[yt-dlp.git] / youtube_dl / extractor / pornhub.py

# coding: utf-8
from __future__ import unicode_literals

import functools
import itertools
import operator
import re

from .common import InfoExtractor
from ..compat import (
    compat_HTTPError,
    compat_str,
    compat_urllib_request,
)
from .openload import PhantomJSwrapper
from ..utils import (
    determine_ext,
    ExtractorError,
    int_or_none,
    NO_DEFAULT,
    orderedSet,
    remove_quotes,
    str_to_int,
    url_or_none,
)


class PornHubBaseIE(InfoExtractor):
    def _download_webpage_handle(self, *args, **kwargs):
        def dl(*args, **kwargs):
            return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs)

        webpage, urlh = dl(*args, **kwargs)

        if any(re.search(p, webpage) for p in (
                r'<body\b[^>]+\bonload=["\']go\(\)',
                r'document\.cookie\s*=\s*["\']RNKEY=',
                r'document\.location\.reload\(true\)')):
            url_or_request = args[0]
            url = (url_or_request.get_full_url()
                   if isinstance(url_or_request, compat_urllib_request.Request)
                   else url_or_request)
            phantom = PhantomJSwrapper(self, required_version='2.0')
            phantom.get(url, html=webpage)
            webpage, urlh = dl(*args, **kwargs)

        return webpage, urlh


class PornHubIE(PornHubBaseIE):
    IE_DESC = 'PornHub and Thumbzilla'
    _VALID_URL = r'''(?x)
                    https?://
                        (?:
                            (?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
                            (?:www\.)?thumbzilla\.com/video/
                        )
                        (?P<id>[\da-z]+)
                    '''
    _TESTS = [{
        'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
        'md5': '1e19b41231a02eba417839222ac9d58e',
        'info_dict': {
            'id': '648719015',
            'ext': 'mp4',
            'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
            'uploader': 'Babes',
            'upload_date': '20130628',
            'duration': 361,
            'view_count': int,
            'like_count': int,
            'dislike_count': int,
            'comment_count': int,
            'age_limit': 18,
            'tags': list,
            'categories': list,
        },
    }, {
        # 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': 'Unknown',
            'upload_date': '20150213',
            'duration': 1753,
            'view_count': int,
            'like_count': int,
            'dislike_count': int,
            'comment_count': int,
            'age_limit': 18,
            'tags': list,
            'categories': list,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        # subtitles
        'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7',
        'info_dict': {
            'id': 'ph5af5fef7c2aa7',
            'ext': 'mp4',
            'title': 'BFFS - Cute Teen Girls Share Cock On the Floor',
            'uploader': 'BFFs',
            'duration': 622,
            'view_count': int,
            'like_count': int,
            'dislike_count': int,
            'comment_count': int,
            'age_limit': 18,
            'tags': list,
            'categories': list,
            'subtitles': {
                'en': [{
                    "ext": 'srt'
                }]
            },
        },
        '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,
    }, {
        'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
        'only_matching': True,
    }, {
        'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933',
        'only_matching': True,
    }]

    @staticmethod
    def _extract_urls(webpage):
        return re.findall(
            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com|net)/embed/[\da-z]+)',
            webpage)

    def _extract_count(self, pattern, webpage, name):
        return str_to_int(self._search_regex(
            pattern, webpage, '%s count' % name, fatal=False))

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        host = mobj.group('host') or 'pornhub.com'
        video_id = mobj.group('id')

        self._set_cookie(host, 'age_verified', '1')

        def dl_webpage(platform):
            self._set_cookie(host, 'platform', platform)
            return self._download_webpage(
                'https://www.%s/view_video.php?viewkey=%s' % (host, video_id),
                video_id, 'Downloading %s webpage' % platform)

        webpage = dl_webpage('pc')

        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')

        video_urls = []
        video_urls_set = set()
        subtitles = {}

        flashvars = self._parse_json(
            self._search_regex(
                r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
            video_id)
        if flashvars:
            subtitle_url = url_or_none(flashvars.get('closedCaptionsFile'))
            if subtitle_url:
                subtitles.setdefault('en', []).append({
                    'url': subtitle_url,
                    'ext': 'srt',
                })
            thumbnail = flashvars.get('image_url')
            duration = int_or_none(flashvars.get('video_duration'))
            media_definitions = flashvars.get('mediaDefinitions')
            if isinstance(media_definitions, list):
                for definition in media_definitions:
                    if not isinstance(definition, dict):
                        continue
                    video_url = definition.get('videoUrl')
                    if not video_url or not isinstance(video_url, compat_str):
                        continue
                    if video_url in video_urls_set:
                        continue
                    video_urls_set.add(video_url)
                    video_urls.append(
                        (video_url, int_or_none(definition.get('quality'))))
        else:
            thumbnail, duration = [None] * 2

        def extract_js_vars(webpage, pattern, default=NO_DEFAULT):
            assignments = self._search_regex(
                pattern, webpage, 'encoded url', default=default)
            if not assignments:
                return {}

            assignments = assignments.split(';')

            js_vars = {}

            def parse_js_value(inp):
                inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
                if '+' in inp:
                    inps = inp.split('+')
                    return functools.reduce(
                        operator.concat, map(parse_js_value, inps))
                inp = inp.strip()
                if inp in js_vars:
                    return js_vars[inp]
                return remove_quotes(inp)

            for assn in assignments:
                assn = assn.strip()
                if not assn:
                    continue
                assn = re.sub(r'var\s+', '', assn)
                vname, value = assn.split('=', 1)
                js_vars[vname] = parse_js_value(value)
            return js_vars

        def add_video_url(video_url):
            v_url = url_or_none(video_url)
            if not v_url:
                return
            if v_url in video_urls_set:
                return
            video_urls.append((v_url, None))
            video_urls_set.add(v_url)

        if not video_urls:
            FORMAT_PREFIXES = ('media', 'quality')
            js_vars = extract_js_vars(
                webpage, r'(var\s+(?:%s)_.+)' % '|'.join(FORMAT_PREFIXES),
                default=None)
            if js_vars:
                for key, format_url in js_vars.items():
                    if any(key.startswith(p) for p in FORMAT_PREFIXES):
                        add_video_url(format_url)
            if not video_urls and re.search(
                    r'<[^>]+\bid=["\']lockedPlayer', webpage):
                raise ExtractorError(
                    'Video %s is locked' % video_id, expected=True)

        if not video_urls:
            js_vars = extract_js_vars(
                dl_webpage('tv'), r'(var.+?mediastring.+?)</script>')
            add_video_url(js_vars['mediastring'])

        for mobj in re.finditer(
                r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1',
                webpage):
            video_url = mobj.group('url')
            if video_url not in video_urls_set:
                video_urls.append((video_url, None))
                video_urls_set.add(video_url)

        upload_date = None
        formats = []
        for video_url, height in video_urls:
            if not upload_date:
                upload_date = self._search_regex(
                    r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
                if upload_date:
                    upload_date = upload_date.replace('/', '')
            ext = determine_ext(video_url)
            if ext == 'mpd':
                formats.extend(self._extract_mpd_formats(
                    video_url, video_id, mpd_id='dash', fatal=False))
                continue
            elif ext == 'm3u8':
                formats.extend(self._extract_m3u8_formats(
                    video_url, video_id, 'mp4', entry_protocol='m3u8_native',
                    m3u8_id='hls', fatal=False))
                continue
            tbr = None
            mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
            if mobj:
                if not height:
                    height = int(mobj.group('height'))
                tbr = int(mobj.group('tbr'))
            formats.append({
                'url': video_url,
                'format_id': '%dp' % height if height else None,
                'height': height,
                'tbr': tbr,
            })
        self._sort_formats(formats)

        video_uploader = self._html_search_regex(
            r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
            webpage, 'uploader', fatal=False)

        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')

        def extract_list(meta_key):
            div = self._search_regex(
                r'(?s)<div[^>]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)</div>'
                % meta_key, webpage, meta_key, default=None)
            if div:
                return re.findall(r'<a[^>]+\bhref=[^>]+>([^<]+)', div)

        return {
            'id': video_id,
            'uploader': video_uploader,
            'upload_date': upload_date,
            'title': title,
            'thumbnail': thumbnail,
            'duration': duration,
            'view_count': view_count,
            'like_count': like_count,
            'dislike_count': dislike_count,
            'comment_count': comment_count,
            'formats': formats,
            'age_limit': 18,
            'tags': extract_list('tags'),
            'categories': extract_list('categories'),
            'subtitles': subtitles,
        }


class PornHubPlaylistBaseIE(PornHubBaseIE):
    def _extract_entries(self, webpage, host):
        # Only process container div with main playlist content skipping
        # drop-down menu that uses similar pattern for videos (see
        # https://github.com/ytdl-org/youtube-dl/issues/11594).
        container = self._search_regex(
            r'(?s)(<div[^>]+class=["\']container.+)', webpage,
            'container', default=webpage)

        return [
            self.url_result(
                'http://www.%s/%s' % (host, 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="([^"]+)"',
                container))
        ]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        host = mobj.group('host')
        playlist_id = mobj.group('id')

        webpage = self._download_webpage(url, playlist_id)

        entries = self._extract_entries(webpage, host)

        playlist = self._parse_json(
            self._search_regex(
                r'(?:playlistObject|PLAYLIST_VIEW)\s*=\s*({.+?});', webpage,
                'playlist', default='{}'),
            playlist_id, fatal=False)
        title = playlist.get('title') or self._search_regex(
            r'>Videos\s+in\s+(.+?)\s+[Pp]laylist<', webpage, 'title', fatal=False)

        return self.playlist_result(
            entries, playlist_id, title, playlist.get('description'))


class PornHubUserIE(PornHubPlaylistBaseIE):
    _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
    _TESTS = [{
        'url': 'https://www.pornhub.com/model/zoe_ph',
        'playlist_mincount': 118,
    }, {
        'url': 'https://www.pornhub.com/pornstar/liz-vicious',
        'info_dict': {
            'id': 'liz-vicious',
        },
        'playlist_mincount': 118,
    }, {
        'url': 'https://www.pornhub.com/users/russianveet69',
        'only_matching': True,
    }, {
        'url': 'https://www.pornhub.com/channels/povd',
        'only_matching': True,
    }, {
        'url': 'https://www.pornhub.com/model/zoe_ph?abc=1',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        user_id = mobj.group('id')
        return self.url_result(
            '%s/videos' % mobj.group('url'), ie=PornHubPagedVideoListIE.ie_key(),
            video_id=user_id)


class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
    @staticmethod
    def _has_more(webpage):
        return re.search(
            r'''(?x)
                <li[^>]+\bclass=["\']page_next|
                <link[^>]+\brel=["\']next|
                <button[^>]+\bid=["\']moreDataBtn
            ''', webpage) is not None

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        host = mobj.group('host')
        item_id = mobj.group('id')

        page = int_or_none(self._search_regex(
            r'\bpage=(\d+)', url, 'page', default=None))

        entries = []
        for page_num in (page, ) if page is not None else itertools.count(1):
            try:
                webpage = self._download_webpage(
                    url, item_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
                raise
            page_entries = self._extract_entries(webpage, host)
            if not page_entries:
                break
            entries.extend(page_entries)
            if not self._has_more(webpage):
                break

        return self.playlist_result(orderedSet(entries), item_id)


class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
    _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)'
    _TESTS = [{
        'url': 'https://www.pornhub.com/model/zoe_ph/videos',
        'only_matching': True,
    }, {
        'url': 'http://www.pornhub.com/users/rushandlia/videos',
        'only_matching': True,
    }, {
        'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos',
        'info_dict': {
            'id': 'pornstar/jenny-blighe/videos',
        },
        'playlist_mincount': 149,
    }, {
        'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos?page=3',
        'info_dict': {
            'id': 'pornstar/jenny-blighe/videos',
        },
        'playlist_mincount': 40,
    }, {
        # default sorting as Top Rated Videos
        'url': 'https://www.pornhub.com/channels/povd/videos',
        'info_dict': {
            'id': 'channels/povd/videos',
        },
        'playlist_mincount': 293,
    }, {
        # Top Rated Videos
        'url': 'https://www.pornhub.com/channels/povd/videos?o=ra',
        'only_matching': True,
    }, {
        # Most Recent Videos
        'url': 'https://www.pornhub.com/channels/povd/videos?o=da',
        'only_matching': True,
    }, {
        # Most Viewed Videos
        'url': 'https://www.pornhub.com/channels/povd/videos?o=vi',
        'only_matching': True,
    }, {
        'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
        'only_matching': True,
    }, {
        # Most Viewed Videos
        'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=mv',
        'only_matching': True,
    }, {
        # Top Rated Videos
        'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=tr',
        'only_matching': True,
    }, {
        # Longest Videos
        'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=lg',
        'only_matching': True,
    }, {
        # Newest Videos
        'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=cm',
        'only_matching': True,
    }, {
        'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/paid',
        'only_matching': True,
    }, {
        'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/fanonly',
        'only_matching': True,
    }, {
        'url': 'https://www.pornhub.com/video',
        'only_matching': True,
    }, {
        'url': 'https://www.pornhub.com/video?page=3',
        'only_matching': True,
    }, {
        'url': 'https://www.pornhub.com/video/search?search=123',
        'only_matching': True,
    }, {
        'url': 'https://www.pornhub.com/categories/teen',
        'only_matching': True,
    }, {
        'url': 'https://www.pornhub.com/categories/teen?page=3',
        'only_matching': True,
    }, {
        'url': 'https://www.pornhub.com/hd',
        'only_matching': True,
    }, {
        'url': 'https://www.pornhub.com/hd?page=3',
        'only_matching': True,
    }, {
        'url': 'https://www.pornhub.com/described-video',
        'only_matching': True,
    }, {
        'url': 'https://www.pornhub.com/described-video?page=2',
        'only_matching': True,
    }, {
        'url': 'https://www.pornhub.com/video/incategories/60fps-1/hd-porn',
        'only_matching': True,
    }, {
        'url': 'https://www.pornhub.com/playlist/44121572',
        'info_dict': {
            'id': 'playlist/44121572',
        },
        'playlist_mincount': 132,
    }, {
        'url': 'https://www.pornhub.com/playlist/4667351',
        'only_matching': True,
    }, {
        'url': 'https://de.pornhub.com/playlist/4667351',
        'only_matching': True,
    }]

    @classmethod
    def suitable(cls, url):
        return (False
                if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
                else super(PornHubPagedVideoListIE, cls).suitable(url))


class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
    _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
    _TESTS = [{
        'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
        'info_dict': {
            'id': 'jenny-blighe',
        },
        'playlist_mincount': 129,
    }, {
        'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload',
        'only_matching': True,
    }]
Commit	Line	Data
6c376029	1	# coding: utf-8
9933b574 PH	2	from __future__ import unicode_literals
9933b574 PH	3
21fbf0f9	4	import functools
34541395	5	import itertools
21fbf0f9	6	import operator
125cfd78	7	import re
	8
	9	from .common import InfoExtractor
1cc79574	10	from ..compat import (
34541395	11	compat_HTTPError,
79367a98	12	compat_str,
278d061a	13	compat_urllib_request,
1cc79574	14	)
278d061a	15	from .openload import PhantomJSwrapper
1cc79574	16	from ..utils import (
b8526c78	17	determine_ext,
50789175	18	ExtractorError,
ed8648a3	19	int_or_none,
0164cd5d	20	NO_DEFAULT,
8f9a477e	21	orderedSet,
e1e35d1a	22	remove_quotes,
0320ddc1	23	str_to_int,
4938c8d5	24	url_or_none,
125cfd78	25	)
125cfd78	26
9933b574	27
71a1f617 S	28	class PornHubBaseIE(InfoExtractor):
	29	def _download_webpage_handle(self, args, *kwargs):
	30	def dl(args, *kwargs):
	31	return super(PornHubBaseIE, self)._download_webpage_handle(args, *kwargs)
	32
	33	webpage, urlh = dl(args, *kwargs)
	34
	35	if any(re.search(p, webpage) for p in (
	36	r'<body\b[^>]+\bonload=["\']go\(\)',
	37	r'document\.cookie\s=\s["\']RNKEY=',
	38	r'document\.location\.reload\(true\)')):
	39	url_or_request = args[0]
	40	url = (url_or_request.get_full_url()
	41	if isinstance(url_or_request, compat_urllib_request.Request)
	42	else url_or_request)
	43	phantom = PhantomJSwrapper(self, required_version='2.0')
	44	phantom.get(url, html=webpage)
	45	webpage, urlh = dl(args, *kwargs)
	46
	47	return webpage, urlh
	48
	49
	50	class PornHubIE(PornHubBaseIE):
bc4b2d75 S	51	IE_DESC = 'PornHub and Thumbzilla'
	52	_VALID_URL = r'''(?x)
	53	https?://
	54	(?:
3430ff9b	55	(?:[^/]+\.)?(?P<host>pornhub\.(?:com\|net))/(?:(?:view_video\.php\|video/show)\?viewkey=\|embed/)\|
bc4b2d75 S	56	(?:www\.)?thumbzilla\.com/video/
bc4b2d75 S	57	)
b52c9ef1	58	(?P<id>[\da-z]+)
bc4b2d75	59	'''
360075e2	60	_TESTS = [{
9933b574	61	'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
ed8648a3	62	'md5': '1e19b41231a02eba417839222ac9d58e',
9933b574	63	'info_dict': {
249efaf4 PH	64	'id': '648719015',
249efaf4 PH	65	'ext': 'mp4',
611c1dd9	66	'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
ed8648a3	67	'uploader': 'Babes',
3661ebf2	68	'upload_date': '20130628',
ed8648a3 S	69	'duration': 361,
	70	'view_count': int,
	71	'like_count': int,
	72	'dislike_count': int,
	73	'comment_count': int,
	74	'age_limit': 18,
6bb05b32 YCH	75	'tags': list,
6bb05b32 YCH	76	'categories': list,
6c376029 S	77	},
	78	}, {
	79	# non-ASCII title
	80	'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002',
	81	'info_dict': {
	82	'id': '1331683002',
	83	'ext': 'mp4',
	84	'title': '重庆婷婷女王足交',
79367a98	85	'uploader': 'Unknown',
3661ebf2	86	'upload_date': '20150213',
6c376029 S	87	'duration': 1753,
	88	'view_count': int,
	89	'like_count': int,
	90	'dislike_count': int,
	91	'comment_count': int,
	92	'age_limit': 18,
6bb05b32 YCH	93	'tags': list,
6bb05b32 YCH	94	'categories': list,
6c376029 S	95	},
	96	'params': {
	97	'skip_download': True,
	98	},
4938c8d5 GF	99	}, {
	100	# subtitles
	101	'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7',
	102	'info_dict': {
	103	'id': 'ph5af5fef7c2aa7',
	104	'ext': 'mp4',
	105	'title': 'BFFS - Cute Teen Girls Share Cock On the Floor',
	106	'uploader': 'BFFs',
	107	'duration': 622,
	108	'view_count': int,
	109	'like_count': int,
	110	'dislike_count': int,
	111	'comment_count': int,
	112	'age_limit': 18,
	113	'tags': list,
	114	'categories': list,
	115	'subtitles': {
	116	'en': [{
	117	"ext": 'srt'
	118	}]
	119	},
	120	},
	121	'params': {
	122	'skip_download': True,
	123	},
360075e2 S	124	}, {
	125	'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
	126	'only_matching': True,
272e4db5	127	}, {
eaaaaec0	128	# removed at the request of cam4.com
272e4db5 S	129	'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862',
272e4db5 S	130	'only_matching': True,
eaaaaec0 S	131	}, {
	132	# removed at the request of the copyright owner
	133	'url': 'http://www.pornhub.com/view_video.php?viewkey=788152859',
	134	'only_matching': True,
	135	}, {
	136	# removed by uploader
	137	'url': 'http://www.pornhub.com/view_video.php?viewkey=ph572716d15a111',
	138	'only_matching': True,
195f0845 S	139	}, {
	140	# private video
	141	'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7',
	142	'only_matching': True,
bc4b2d75 S	143	}, {
	144	'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex',
	145	'only_matching': True,
a99cc4ca S	146	}, {
	147	'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
	148	'only_matching': True,
f97c0991 S	149	}, {
	150	'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933',
	151	'only_matching': True,
360075e2	152	}]
125cfd78	153
b52c9ef1 S	154	@staticmethod
	155	def _extract_urls(webpage):
	156	return re.findall(
3430ff9b	157	r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com\|net)/embed/[\da-z]+)',
b52c9ef1	158	webpage)
65d161c4	159
0320ddc1	160	def _extract_count(self, pattern, webpage, name):
7700207e S	161	return str_to_int(self._search_regex(
7700207e S	162	pattern, webpage, '%s count' % name, fatal=False))
0320ddc1	163
125cfd78	164	def _real_extract(self, url):
3430ff9b S	165	mobj = re.match(self._VALID_URL, url)
	166	host = mobj.group('host') or 'pornhub.com'
	167	video_id = mobj.group('id')
7399ca1f	168
3430ff9b	169	self._set_cookie(host, 'age_verified', '1')
125cfd78	170
9a372f14	171	def dl_webpage(platform):
3430ff9b	172	self._set_cookie(host, 'platform', platform)
9a372f14	173	return self._download_webpage(
2c53c0eb	174	'https://www.%s/view_video.php?viewkey=%s' % (host, video_id),
79367a98	175	video_id, 'Downloading %s webpage' % platform)
9a372f14 S	176
9a372f14 S	177	webpage = dl_webpage('pc')
125cfd78	178
50789175	179	error_msg = self._html_search_regex(
add7d2a0	180	r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)\b(?:removed\|userMessageSection)\b(?:(?!\1).)\1[^>]*>(?P<error>.+?)</div>',
3cb3b600	181	webpage, 'error message', default=None, group='error')
50789175 PH	182	if error_msg:
	183	error_msg = re.sub(r'\s+', ' ', error_msg)
	184	raise ExtractorError(
	185	'PornHub said: %s' % error_msg,
	186	expected=True, video_id=video_id)
	187
6c376029 S	188	# video_title from flashvars contains whitespace instead of non-ASCII (see
	189	# http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
	190	# on that anymore.
79367a98	191	title = self._html_search_meta(
6c376029 S	192	'twitter:title', webpage, default=None) or self._search_regex(
	193	(r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)',
	194	r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1',
	195	r'shareTitle\s=\s(["\'])(?P<title>.+?)\1'),
	196	webpage, 'title', group='title')
	197
79367a98 S	198	video_urls = []
79367a98 S	199	video_urls_set = set()
4938c8d5	200	subtitles = {}
79367a98	201
ed8648a3 S	202	flashvars = self._parse_json(
ed8648a3 S	203	self._search_regex(
03442072	204	r'var\s+flashvars_\d+\s=\s({.+?});', webpage, 'flashvars', default='{}'),
ed8648a3 S	205	video_id)
ed8648a3 S	206	if flashvars:
4938c8d5 GF	207	subtitle_url = url_or_none(flashvars.get('closedCaptionsFile'))
	208	if subtitle_url:
	209	subtitles.setdefault('en', []).append({
	210	'url': subtitle_url,
	211	'ext': 'srt',
	212	})
ed8648a3 S	213	thumbnail = flashvars.get('image_url')
ed8648a3 S	214	duration = int_or_none(flashvars.get('video_duration'))
79367a98 S	215	media_definitions = flashvars.get('mediaDefinitions')
	216	if isinstance(media_definitions, list):
	217	for definition in media_definitions:
	218	if not isinstance(definition, dict):
	219	continue
	220	video_url = definition.get('videoUrl')
	221	if not video_url or not isinstance(video_url, compat_str):
	222	continue
	223	if video_url in video_urls_set:
	224	continue
	225	video_urls_set.add(video_url)
	226	video_urls.append(
	227	(video_url, int_or_none(definition.get('quality'))))
ed8648a3	228	else:
79367a98 S	229	thumbnail, duration = [None] * 2
79367a98 S	230
0164cd5d	231	def extract_js_vars(webpage, pattern, default=NO_DEFAULT):
79367a98	232	assignments = self._search_regex(
0164cd5d	233	pattern, webpage, 'encoded url', default=default)
f4134726 S	234	if not assignments:
	235	return {}
	236
	237	assignments = assignments.split(';')
79367a98 S	238
	239	js_vars = {}
	240
	241	def parse_js_value(inp):
	242	inp = re.sub(r'/\(?:(?!\/).)?\/', '', inp)
	243	if '+' in inp:
	244	inps = inp.split('+')
	245	return functools.reduce(
	246	operator.concat, map(parse_js_value, inps))
	247	inp = inp.strip()
	248	if inp in js_vars:
	249	return js_vars[inp]
	250	return remove_quotes(inp)
	251
	252	for assn in assignments:
	253	assn = assn.strip()
	254	if not assn:
	255	continue
	256	assn = re.sub(r'var\s+', '', assn)
	257	vname, value = assn.split('=', 1)
	258	js_vars[vname] = parse_js_value(value)
f4134726	259	return js_vars
79367a98	260
f4134726 S	261	def add_video_url(video_url):
	262	v_url = url_or_none(video_url)
	263	if not v_url:
	264	return
	265	if v_url in video_urls_set:
	266	return
	267	video_urls.append((v_url, None))
	268	video_urls_set.add(v_url)
	269
	270	if not video_urls:
	271	FORMAT_PREFIXES = ('media', 'quality')
	272	js_vars = extract_js_vars(
	273	webpage, r'(var\s+(?:%s)_.+)' % '\|'.join(FORMAT_PREFIXES),
0164cd5d	274	default=None)
f4134726 S	275	if js_vars:
	276	for key, format_url in js_vars.items():
	277	if any(key.startswith(p) for p in FORMAT_PREFIXES):
	278	add_video_url(format_url)
0164cd5d S	279	if not video_urls and re.search(
	280	r'<[^>]+\bid=["\']lockedPlayer', webpage):
	281	raise ExtractorError(
	282	'Video %s is locked' % video_id, expected=True)
f4134726 S	283
	284	if not video_urls:
	285	js_vars = extract_js_vars(
	286	dl_webpage('tv'), r'(var.+?mediastring.+?)</script>')
	287	add_video_url(js_vars['mediastring'])
79367a98 S	288
	289	for mobj in re.finditer(
	290	r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1',
	291	webpage):
	292	video_url = mobj.group('url')
	293	if video_url not in video_urls_set:
	294	video_urls.append((video_url, None))
	295	video_urls_set.add(video_url)
	296
3661ebf2	297	upload_date = None
79367a98 S	298	formats = []
79367a98 S	299	for video_url, height in video_urls:
3661ebf2 S	300	if not upload_date:
	301	upload_date = self._search_regex(
	302	r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
	303	if upload_date:
	304	upload_date = upload_date.replace('/', '')
f4134726 S	305	ext = determine_ext(video_url)
f4134726 S	306	if ext == 'mpd':
b8526c78 S	307	formats.extend(self._extract_mpd_formats(
	308	video_url, video_id, mpd_id='dash', fatal=False))
	309	continue
f4134726 S	310	elif ext == 'm3u8':
	311	formats.extend(self._extract_m3u8_formats(
	312	video_url, video_id, 'mp4', entry_protocol='m3u8_native',
	313	m3u8_id='hls', fatal=False))
	314	continue
79367a98 S	315	tbr = None
	316	mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
	317	if mobj:
	318	if not height:
	319	height = int(mobj.group('height'))
	320	tbr = int(mobj.group('tbr'))
	321	formats.append({
	322	'url': video_url,
	323	'format_id': '%dp' % height if height else None,
	324	'height': height,
	325	'tbr': tbr,
	326	})
	327	self._sort_formats(formats)
ed8648a3	328
0320ddc1	329	video_uploader = self._html_search_regex(
2d4fe594	330	r'(?s)From: .+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user\|channel)s\|model\|pornstar)/\|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
0320ddc1	331	webpage, 'uploader', fatal=False)
125cfd78	332
7700207e S	333	view_count = self._extract_count(
	334	r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
	335	like_count = self._extract_count(
	336	r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
	337	dislike_count = self._extract_count(
	338	r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
0320ddc1	339	comment_count = self._extract_count(
7700207e	340	r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
0320ddc1	341
5dda1ede	342	def extract_list(meta_key):
d2d970d0	343	div = self._search_regex(
5dda1ede S	344	r'(?s)<div[^>]+\bclass=["\'].?\b%sWrapper[^>]>(.+?)</div>'
5dda1ede S	345	% meta_key, webpage, meta_key, default=None)
d2d970d0	346	if div:
5dda1ede	347	return re.findall(r'<a[^>]+\bhref=[^>]+>([^<]+)', div)
6bb05b32	348
125cfd78	349	return {
	350	'id': video_id,
	351	'uploader': video_uploader,
3661ebf2	352	'upload_date': upload_date,
6c376029	353	'title': title,
125cfd78	354	'thumbnail': thumbnail,
ed8648a3	355	'duration': duration,
0320ddc1 S	356	'view_count': view_count,
	357	'like_count': like_count,
	358	'dislike_count': dislike_count,
	359	'comment_count': comment_count,
79367a98	360	'formats': formats,
750e9833	361	'age_limit': 18,
5dda1ede S	362	'tags': extract_list('tags'),
5dda1ede S	363	'categories': extract_list('categories'),
4938c8d5	364	'subtitles': subtitles,
125cfd78	365	}
e66e1a00 S	366
e66e1a00 S	367
71a1f617	368	class PornHubPlaylistBaseIE(PornHubBaseIE):
3430ff9b	369	def _extract_entries(self, webpage, host):
475bcb22 S	370	# Only process container div with main playlist content skipping
475bcb22 S	371	# drop-down menu that uses similar pattern for videos (see
067aa17e	372	# https://github.com/ytdl-org/youtube-dl/issues/11594).
475bcb22 S	373	container = self._search_regex(
	374	r'(?s)(<div[^>]+class=["\']container.+)', webpage,
	375	'container', default=webpage)
	376
40e146aa	377	return [
3a23bae9	378	self.url_result(
3430ff9b	379	'http://www.%s/%s' % (host, video_url),
3a23bae9 S	380	PornHubIE.ie_key(), video_title=title)
	381	for video_url, title in orderedSet(re.findall(
	382	r'href="/?(view_video\.php\?.\bviewkey=[\da-z]+[^"])"[^>]*\s+title="([^"]+)"',
475bcb22	383	container))
40e146aa	384	]
e66e1a00 S	385
e66e1a00 S	386	def _real_extract(self, url):
3430ff9b S	387	mobj = re.match(self._VALID_URL, url)
	388	host = mobj.group('host')
	389	playlist_id = mobj.group('id')
e66e1a00 S	390
	391	webpage = self._download_webpage(url, playlist_id)
	392
3430ff9b	393	entries = self._extract_entries(webpage, host)
e66e1a00 S	394
	395	playlist = self._parse_json(
	396	self._search_regex(
cd138d8b S	397	r'(?:playlistObject\|PLAYLIST_VIEW)\s=\s({.+?});', webpage,
	398	'playlist', default='{}'),
	399	playlist_id, fatal=False)
	400	title = playlist.get('title') or self._search_regex(
	401	r'>Videos\s+in\s+(.+?)\s+[Pp]laylist<', webpage, 'title', fatal=False)
e66e1a00 S	402
e66e1a00 S	403	return self.playlist_result(
cd138d8b	404	entries, playlist_id, title, playlist.get('description'))
40e146aa S	405
40e146aa S	406
21b08463	407	class PornHubUserIE(PornHubPlaylistBaseIE):
9634de17	408	_VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?pornhub\.(?:com\|net)/(?:(?:user\|channel)s\|model\|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]\|/(?!videos)\|$)'
40e146aa	409	_TESTS = [{
21b08463 S	410	'url': 'https://www.pornhub.com/model/zoe_ph',
	411	'playlist_mincount': 118,
	412	}, {
	413	'url': 'https://www.pornhub.com/pornstar/liz-vicious',
40e146aa	414	'info_dict': {
21b08463	415	'id': 'liz-vicious',
40e146aa	416	},
21b08463 S	417	'playlist_mincount': 118,
	418	}, {
	419	'url': 'https://www.pornhub.com/users/russianveet69',
9634de17	420	'only_matching': True,
21b08463 S	421	}, {
21b08463 S	422	'url': 'https://www.pornhub.com/channels/povd',
9634de17 S	423	'only_matching': True,
	424	}, {
	425	'url': 'https://www.pornhub.com/model/zoe_ph?abc=1',
	426	'only_matching': True,
21b08463 S	427	}]
21b08463 S	428
21b08463 S	429	def _real_extract(self, url):
	430	mobj = re.match(self._VALID_URL, url)
	431	user_id = mobj.group('id')
	432	return self.url_result(
9634de17	433	'%s/videos' % mobj.group('url'), ie=PornHubPagedVideoListIE.ie_key(),
21b08463 S	434	video_id=user_id)
	435
	436
	437	class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
4bf568d3 S	438	@staticmethod
	439	def _has_more(webpage):
	440	return re.search(
	441	r'''(?x)
	442	<li[^>]+\bclass=["\']page_next\|
	443	<link[^>]+\brel=["\']next\|
	444	<button[^>]+\bid=["\']moreDataBtn
	445	''', webpage) is not None
	446
21b08463 S	447	def _real_extract(self, url):
	448	mobj = re.match(self._VALID_URL, url)
	449	host = mobj.group('host')
9634de17	450	item_id = mobj.group('id')
21b08463	451
1f7a563a S	452	page = int_or_none(self._search_regex(
	453	r'\bpage=(\d+)', url, 'page', default=None))
	454
21b08463	455	entries = []
1f7a563a	456	for page_num in (page, ) if page is not None else itertools.count(1):
21b08463 S	457	try:
21b08463 S	458	webpage = self._download_webpage(
4bf568d3	459	url, item_id, 'Downloading page %d' % page_num,
21b08463 S	460	query={'page': page_num})
	461	except ExtractorError as e:
	462	if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
	463	break
	464	raise
	465	page_entries = self._extract_entries(webpage, host)
	466	if not page_entries:
	467	break
	468	entries.extend(page_entries)
	469	if not self._has_more(webpage):
	470	break
	471
9634de17	472	return self.playlist_result(orderedSet(entries), item_id)
21b08463 S	473
21b08463 S	474
9634de17 S	475	class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
9634de17 S	476	_VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com\|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)'
21b08463	477	_TESTS = [{
1f7a563a	478	'url': 'https://www.pornhub.com/model/zoe_ph/videos',
21b08463	479	'only_matching': True,
34541395 S	480	}, {
	481	'url': 'http://www.pornhub.com/users/rushandlia/videos',
	482	'only_matching': True,
21b08463 S	483	}, {
	484	'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos',
	485	'info_dict': {
9634de17	486	'id': 'pornstar/jenny-blighe/videos',
21b08463 S	487	},
21b08463 S	488	'playlist_mincount': 149,
1f7a563a S	489	}, {
	490	'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos?page=3',
	491	'info_dict': {
9634de17	492	'id': 'pornstar/jenny-blighe/videos',
1f7a563a S	493	},
1f7a563a S	494	'playlist_mincount': 40,
f66df20c PV	495	}, {
	496	# default sorting as Top Rated Videos
	497	'url': 'https://www.pornhub.com/channels/povd/videos',
	498	'info_dict': {
9634de17	499	'id': 'channels/povd/videos',
f66df20c PV	500	},
	501	'playlist_mincount': 293,
	502	}, {
	503	# Top Rated Videos
	504	'url': 'https://www.pornhub.com/channels/povd/videos?o=ra',
	505	'only_matching': True,
	506	}, {
	507	# Most Recent Videos
	508	'url': 'https://www.pornhub.com/channels/povd/videos?o=da',
	509	'only_matching': True,
	510	}, {
	511	# Most Viewed Videos
	512	'url': 'https://www.pornhub.com/channels/povd/videos?o=vi',
	513	'only_matching': True,
92ded33a S	514	}, {
	515	'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
	516	'only_matching': True,
21b08463 S	517	}, {
	518	# Most Viewed Videos
	519	'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=mv',
	520	'only_matching': True,
	521	}, {
	522	# Top Rated Videos
	523	'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=tr',
	524	'only_matching': True,
	525	}, {
	526	# Longest Videos
	527	'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=lg',
	528	'only_matching': True,
	529	}, {
	530	# Newest Videos
	531	'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=cm',
	532	'only_matching': True,
21b08463 S	533	}, {
	534	'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/paid',
	535	'only_matching': True,
	536	}, {
	537	'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/fanonly',
	538	'only_matching': True,
9634de17 S	539	}, {
	540	'url': 'https://www.pornhub.com/video',
	541	'only_matching': True,
	542	}, {
	543	'url': 'https://www.pornhub.com/video?page=3',
	544	'only_matching': True,
	545	}, {
	546	'url': 'https://www.pornhub.com/video/search?search=123',
	547	'only_matching': True,
	548	}, {
	549	'url': 'https://www.pornhub.com/categories/teen',
	550	'only_matching': True,
	551	}, {
	552	'url': 'https://www.pornhub.com/categories/teen?page=3',
	553	'only_matching': True,
	554	}, {
	555	'url': 'https://www.pornhub.com/hd',
	556	'only_matching': True,
	557	}, {
	558	'url': 'https://www.pornhub.com/hd?page=3',
	559	'only_matching': True,
	560	}, {
	561	'url': 'https://www.pornhub.com/described-video',
	562	'only_matching': True,
	563	}, {
	564	'url': 'https://www.pornhub.com/described-video?page=2',
	565	'only_matching': True,
	566	}, {
	567	'url': 'https://www.pornhub.com/video/incategories/60fps-1/hd-porn',
	568	'only_matching': True,
	569	}, {
	570	'url': 'https://www.pornhub.com/playlist/44121572',
	571	'info_dict': {
	572	'id': 'playlist/44121572',
	573	},
	574	'playlist_mincount': 132,
	575	}, {
	576	'url': 'https://www.pornhub.com/playlist/4667351',
	577	'only_matching': True,
	578	}, {
	579	'url': 'https://de.pornhub.com/playlist/4667351',
	580	'only_matching': True,
40e146aa S	581	}]
40e146aa S	582
21b08463 S	583	@classmethod
	584	def suitable(cls, url):
	585	return (False
9634de17 S	586	if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
9634de17 S	587	else super(PornHubPagedVideoListIE, cls).suitable(url))
21b08463	588
34541395	589
21b08463 S	590	class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
	591	_VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com\|net))/(?:(?:user\|channel)s\|model\|pornstar)/(?P<id>[^/]+)/videos/upload)'
	592	_TESTS = [{
	593	'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
	594	'info_dict': {
	595	'id': 'jenny-blighe',
	596	},
	597	'playlist_mincount': 129,
	598	}, {
	599	'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload',
	600	'only_matching': True,
	601	}]