29:01 +09:00
|
|
|
def _extract_count(self, pattern, webpage, name):
|
2015-03-30 22:41:04 +09:00
|
|
|
return str_to_int(self._search_regex(
|
|
|
|
pattern, webpage, '%s count' % name, fatal=False))
|
2014-03-22 23:29:01 +09:00
|
|
|
|
2013-10-27 08:04:22 +09:00
|
|
|
def _real_extract(self, url):
|
2014-10-27 08:33:35 +09:00
|
|
|
video_id = self._match_id(url)
|
2013-10-27 08:04:22 +09:00
|
|
|
|
2015-11-22 01:18:17 +09:00
|
|
|
req = sanitized_Request(
|
2015-06-13 06:24:36 +09:00
|
|
|
'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id)
|
2013-10-27 08:04:22 +09:00
|
|
|
req.add_header('Cookie', 'age_verified=1')
|
|
|
|
webpage = self._download_webpage(req, video_id)
|
|
|
|
|
2015-01-23 07:48:58 +09:00
|
|
|
error_msg = self._html_search_regex(
|
2016-07-22 23:24:09 +09:00
|
|
|
r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
|
2016-07-01 05:14:23 +09:00
|
|
|
webpage, 'error message', default=None, group='error')
|
2015-01-23 07:48:58 +09:00
|
|
|
if error_msg:
|
|
|
|
error_msg = re.sub(r'\s+', ' ', error_msg)
|
|
|
|
raise ExtractorError(
|
|
|
|
'PornHub said: %s' % error_msg,
|
|
|
|
expected=True, video_id=video_id)
|
|
|
|
|
2016-06-14 06:57:59 +09:00
|
|
|
# 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')
|
|
|
|
|
2016-02-20 00:42:46 +09:00
|
|
|
flashvars = self._parse_json(
|
|
|
|
self._search_regex(
|
2016-03-28 04:21:44 +09:00
|
|
|
r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
|
2016-02-20 00:42:46 +09:00
|
|
|
video_id)
|
|
|
|
if flashvars:
|
|
|
|
thumbnail = flashvars.get('image_url')
|
|
|
|
duration = int_or_none(flashvars.get('video_duration'))
|
|
|
|
else:
|
2016-06-14 06:57:59 +09:00
|
|
|
title, thumbnail, duration = [None] * 3
|
2016-02-20 00:42:46 +09:00
|
|
|
|
2014-03-22 23:29:01 +09:00
|
|
|
video_uploader = self._html_search_regex(
|
2015-02-20 01:15:49 +09:00
|
|
|
r'(?s)From: .+?<(?:a href="/users/|a href="/channels/|span class="username)[^>]+>(.+?)<',
|
2014-03-22 23:29:01 +09:00
|
|
|
webpage, 'uploader', fatal=False)
|
2013-10-27 08:04:22 +09:00
|
|
|
|
2015-03-30 22:41:04 +09:00
|
|
|
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')
|
2014-03-22 23:29:01 +09:00
|
|
|
comment_count = self._extract_count(
|
2015-03-30 22:41:04 +09:00
|
|
|
r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
|
2014-03-22 23:29:01 +09:00
|
|
|
|
2017-02-07 03:52:59 +09:00
|
|
|
video_urls = []
|
|
|
|
for quote, video_url in re.findall(
|
|
|
|
r'player_quality_[0-9]{3,4}p\s*=\s*(["\'])(.+?)\1;', webpage):
|
|
|
|
video_urls.append(compat_urllib_parse_unquote(re.sub(
|
|
|
|
r'{0}\s*\+\s*{0}'.format(quote), '', video_url)))
|
|
|
|
|
2013-10-27 08:04:22 +09:00
|
|
|
if webpage.find('"encrypted":true') != -1:
|
2015-07-18 02:47:23 +09:00
|
|
|
password = compat_urllib_parse_unquote_plus(
|
2015-05-27 04:41:00 +09:00
|
|
|
self._search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
|
2013-10-27 08:04:22 +09:00
|
|
|
video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
|
|
|
|
|
|
|
|
formats = []
|
|
|
|
for video_url in video_urls:
|
2013-11-03 22:03:17 +09:00
|
|
|
path = compat_urllib_parse_urlparse(video_url).path
|
|
|
|
extension = os.path.splitext(path)[1][1:]
|
2013-10-27 08:04:22 +09:00
|
|
|
format = path.split('/')[5].split('_')[:2]
|
2016-02-14 18:37:17 +09:00
|
|
|
format = '-'.join(format)
|
2014-01-07 18:25:34 +09:00
|
|
|
|
2015-08-03 22:37:48 +09:00
|
|
|
m = re.match(r'^(?P<height>[0-9]+)[pP]-(?P<tbr>[0-9]+)[kK]$', format)
|
2014-01-07 18:25:34 +09:00
|
|
|
if m is None:
|
|
|
|
height = None
|
|
|
|
tbr = None
|
|
|
|
else:
|
|
|
|
height = int(m.group('height'))
|
|
|
|
tbr = int(m.group('tbr'))
|
|
|
|
|
2013-10-27 08:04:22 +09:00
|
|
|
formats.append({
|
|
|
|
'url': video_url,
|
|
|
|
'ext': extension,
|
|
|
|
'format': format,
|
|
|
|
'format_id': format,
|
2014-01-07 18:25:34 +09:00
|
|
|
'tbr': tbr,
|
|
|
|
'height': height,
|
2013-10-27 08:04:22 +09:00
|
|
|
})
|
2014-01-07 18:25:34 +09:00
|
|
|
self._sort_formats(formats)
|
2013-10-27 08:04:22 +09:00
|
|
|
|
2016-09-11 20:22:51 +09:00
|
|
|
page_params = self._parse_json(self._search_regex(
|
|
|
|
r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})',
|
|
|
|
webpage, 'page parameters', group='data', default='{}'),
|
|
|
|
video_id, transform_source=js_to_json, fatal=False)
|
|
|
|
tags = categories = None
|
|
|
|
if page_params:
|
|
|
|
tags = page_params.get('tags', '').split(',')
|
|
|
|
categories = page_params.get('categories', '').split(',')
|
|
|
|
|
2013-10-27 08:04:22 +09:00
|
|
|
return {
|
|
|
|
'id': video_id,
|
|
|
|
'uploader': video_uploader,
|
2016-06-14 06:57:59 +09:00
|
|
|
'title': title,
|
2013-10-27 08:04:22 +09:00
|
|
|
'thumbnail': thumbnail,
|
2016-02-20 00:42:46 +09:00
|
|
|
'duration': duration,
|
2014-03-22 23:29:01 +09:00
|
|
|
'view_count': view_count,
|
|
|
|
'like_count': like_count,
|
|
|
|
'dislike_count': dislike_count,
|
|
|
|
'comment_count': comment_count,
|
2013-10-27 08:04:22 +09:00
|
|
|
'formats': formats,
|
2013-10-28 14:50:17 +09:00
|
|
|
'age_limit': 18,
|
2016-09-11 20:22:51 +09:00
|
|
|
'tags': tags,
|
|
|
|
'categories': categories,
|
2013-10-27 08:04:22 +09:00
|
|
|
}
|
2015-02-20 01:15:19 +09:00
|
|
|
|
|
|
|
|
2016-02-19 01:29:17 +09:00
|
|
|
class PornHubPlaylistBaseIE(InfoExtractor):
|
|
|
|
def _extract_entries(self, webpage):
|
|
|
|
return [
|
2016-03-28 03:32:57 +09:00
|
|
|
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))
|
2016-02-19 01:29:17 +09:00
|
|
|
]
|
2015-02-20 01:15:19 +09:00
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
playlist_id = self._match_id(url)
|
|
|
|
|
|
|
|
webpage = self._download_webpage(url, playlist_id)
|
|
|
|
|
2017-01-04 07:32:18 +09:00
|
|
|
# Only process container div with main playlist content skipping
|
|
|
|
# drop-down menu that uses similar pattern for videos (see
|
|
|
|
# https://github.com/rg3/youtube-dl/issues/11594).
|
|
|
|
container = self._search_regex(
|
|
|
|
r'(?s)(<div[^>]+class=["\']container.+)', webpage,
|
|
|
|
'container', default=webpage)
|
|
|
|
|
|
|
|
entries = self._extract_entries(container)
|
2015-02-20 01:15:19 +09:00
|
|
|
|
|
|
|
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'))
|
2016-02-19 01:29:17 +09:00
|
|
|
|
|
|
|
|
|
|
|
class PornHubPlaylistIE(PornHubPlaylistBaseIE):
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)'
|
|
|
|
_TESTS = [{
|
2017-01-04 07:32:18 +09:00
|
|
|
'url': 'http://www.pornhub.com/playlist/4667351',
|
2016-02-19 01:29:17 +09:00
|
|
|
'info_dict': {
|
2017-01-04 07:32:18 +09:00
|
|
|
'id': '4667351',
|
|
|
|
'title': 'Nataly Hot',
|
2016-02-19 01:29:17 +09:00
|
|
|
},
|
2017-01-04 07:32:18 +09:00
|
|
|
'playlist_mincount': 2,
|
2016-02-19 01:29:17 +09:00
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
|
|
class PornHubUserVideosIE(PornHubPlaylistBaseIE):
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?pornhub\.com/users/(?P<id>[^/]+)/videos'
|
|
|
|
_TESTS = [{
|
2016-03-28 03:50:46 +09:00
|
|
|
'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
|
2016-02-19 01:29:17 +09:00
|
|
|
'info_dict': {
|
2016-03-28 03:50:46 +09:00
|
|
|
'id': 'zoe_ph',
|
2016-02-19 01:29:17 +09:00
|
|
|
},
|
2016-03-28 03:50:46 +09:00
|
|
|
'playlist_mincount': 171,
|
|
|
|
}, {
|
|
|
|
'url': 'http://www.pornhub.com/users/rushandlia/videos',
|
|
|
|
'only_matching': True,
|
2016-02-19 01:29:17 +09:00
|
|
|
}]
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
user_id = self._match_id(url)
|
|
|
|
|
2016-03-28 03:50:46 +09:00
|
|
|
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)
|