[yt-dlp.git] / yt_dlp / extractor / xhamster.py

from __future__ import unicode_literals

import itertools
import re

from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
    clean_html,
    determine_ext,
    dict_get,
    extract_attributes,
    ExtractorError,
    float_or_none,
    int_or_none,
    parse_duration,
    str_or_none,
    try_get,
    unified_strdate,
    url_or_none,
    urljoin,
)


class XHamsterIE(InfoExtractor):
    _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com)'
    _VALID_URL = r'''(?x)
                    https?://
                        (?:.+?\.)?%s/
                        (?:
                            movies/(?P<id>[\dA-Za-z]+)/(?P<display_id>[^/]*)\.html|
                            videos/(?P<display_id_2>[^/]*)-(?P<id_2>[\dA-Za-z]+)
                        )
                    ''' % _DOMAINS
    _TESTS = [{
        'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
        'md5': '98b4687efb1ffd331c4197854dc09e8f',
        'info_dict': {
            'id': '1509445',
            'display_id': 'femaleagent-shy-beauty-takes-the-bait',
            'ext': 'mp4',
            'title': 'FemaleAgent Shy beauty takes the bait',
            'timestamp': 1350194821,
            'upload_date': '20121014',
            'uploader': 'Ruseful2011',
            'duration': 893,
            'age_limit': 18,
        },
    }, {
        'url': 'https://xhamster.com/videos/britney-spears-sexy-booty-2221348?hd=',
        'info_dict': {
            'id': '2221348',
            'display_id': 'britney-spears-sexy-booty',
            'ext': 'mp4',
            'title': 'Britney Spears  Sexy Booty',
            'timestamp': 1379123460,
            'upload_date': '20130914',
            'uploader': 'jojo747400',
            'duration': 200,
            'age_limit': 18,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        # empty seo, unavailable via new URL schema
        'url': 'http://xhamster.com/movies/5667973/.html',
        'info_dict': {
            'id': '5667973',
            'ext': 'mp4',
            'title': '....',
            'timestamp': 1454948101,
            'upload_date': '20160208',
            'uploader': 'parejafree',
            'duration': 72,
            'age_limit': 18,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        # mobile site
        'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111',
        'only_matching': True,
    }, {
        'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
        'only_matching': True,
    }, {
        # This video is visible for marcoalfa123456's friends only
        'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
        'only_matching': True,
    }, {
        # new URL schema
        'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
        'only_matching': True,
    }, {
        'url': 'https://xhamster.one/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
        'only_matching': True,
    }, {
        'url': 'https://xhamster.desi/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
        'only_matching': True,
    }, {
        'url': 'https://xhamster2.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
        'only_matching': True,
    }, {
        'url': 'https://xhamster11.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
        'only_matching': True,
    }, {
        'url': 'https://xhamster26.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
        'only_matching': True,
    }, {
        'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
        'only_matching': True,
    }, {
        'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
        'only_matching': True,
    }, {
        'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id') or mobj.group('id_2')
        display_id = mobj.group('display_id') or mobj.group('display_id_2')

        desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
        webpage, urlh = self._download_webpage_handle(desktop_url, video_id)

        error = self._html_search_regex(
            r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
            webpage, 'error', default=None)
        if error:
            raise ExtractorError(error, expected=True)

        age_limit = self._rta_search(webpage)

        def get_height(s):
            return int_or_none(self._search_regex(
                r'^(\d+)[pP]', s, 'height', default=None))

        initials = self._parse_json(
            self._search_regex(
                (r'window\.initials\s*=\s*({.+?})\s*;\s*</script>',
                 r'window\.initials\s*=\s*({.+?})\s*;'), webpage, 'initials',
                default='{}'),
            video_id, fatal=False)
        if initials:
            video = initials['videoModel']
            title = video['title']
            formats = []
            format_urls = set()
            format_sizes = {}
            sources = try_get(video, lambda x: x['sources'], dict) or {}
            for format_id, formats_dict in sources.items():
                if not isinstance(formats_dict, dict):
                    continue
                download_sources = try_get(sources, lambda x: x['download'], dict) or {}
                for quality, format_dict in download_sources.items():
                    if not isinstance(format_dict, dict):
                        continue
                    format_sizes[quality] = float_or_none(format_dict.get('size'))
                for quality, format_item in formats_dict.items():
                    if format_id == 'download':
                        # Download link takes some time to be generated,
                        # skipping for now
                        continue
                    format_url = format_item
                    format_url = url_or_none(format_url)
                    if not format_url or format_url in format_urls:
                        continue
                    format_urls.add(format_url)
                    formats.append({
                        'format_id': '%s-%s' % (format_id, quality),
                        'url': format_url,
                        'ext': determine_ext(format_url, 'mp4'),
                        'height': get_height(quality),
                        'filesize': format_sizes.get(quality),
                        'http_headers': {
                            'Referer': urlh.geturl(),
                        },
                    })
            xplayer_sources = try_get(
                initials, lambda x: x['xplayerSettings']['sources'], dict)
            if xplayer_sources:
                hls_sources = xplayer_sources.get('hls')
                if isinstance(hls_sources, dict):
                    for hls_format_key in ('url', 'fallback'):
                        hls_url = hls_sources.get(hls_format_key)
                        if not hls_url:
                            continue
                        hls_url = urljoin(url, hls_url)
                        if not hls_url or hls_url in format_urls:
                            continue
                        format_urls.add(hls_url)
                        formats.extend(self._extract_m3u8_formats(
                            hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
                            m3u8_id='hls', fatal=False))
                standard_sources = xplayer_sources.get('standard')
                if isinstance(standard_sources, dict):
                    for format_id, formats_list in standard_sources.items():
                        if not isinstance(formats_list, list):
                            continue
                        for standard_format in formats_list:
                            if not isinstance(standard_format, dict):
                                continue
                            for standard_format_key in ('url', 'fallback'):
                                standard_url = standard_format.get(standard_format_key)
                                if not standard_url:
                                    continue
                                standard_url = urljoin(url, standard_url)
                                if not standard_url or standard_url in format_urls:
                                    continue
                                format_urls.add(standard_url)
                                ext = determine_ext(standard_url, 'mp4')
                                if ext == 'm3u8':
                                    formats.extend(self._extract_m3u8_formats(
                                        standard_url, video_id, 'mp4', entry_protocol='m3u8_native',
                                        m3u8_id='hls', fatal=False))
                                    continue
                                quality = (str_or_none(standard_format.get('quality'))
                                           or str_or_none(standard_format.get('label'))
                                           or '')
                                formats.append({
                                    'format_id': '%s-%s' % (format_id, quality),
                                    'url': standard_url,
                                    'ext': ext,
                                    'height': get_height(quality),
                                    'filesize': format_sizes.get(quality),
                                    'http_headers': {
                                        'Referer': standard_url,
                                    },
                                })
            self._sort_formats(formats)

            categories_list = video.get('categories')
            if isinstance(categories_list, list):
                categories = []
                for c in categories_list:
                    if not isinstance(c, dict):
                        continue
                    c_name = c.get('name')
                    if isinstance(c_name, compat_str):
                        categories.append(c_name)
            else:
                categories = None

            return {
                'id': video_id,
                'display_id': display_id,
                'title': title,
                'description': video.get('description'),
                'timestamp': int_or_none(video.get('created')),
                'uploader': try_get(
                    video, lambda x: x['author']['name'], compat_str),
                'thumbnail': video.get('thumbURL'),
                'duration': int_or_none(video.get('duration')),
                'view_count': int_or_none(video.get('views')),
                'like_count': int_or_none(try_get(
                    video, lambda x: x['rating']['likes'], int)),
                'dislike_count': int_or_none(try_get(
                    video, lambda x: x['rating']['dislikes'], int)),
                'comment_count': int_or_none(video.get('views')),
                'age_limit': age_limit,
                'categories': categories,
                'formats': formats,
            }

        # Old layout fallback

        title = self._html_search_regex(
            [r'<h1[^>]*>([^<]+)</h1>',
             r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
             r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
            webpage, 'title')

        formats = []
        format_urls = set()

        sources = self._parse_json(
            self._search_regex(
                r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources',
                default='{}'),
            video_id, fatal=False)
        for format_id, format_url in sources.items():
            format_url = url_or_none(format_url)
            if not format_url:
                continue
            if format_url in format_urls:
                continue
            format_urls.add(format_url)
            formats.append({
                'format_id': format_id,
                'url': format_url,
                'height': get_height(format_id),
            })

        video_url = self._search_regex(
            [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
             r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
             r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
            webpage, 'video url', group='mp4', default=None)
        if video_url and video_url not in format_urls:
            formats.append({
                'url': video_url,
            })

        self._sort_formats(formats)

        # Only a few videos have an description
        mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
        description = mobj.group(1) if mobj else None

        upload_date = unified_strdate(self._search_regex(
            r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
            webpage, 'upload date', fatal=False))

        uploader = self._html_search_regex(
            r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
            webpage, 'uploader', default='anonymous')

        thumbnail = self._search_regex(
            [r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
             r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
            webpage, 'thumbnail', fatal=False, group='thumbnail')

        duration = parse_duration(self._search_regex(
            [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
             r'Runtime:\s*</span>\s*([\d:]+)'], webpage,
            'duration', fatal=False))

        view_count = int_or_none(self._search_regex(
            r'content=["\']User(?:View|Play)s:(\d+)',
            webpage, 'view count', fatal=False))

        mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
        (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)

        mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
        comment_count = mobj.group('commentcount') if mobj else 0

        categories_html = self._search_regex(
            r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
            'categories', default=None)
        categories = [clean_html(category) for category in re.findall(
            r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None

        return {
            'id': video_id,
            'display_id': display_id,
            'title': title,
            'description': description,
            'upload_date': upload_date,
            'uploader': uploader,
            'thumbnail': thumbnail,
            'duration': duration,
            'view_count': view_count,
            'like_count': int_or_none(like_count),
            'dislike_count': int_or_none(dislike_count),
            'comment_count': int_or_none(comment_count),
            'age_limit': age_limit,
            'categories': categories,
            'formats': formats,
        }


class XHamsterEmbedIE(InfoExtractor):
    _VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
    _TEST = {
        'url': 'http://xhamster.com/xembed.php?video=3328539',
        'info_dict': {
            'id': '3328539',
            'ext': 'mp4',
            'title': 'Pen Masturbation',
            'timestamp': 1406581861,
            'upload_date': '20140728',
            'uploader': 'ManyakisArt',
            'duration': 5,
            'age_limit': 18,
        }
    }

    @staticmethod
    def _extract_urls(webpage):
        return [url for _, url in re.findall(
            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
            webpage)]

    def _real_extract(self, url):
        video_id = self._match_id(url)

        webpage = self._download_webpage(url, video_id)

        video_url = self._search_regex(
            r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id),
            webpage, 'xhamster url', default=None)

        if not video_url:
            vars = self._parse_json(
                self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
                video_id)
            video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))

        return self.url_result(video_url, 'XHamster')


class XHamsterUserIE(InfoExtractor):
    _VALID_URL = r'https?://(?:.+?\.)?%s/users/(?P<id>[^/?#&]+)' % XHamsterIE._DOMAINS
    _TESTS = [{
        # Paginated user profile
        'url': 'https://xhamster.com/users/netvideogirls/videos',
        'info_dict': {
            'id': 'netvideogirls',
        },
        'playlist_mincount': 267,
    }, {
        # Non-paginated user profile
        'url': 'https://xhamster.com/users/firatkaan/videos',
        'info_dict': {
            'id': 'firatkaan',
        },
        'playlist_mincount': 1,
    }]

    def _entries(self, user_id):
        next_page_url = 'https://xhamster.com/users/%s/videos/1' % user_id
        for pagenum in itertools.count(1):
            page = self._download_webpage(
                next_page_url, user_id, 'Downloading page %s' % pagenum)
            for video_tag in re.findall(
                    r'(<a[^>]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)',
                    page):
                video = extract_attributes(video_tag)
                video_url = url_or_none(video.get('href'))
                if not video_url or not XHamsterIE.suitable(video_url):
                    continue
                video_id = XHamsterIE._match_id(video_url)
                yield self.url_result(
                    video_url, ie=XHamsterIE.ie_key(), video_id=video_id)
            mobj = re.search(r'<a[^>]+data-page=["\']next[^>]+>', page)
            if not mobj:
                break
            next_page = extract_attributes(mobj.group(0))
            next_page_url = url_or_none(next_page.get('href'))
            if not next_page_url:
                break

    def _real_extract(self, url):
        user_id = self._match_id(url)
        return self.playlist_result(self._entries(user_id), user_id)
Commit	Line	Data
35409e11 PH	1	from __future__ import unicode_literals
35409e11 PH	2
df228355	3	import itertools
cb10cded PH	4	import re
	5
	6	from .common import InfoExtractor
d852c6bc	7	from ..compat import compat_str
cb10cded	8	from ..utils import (
85552042	9	clean_html,
fea92aa6	10	determine_ext,
065c4b27	11	dict_get,
df228355	12	extract_attributes,
103f8c8d	13	ExtractorError,
cc2db878	14	float_or_none,
ccb079ee	15	int_or_none,
51378d35	16	parse_duration,
cc2db878	17	str_or_none,
fea92aa6	18	try_get,
44731e30	19	unified_strdate,
3052a30d	20	url_or_none,
cc2db878	21	urljoin,
cb10cded PH	22	)
	23
	24
	25	class XHamsterIE(InfoExtractor):
10709fc7	26	_DOMAINS = r'(?:xhamster\.(?:com\|one\|desi)\|xhms\.pro\|xhamster\d+\.com)'
00e5c363 S	27	_VALID_URL = r'''(?x)
00e5c363 S	28	https?://
8945b10f	29	(?:.+?\.)?%s/
00e5c363	30	(?:
6cb30ea5 J	31	movies/(?P<id>[\dA-Za-z]+)/(?P<display_id>[^/]*)\.html\|
6cb30ea5 J	32	videos/(?P<display_id_2>[^/]*)-(?P<id_2>[\dA-Za-z]+)
00e5c363	33	)
8945b10f	34	''' % _DOMAINS
6b43132c	35	_TESTS = [{
8945b10f S	36	'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
8945b10f S	37	'md5': '98b4687efb1ffd331c4197854dc09e8f',
6b43132c S	38	'info_dict': {
6b43132c S	39	'id': '1509445',
8945b10f	40	'display_id': 'femaleagent-shy-beauty-takes-the-bait',
6b43132c S	41	'ext': 'mp4',
6b43132c S	42	'title': 'FemaleAgent Shy beauty takes the bait',
fea92aa6	43	'timestamp': 1350194821,
6b43132c S	44	'upload_date': '20121014',
6b43132c S	45	'uploader': 'Ruseful2011',
51378d35	46	'duration': 893,
6b43132c	47	'age_limit': 18,
ccb079ee	48	},
6b43132c	49	}, {
8945b10f	50	'url': 'https://xhamster.com/videos/britney-spears-sexy-booty-2221348?hd=',
6b43132c S	51	'info_dict': {
6b43132c S	52	'id': '2221348',
8945b10f	53	'display_id': 'britney-spears-sexy-booty',
6b43132c S	54	'ext': 'mp4',
6b43132c S	55	'title': 'Britney Spears Sexy Booty',
fea92aa6	56	'timestamp': 1379123460,
6b43132c S	57	'upload_date': '20130914',
6b43132c S	58	'uploader': 'jojo747400',
51378d35	59	'duration': 200,
6b43132c	60	'age_limit': 18,
5b9aefef	61	},
6b43132c S	62	'params': {
6b43132c S	63	'skip_download': True,
a4690b32	64	},
6b43132c	65	}, {
8945b10f	66	# empty seo, unavailable via new URL schema
6b43132c S	67	'url': 'http://xhamster.com/movies/5667973/.html',
	68	'info_dict': {
	69	'id': '5667973',
	70	'ext': 'mp4',
	71	'title': '....',
fea92aa6	72	'timestamp': 1454948101,
6b43132c S	73	'upload_date': '20160208',
6b43132c S	74	'uploader': 'parejafree',
51378d35	75	'duration': 72,
6b43132c	76	'age_limit': 18,
5b9aefef	77	},
6b43132c S	78	'params': {
	79	'skip_download': True,
	80	},
b271e335 W	81	}, {
	82	# mobile site
	83	'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111',
	84	'only_matching': True,
6b43132c S	85	}, {
	86	'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
	87	'only_matching': True,
103f8c8d S	88	}, {
	89	# This video is visible for marcoalfa123456's friends only
	90	'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
	91	'only_matching': True,
00e5c363 S	92	}, {
	93	# new URL schema
	94	'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
	95	'only_matching': True,
b43c5f47 S	96	}, {
	97	'url': 'https://xhamster.one/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
	98	'only_matching': True,
8945b10f S	99	}, {
	100	'url': 'https://xhamster.desi/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
	101	'only_matching': True,
	102	}, {
	103	'url': 'https://xhamster2.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
	104	'only_matching': True,
10709fc7 S	105	}, {
	106	'url': 'https://xhamster11.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
	107	'only_matching': True,
	108	}, {
	109	'url': 'https://xhamster26.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
	110	'only_matching': True,
8945b10f S	111	}, {
	112	'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
	113	'only_matching': True,
	114	}, {
	115	'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
	116	'only_matching': True,
6cb30ea5 J	117	}, {
	118	'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx',
	119	'only_matching': True,
6b43132c	120	}]
cb10cded	121
5f6a1245	122	def _real_extract(self, url):
cb10cded	123	mobj = re.match(self._VALID_URL, url)
00e5c363 S	124	video_id = mobj.group('id') or mobj.group('id_2')
	125	display_id = mobj.group('display_id') or mobj.group('display_id_2')
	126
b271e335	127	desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
b274e48d	128	webpage, urlh = self._download_webpage_handle(desktop_url, video_id)
cb10cded	129
103f8c8d S	130	error = self._html_search_regex(
	131	r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
	132	webpage, 'error', default=None)
	133	if error:
	134	raise ExtractorError(error, expected=True)
	135
fea92aa6 S	136	age_limit = self._rta_search(webpage)
	137
	138	def get_height(s):
	139	return int_or_none(self._search_regex(
	140	r'^(\d+)[pP]', s, 'height', default=None))
	141
	142	initials = self._parse_json(
	143	self._search_regex(
39e7107d U	144	(r'window\.initials\s=\s({.+?})\s;\s</script>',
39e7107d U	145	r'window\.initials\s=\s({.+?})\s*;'), webpage, 'initials',
fea92aa6 S	146	default='{}'),
	147	video_id, fatal=False)
	148	if initials:
	149	video = initials['videoModel']
	150	title = video['title']
	151	formats = []
cc2db878	152	format_urls = set()
	153	format_sizes = {}
	154	sources = try_get(video, lambda x: x['sources'], dict) or {}
	155	for format_id, formats_dict in sources.items():
fea92aa6 S	156	if not isinstance(formats_dict, dict):
fea92aa6 S	157	continue
cc2db878	158	download_sources = try_get(sources, lambda x: x['download'], dict) or {}
	159	for quality, format_dict in download_sources.items():
	160	if not isinstance(format_dict, dict):
	161	continue
	162	format_sizes[quality] = float_or_none(format_dict.get('size'))
fea92aa6 S	163	for quality, format_item in formats_dict.items():
	164	if format_id == 'download':
	165	# Download link takes some time to be generated,
	166	# skipping for now
	167	continue
cc2db878	168	format_url = format_item
3052a30d	169	format_url = url_or_none(format_url)
cc2db878	170	if not format_url or format_url in format_urls:
fea92aa6	171	continue
cc2db878	172	format_urls.add(format_url)
fea92aa6 S	173	formats.append({
	174	'format_id': '%s-%s' % (format_id, quality),
	175	'url': format_url,
	176	'ext': determine_ext(format_url, 'mp4'),
	177	'height': get_height(quality),
cc2db878	178	'filesize': format_sizes.get(quality),
b274e48d S	179	'http_headers': {
	180	'Referer': urlh.geturl(),
	181	},
fea92aa6	182	})
cc2db878	183	xplayer_sources = try_get(
	184	initials, lambda x: x['xplayerSettings']['sources'], dict)
	185	if xplayer_sources:
	186	hls_sources = xplayer_sources.get('hls')
	187	if isinstance(hls_sources, dict):
	188	for hls_format_key in ('url', 'fallback'):
	189	hls_url = hls_sources.get(hls_format_key)
	190	if not hls_url:
	191	continue
	192	hls_url = urljoin(url, hls_url)
	193	if not hls_url or hls_url in format_urls:
	194	continue
	195	format_urls.add(hls_url)
	196	formats.extend(self._extract_m3u8_formats(
	197	hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
	198	m3u8_id='hls', fatal=False))
	199	standard_sources = xplayer_sources.get('standard')
	200	if isinstance(standard_sources, dict):
	201	for format_id, formats_list in standard_sources.items():
	202	if not isinstance(formats_list, list):
	203	continue
	204	for standard_format in formats_list:
	205	if not isinstance(standard_format, dict):
	206	continue
	207	for standard_format_key in ('url', 'fallback'):
	208	standard_url = standard_format.get(standard_format_key)
	209	if not standard_url:
	210	continue
	211	standard_url = urljoin(url, standard_url)
	212	if not standard_url or standard_url in format_urls:
	213	continue
	214	format_urls.add(standard_url)
	215	ext = determine_ext(standard_url, 'mp4')
	216	if ext == 'm3u8':
	217	formats.extend(self._extract_m3u8_formats(
	218	standard_url, video_id, 'mp4', entry_protocol='m3u8_native',
	219	m3u8_id='hls', fatal=False))
	220	continue
	221	quality = (str_or_none(standard_format.get('quality'))
	222	or str_or_none(standard_format.get('label'))
	223	or '')
	224	formats.append({
	225	'format_id': '%s-%s' % (format_id, quality),
	226	'url': standard_url,
	227	'ext': ext,
	228	'height': get_height(quality),
	229	'filesize': format_sizes.get(quality),
	230	'http_headers': {
	231	'Referer': standard_url,
	232	},
	233	})
54f37eea	234	self._sort_formats(formats)
fea92aa6 S	235
	236	categories_list = video.get('categories')
	237	if isinstance(categories_list, list):
	238	categories = []
	239	for c in categories_list:
	240	if not isinstance(c, dict):
	241	continue
	242	c_name = c.get('name')
	243	if isinstance(c_name, compat_str):
	244	categories.append(c_name)
	245	else:
	246	categories = None
	247
	248	return {
	249	'id': video_id,
	250	'display_id': display_id,
	251	'title': title,
	252	'description': video.get('description'),
	253	'timestamp': int_or_none(video.get('created')),
	254	'uploader': try_get(
	255	video, lambda x: x['author']['name'], compat_str),
	256	'thumbnail': video.get('thumbURL'),
	257	'duration': int_or_none(video.get('duration')),
	258	'view_count': int_or_none(video.get('views')),
	259	'like_count': int_or_none(try_get(
	260	video, lambda x: x['rating']['likes'], int)),
	261	'dislike_count': int_or_none(try_get(
	262	video, lambda x: x['rating']['dislikes'], int)),
	263	'comment_count': int_or_none(video.get('views')),
	264	'age_limit': age_limit,
	265	'categories': categories,
	266	'formats': formats,
	267	}
	268
	269	# Old layout fallback
	270
4395ca2e	271	title = self._html_search_regex(
1a6d9284 S	272	[r'<h1[^>]*>([^<]+)</h1>',
	273	r'<meta[^>]+itemprop=".?caption.?"[^>]+content="(.+?)"',
	274	r'<title[^>]>(.+?)(?:,\s[^,]?\sPorn\s[^,]?:\sxHamster[^<]\| - xHamster\.com)</title>'],
	275	webpage, 'title')
cb10cded	276
d852c6bc S	277	formats = []
	278	format_urls = set()
	279
	280	sources = self._parse_json(
	281	self._search_regex(
	282	r'sources\s:\s({.+?})\s,?\s\n', webpage, 'sources',
	283	default='{}'),
	284	video_id, fatal=False)
	285	for format_id, format_url in sources.items():
3052a30d S	286	format_url = url_or_none(format_url)
3052a30d S	287	if not format_url:
d852c6bc S	288	continue
	289	if format_url in format_urls:
	290	continue
	291	format_urls.add(format_url)
	292	formats.append({
	293	'format_id': format_id,
	294	'url': format_url,
fea92aa6	295	'height': get_height(format_id),
d852c6bc S	296	})
	297
	298	video_url = self._search_regex(
	299	[r'''file\s:\s(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
	300	r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
	301	r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
	302	webpage, 'video url', group='mp4', default=None)
	303	if video_url and video_url not in format_urls:
	304	formats.append({
	305	'url': video_url,
	306	})
	307
	308	self._sort_formats(formats)
	309
4353cf51	310	# Only a few videos have an description
22ff1c4a	311	mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
ccb079ee	312	description = mobj.group(1) if mobj else None
cb10cded	313
4763b624 S	314	upload_date = unified_strdate(self._search_regex(
	315	r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
	316	webpage, 'upload date', fatal=False))
cb10cded	317
3e485224	318	uploader = self._html_search_regex(
a846173d	319	r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
3e485224	320	webpage, 'uploader', default='anonymous')
cb10cded	321
251a44b7	322	thumbnail = self._search_regex(
b271e335 W	323	[r'''["']thumbUrl["']\s:\s(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
b271e335 W	324	r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
c73cdd80	325	webpage, 'thumbnail', fatal=False, group='thumbnail')
ccb079ee	326
51378d35	327	duration = parse_duration(self._search_regex(
d852c6bc S	328	[r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
d852c6bc S	329	r'Runtime:\s</span>\s([\d:]+)'], webpage,
51378d35	330	'duration', fatal=False))
ccb079ee	331
6a16fd4a S	332	view_count = int_or_none(self._search_regex(
	333	r'content=["\']User(?:View\|Play)s:(\d+)',
	334	webpage, 'view count', fatal=False))
ccb079ee	335
a846173d	336	mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
ccb079ee S	337	(like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
	338
	339	mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
	340	comment_count = mobj.group('commentcount') if mobj else 0
cb10cded	341
85552042 S	342	categories_html = self._search_regex(
	343	r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
	344	'categories', default=None)
	345	categories = [clean_html(category) for category in re.findall(
	346	r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
	347
5d0c9754	348	return {
5d0c9754	349	'id': video_id,
d852c6bc	350	'display_id': display_id,
ccb079ee S	351	'title': title,
	352	'description': description,
	353	'upload_date': upload_date,
3e485224	354	'uploader': uploader,
ccb079ee S	355	'thumbnail': thumbnail,
	356	'duration': duration,
	357	'view_count': view_count,
	358	'like_count': int_or_none(like_count),
	359	'dislike_count': int_or_none(dislike_count),
	360	'comment_count': int_or_none(comment_count),
9d92015d	361	'age_limit': age_limit,
85552042	362	'categories': categories,
ccb079ee	363	'formats': formats,
5d0c9754	364	}
0bbba43e S	365
	366
	367	class XHamsterEmbedIE(InfoExtractor):
8945b10f	368	_VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
0bbba43e S	369	_TEST = {
	370	'url': 'http://xhamster.com/xembed.php?video=3328539',
	371	'info_dict': {
	372	'id': '3328539',
	373	'ext': 'mp4',
	374	'title': 'Pen Masturbation',
b271e335	375	'timestamp': 1406581861,
0bbba43e	376	'upload_date': '20140728',
b271e335	377	'uploader': 'ManyakisArt',
0bbba43e S	378	'duration': 5,
	379	'age_limit': 18,
	380	}
	381	}
	382
2bb5b6d0 S	383	@staticmethod
	384	def _extract_urls(webpage):
	385	return [url for _, url in re.findall(
	386	r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
	387	webpage)]
	388
0bbba43e S	389	def _real_extract(self, url):
	390	video_id = self._match_id(url)
	391
	392	webpage = self._download_webpage(url, video_id)
	393
	394	video_url = self._search_regex(
db962528	395	r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]\.html\|videos/[^/]-{0})[^"]*)"'.format(video_id),
065c4b27 S	396	webpage, 'xhamster url', default=None)
	397
	398	if not video_url:
	399	vars = self._parse_json(
	400	self._search_regex(r'vars\s:\s({.+?})\s,\s\n', webpage, 'vars'),
	401	video_id)
	402	video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
0bbba43e	403
25701d5a	404	return self.url_result(video_url, 'XHamster')
df228355 S	405
	406
	407	class XHamsterUserIE(InfoExtractor):
	408	_VALID_URL = r'https?://(?:.+?\.)?%s/users/(?P<id>[^/?#&]+)' % XHamsterIE._DOMAINS
	409	_TESTS = [{
	410	# Paginated user profile
	411	'url': 'https://xhamster.com/users/netvideogirls/videos',
	412	'info_dict': {
	413	'id': 'netvideogirls',
	414	},
	415	'playlist_mincount': 267,
	416	}, {
	417	# Non-paginated user profile
	418	'url': 'https://xhamster.com/users/firatkaan/videos',
	419	'info_dict': {
	420	'id': 'firatkaan',
	421	},
	422	'playlist_mincount': 1,
	423	}]
	424
	425	def _entries(self, user_id):
	426	next_page_url = 'https://xhamster.com/users/%s/videos/1' % user_id
	427	for pagenum in itertools.count(1):
	428	page = self._download_webpage(
	429	next_page_url, user_id, 'Downloading page %s' % pagenum)
	430	for video_tag in re.findall(
	431	r'(<a[^>]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)',
	432	page):
	433	video = extract_attributes(video_tag)
	434	video_url = url_or_none(video.get('href'))
	435	if not video_url or not XHamsterIE.suitable(video_url):
	436	continue
	437	video_id = XHamsterIE._match_id(video_url)
	438	yield self.url_result(
	439	video_url, ie=XHamsterIE.ie_key(), video_id=video_id)
	440	mobj = re.search(r'<a[^>]+data-page=["\']next[^>]+>', page)
	441	if not mobj:
	442	break
	443	next_page = extract_attributes(mobj.group(0))
	444	next_page_url = url_or_none(next_page.get('href'))
	445	if not next_page_url:
	446	break
	447
	448	def _real_extract(self, url):
	449	user_id = self._match_id(url)
	450	return self.playlist_result(self._entries(user_id), user_id)