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

from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
    fix_xml_ampersands,
    float_or_none,
    int_or_none,
    parse_duration,
    str_to_int,
    unescapeHTML,
    xpath_text,
)


class TNAFlixNetworkBaseIE(InfoExtractor):
    # May be overridden in descendants if necessary
    _CONFIG_REGEX = [
        r'flashvars\.config\s*=\s*escape\("([^"]+)"',
        r'<input[^>]+name="config\d?" value="([^"]+)"',
    ]
    _HOST = 'tna'
    _VKEY_SUFFIX = ''
    _TITLE_REGEX = r'<input[^>]+name="title" value="([^"]+)"'
    _DESCRIPTION_REGEX = r'<input[^>]+name="description" value="([^"]+)"'
    _UPLOADER_REGEX = r'<input[^>]+name="username" value="([^"]+)"'
    _VIEW_COUNT_REGEX = None
    _COMMENT_COUNT_REGEX = None
    _AVERAGE_RATING_REGEX = None
    _CATEGORIES_REGEX = r'<li[^>]*>\s*<span[^>]+class="infoTitle"[^>]*>Categories:</span>\s*<span[^>]+class="listView"[^>]*>(.+?)</span>\s*</li>'

    def _extract_thumbnails(self, flix_xml):

        def get_child(elem, names):
            for name in names:
                child = elem.find(name)
                if child is not None:
                    return child

        timeline = get_child(flix_xml, ['timeline', 'rolloverBarImage'])
        if timeline is None:
            return

        pattern_el = get_child(timeline, ['imagePattern', 'pattern'])
        if pattern_el is None or not pattern_el.text:
            return

        first_el = get_child(timeline, ['imageFirst', 'first'])
        last_el = get_child(timeline, ['imageLast', 'last'])
        if first_el is None or last_el is None:
            return

        first_text = first_el.text
        last_text = last_el.text
        if not first_text.isdigit() or not last_text.isdigit():
            return

        first = int(first_text)
        last = int(last_text)
        if first > last:
            return

        width = int_or_none(xpath_text(timeline, './imageWidth', 'thumbnail width'))
        height = int_or_none(xpath_text(timeline, './imageHeight', 'thumbnail height'))

        return [{
            'url': self._proto_relative_url(pattern_el.text.replace('#', compat_str(i)), 'http:'),
            'width': width,
            'height': height,
        } for i in range(first, last + 1)]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id')
        for display_id_key in ('display_id', 'display_id_2'):
            if display_id_key in mobj.groupdict():
                display_id = mobj.group(display_id_key)
                if display_id:
                    break
        else:
            display_id = video_id

        webpage = self._download_webpage(url, display_id)

        cfg_url = self._proto_relative_url(self._html_search_regex(
            self._CONFIG_REGEX, webpage, 'flashvars.config', default=None), 'http:')

        if not cfg_url:
            inputs = self._hidden_inputs(webpage)
            cfg_url = ('https://cdn-fck.%sflix.com/%sflix/%s%s.fid?key=%s&VID=%s&premium=1&vip=1&alpha'
                       % (self._HOST, self._HOST, inputs['vkey'], self._VKEY_SUFFIX, inputs['nkey'], video_id))

        cfg_xml = self._download_xml(
            cfg_url, display_id, 'Downloading metadata',
            transform_source=fix_xml_ampersands)

        formats = []

        def extract_video_url(vl):
            # Any URL modification now results in HTTP Error 403: Forbidden
            return unescapeHTML(vl.text)

        video_link = cfg_xml.find('./videoLink')
        if video_link is not None:
            formats.append({
                'url': extract_video_url(video_link),
                'ext': xpath_text(cfg_xml, './videoConfig/type', 'type', default='flv'),
            })

        for item in cfg_xml.findall('./quality/item'):
            video_link = item.find('./videoLink')
            if video_link is None:
                continue
            res = item.find('res')
            format_id = None if res is None else res.text
            height = int_or_none(self._search_regex(
                r'^(\d+)[pP]', format_id, 'height', default=None))
            formats.append({
                'url': self._proto_relative_url(extract_video_url(video_link), 'http:'),
                'format_id': format_id,
                'height': height,
            })

        self._sort_formats(formats)

        thumbnail = self._proto_relative_url(
            xpath_text(cfg_xml, './startThumb', 'thumbnail'), 'http:')
        thumbnails = self._extract_thumbnails(cfg_xml)

        title = None
        if self._TITLE_REGEX:
            title = self._html_search_regex(
                self._TITLE_REGEX, webpage, 'title', default=None)
        if not title:
            title = self._og_search_title(webpage)

        age_limit = self._rta_search(webpage) or 18

        duration = parse_duration(self._html_search_meta(
            'duration', webpage, 'duration', default=None))

        def extract_field(pattern, name):
            return self._html_search_regex(pattern, webpage, name, default=None) if pattern else None

        description = extract_field(self._DESCRIPTION_REGEX, 'description')
        uploader = extract_field(self._UPLOADER_REGEX, 'uploader')
        view_count = str_to_int(extract_field(self._VIEW_COUNT_REGEX, 'view count'))
        comment_count = str_to_int(extract_field(self._COMMENT_COUNT_REGEX, 'comment count'))
        average_rating = float_or_none(extract_field(self._AVERAGE_RATING_REGEX, 'average rating'))

        categories_str = extract_field(self._CATEGORIES_REGEX, 'categories')
        categories = [c.strip() for c in categories_str.split(',')] if categories_str is not None else []

        return {
            'id': video_id,
            'display_id': display_id,
            'title': title,
            'description': description,
            'thumbnail': thumbnail,
            'thumbnails': thumbnails,
            'duration': duration,
            'age_limit': age_limit,
            'uploader': uploader,
            'view_count': view_count,
            'comment_count': comment_count,
            'average_rating': average_rating,
            'categories': categories,
            'formats': formats,
        }


class TNAFlixNetworkEmbedIE(TNAFlixNetworkBaseIE):
    _VALID_URL = r'https?://player\.(?:tna|emp)flix\.com/video/(?P<id>\d+)'

    _TITLE_REGEX = r'<title>([^<]+)</title>'

    _TESTS = [{
        'url': 'https://player.tnaflix.com/video/6538',
        'info_dict': {
            'id': '6538',
            'display_id': '6538',
            'ext': 'mp4',
            'title': 'Educational xxx video',
            'thumbnail': r're:https?://.*\.jpg$',
            'age_limit': 18,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        'url': 'https://player.empflix.com/video/33051',
        'only_matching': True,
    }]

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


class TNAEMPFlixBaseIE(TNAFlixNetworkBaseIE):
    _DESCRIPTION_REGEX = r'(?s)>Description:</[^>]+>(.+?)<'
    _UPLOADER_REGEX = r'<span>by\s*<a[^>]+\bhref=["\']/profile/[^>]+>([^<]+)<'
    _CATEGORIES_REGEX = r'(?s)<span[^>]*>Categories:</span>(.+?)</div>'


class TNAFlixIE(TNAEMPFlixBaseIE):
    _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'

    _TITLE_REGEX = r'<title>(.+?) - (?:TNAFlix Porn Videos|TNAFlix\.com)</title>'

    _TESTS = [{
        # anonymous uploader, no categories
        'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
        'md5': '7e569419fe6d69543d01e6be22f5f7c4',
        'info_dict': {
            'id': '553878',
            'display_id': 'Carmella-Decesare-striptease',
            'ext': 'mp4',
            'title': 'Carmella Decesare - striptease',
            'thumbnail': r're:https?://.*\.jpg$',
            'duration': 91,
            'age_limit': 18,
            'categories': ['Porn Stars'],
        }
    }, {
        # non-anonymous uploader, categories
        'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538',
        'md5': '0f5d4d490dbfd117b8607054248a07c0',
        'info_dict': {
            'id': '6538',
            'display_id': 'Educational-xxx-video',
            'ext': 'mp4',
            'title': 'Educational xxx video',
            'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8',
            'thumbnail': r're:https?://.*\.jpg$',
            'duration': 164,
            'age_limit': 18,
            'uploader': 'bobwhite39',
            'categories': list,
        }
    }, {
        'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
        'only_matching': True,
    }]


class EMPFlixIE(TNAEMPFlixBaseIE):
    _VALID_URL = r'https?://(?:www\.)?empflix\.com/(?:videos/(?P<display_id>.+?)-|[^/]+/(?P<display_id_2>[^/]+)/video)(?P<id>[0-9]+)'

    _HOST = 'emp'
    _VKEY_SUFFIX = '-1'

    _TESTS = [{
        'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
        'md5': 'bc30d48b91a7179448a0bda465114676',
        'info_dict': {
            'id': '33051',
            'display_id': 'Amateur-Finger-Fuck',
            'ext': 'mp4',
            'title': 'Amateur Finger Fuck',
            'description': 'Amateur solo finger fucking.',
            'thumbnail': r're:https?://.*\.jpg$',
            'duration': 83,
            'age_limit': 18,
            'uploader': 'cwbike',
            'categories': ['Amateur', 'Anal', 'Fisting', 'Home made', 'Solo'],
        }
    }, {
        'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
        'only_matching': True,
    }, {
        'url': 'https://www.empflix.com/amateur-porn/Amateur-Finger-Fuck/video33051',
        'only_matching': True,
    }]


class MovieFapIE(TNAFlixNetworkBaseIE):
    _VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P<id>[0-9a-f]+)/(?P<display_id>[^/]+)\.html'

    _VIEW_COUNT_REGEX = r'<br>Views\s*<strong>([\d,.]+)</strong>'
    _COMMENT_COUNT_REGEX = r'<span[^>]+id="comCount"[^>]*>([\d,.]+)</span>'
    _AVERAGE_RATING_REGEX = r'Current Rating\s*<br>\s*<strong>([\d.]+)</strong>'
    _CATEGORIES_REGEX = r'(?s)<div[^>]+id="vid_info"[^>]*>\s*<div[^>]*>.+?</div>(.*?)<br>'

    _TESTS = [{
        # normal, multi-format video
        'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html',
        'md5': '26624b4e2523051b550067d547615906',
        'info_dict': {
            'id': 'be9867c9416c19f54a4a',
            'display_id': 'experienced-milf-amazing-handjob',
            'ext': 'mp4',
            'title': 'Experienced MILF Amazing Handjob',
            'description': 'Experienced MILF giving an Amazing Handjob',
            'thumbnail': r're:https?://.*\.jpg$',
            'age_limit': 18,
            'uploader': 'darvinfred06',
            'view_count': int,
            'comment_count': int,
            'average_rating': float,
            'categories': ['Amateur', 'Masturbation', 'Mature', 'Flashing'],
        }
    }, {
        # quirky single-format case where the extension is given as fid, but the video is really an flv
        'url': 'http://www.moviefap.com/videos/e5da0d3edce5404418f5/jeune-couple-russe.html',
        'md5': 'fa56683e291fc80635907168a743c9ad',
        'info_dict': {
            'id': 'e5da0d3edce5404418f5',
            'display_id': 'jeune-couple-russe',
            'ext': 'flv',
            'title': 'Jeune Couple Russe',
            'description': 'Amateur',
            'thumbnail': r're:https?://.*\.jpg$',
            'age_limit': 18,
            'uploader': 'whiskeyjar',
            'view_count': int,
            'comment_count': int,
            'average_rating': float,
            'categories': ['Amateur', 'Teen'],
        }
    }]
Commit	Line	Data
1dba4a21	1	from __future__ import unicode_literals
	2
	3	import re
	4
	5	from .common import InfoExtractor
d16154d1	6	from ..compat import compat_str
1dba4a21	7	from ..utils import (
eb833b7f	8	fix_xml_ampersands,
d16154d1 S	9	float_or_none,
	10	int_or_none,
	11	parse_duration,
	12	str_to_int,
6b18a24e	13	unescapeHTML,
d16154d1	14	xpath_text,
1dba4a21	15	)
1dba4a21	16
eb833b7f	17
d16154d1 S	18	class TNAFlixNetworkBaseIE(InfoExtractor):
	19	# May be overridden in descendants if necessary
	20	_CONFIG_REGEX = [
	21	r'flashvars\.config\s=\sescape\("([^"]+)"',
	22	r'<input[^>]+name="config\d?" value="([^"]+)"',
ed5a637d	23	]
91055238 S	24	_HOST = 'tna'
91055238 S	25	_VKEY_SUFFIX = ''
d16154d1 S	26	_TITLE_REGEX = r'<input[^>]+name="title" value="([^"]+)"'
	27	_DESCRIPTION_REGEX = r'<input[^>]+name="description" value="([^"]+)"'
	28	_UPLOADER_REGEX = r'<input[^>]+name="username" value="([^"]+)"'
	29	_VIEW_COUNT_REGEX = None
	30	_COMMENT_COUNT_REGEX = None
	31	_AVERAGE_RATING_REGEX = None
	32	_CATEGORIES_REGEX = r'<li[^>]>\s<span[^>]+class="infoTitle"[^>]>Categories:</span>\s<span[^>]+class="listView"[^>]>(.+?)</span>\s</li>'
	33
	34	def _extract_thumbnails(self, flix_xml):
	35
	36	def get_child(elem, names):
	37	for name in names:
	38	child = elem.find(name)
	39	if child is not None:
	40	return child
	41
	42	timeline = get_child(flix_xml, ['timeline', 'rolloverBarImage'])
	43	if timeline is None:
	44	return
	45
	46	pattern_el = get_child(timeline, ['imagePattern', 'pattern'])
	47	if pattern_el is None or not pattern_el.text:
	48	return
	49
	50	first_el = get_child(timeline, ['imageFirst', 'first'])
	51	last_el = get_child(timeline, ['imageLast', 'last'])
	52	if first_el is None or last_el is None:
	53	return
	54
	55	first_text = first_el.text
	56	last_text = last_el.text
	57	if not first_text.isdigit() or not last_text.isdigit():
	58	return
	59
	60	first = int(first_text)
	61	last = int(last_text)
	62	if first > last:
	63	return
	64
	65	width = int_or_none(xpath_text(timeline, './imageWidth', 'thumbnail width'))
	66	height = int_or_none(xpath_text(timeline, './imageHeight', 'thumbnail height'))
	67
	68	return [{
	69	'url': self._proto_relative_url(pattern_el.text.replace('#', compat_str(i)), 'http:'),
	70	'width': width,
	71	'height': height,
	72	} for i in range(first, last + 1)]
1dba4a21	73
	74	def _real_extract(self, url):
	75	mobj = re.match(self._VALID_URL, url)
	76	video_id = mobj.group('id')
b7785cf1 S	77	for display_id_key in ('display_id', 'display_id_2'):
	78	if display_id_key in mobj.groupdict():
	79	display_id = mobj.group(display_id_key)
	80	if display_id:
	81	break
	82	else:
	83	display_id = video_id
1dba4a21	84
	85	webpage = self._download_webpage(url, display_id)
	86
68f705ca	87	cfg_url = self._proto_relative_url(self._html_search_regex(
2f2fcf1a S	88	self._CONFIG_REGEX, webpage, 'flashvars.config', default=None), 'http:')
	89
	90	if not cfg_url:
	91	inputs = self._hidden_inputs(webpage)
91055238 S	92	cfg_url = ('https://cdn-fck.%sflix.com/%sflix/%s%s.fid?key=%s&VID=%s&premium=1&vip=1&alpha'
91055238 S	93	% (self._HOST, self._HOST, inputs['vkey'], self._VKEY_SUFFIX, inputs['nkey'], video_id))
eb833b7f S	94
eb833b7f S	95	cfg_xml = self._download_xml(
d16154d1	96	cfg_url, display_id, 'Downloading metadata',
eb833b7f S	97	transform_source=fix_xml_ampersands)
eb833b7f S	98
1dba4a21	99	formats = []
d16154d1 S	100
d16154d1 S	101	def extract_video_url(vl):
dbb25af6 S	102	# Any URL modification now results in HTTP Error 403: Forbidden
dbb25af6 S	103	return unescapeHTML(vl.text)
d16154d1 S	104
	105	video_link = cfg_xml.find('./videoLink')
	106	if video_link is not None:
	107	formats.append({
	108	'url': extract_video_url(video_link),
	109	'ext': xpath_text(cfg_xml, './videoConfig/type', 'type', default='flv'),
	110	})
	111
eb833b7f	112	for item in cfg_xml.findall('./quality/item'):
d16154d1 S	113	video_link = item.find('./videoLink')
	114	if video_link is None:
	115	continue
	116	res = item.find('res')
	117	format_id = None if res is None else res.text
	118	height = int_or_none(self._search_regex(
	119	r'^(\d+)[pP]', format_id, 'height', default=None))
	120	formats.append({
	121	'url': self._proto_relative_url(extract_video_url(video_link), 'http:'),
1dba4a21	122	'format_id': format_id,
d16154d1 S	123	'height': height,
	124	})
	125
1dba4a21	126	self._sort_formats(formats)
5f6a1245	127
d16154d1 S	128	thumbnail = self._proto_relative_url(
	129	xpath_text(cfg_xml, './startThumb', 'thumbnail'), 'http:')
	130	thumbnails = self._extract_thumbnails(cfg_xml)
	131
a1aadd09 S	132	title = None
	133	if self._TITLE_REGEX:
	134	title = self._html_search_regex(
	135	self._TITLE_REGEX, webpage, 'title', default=None)
	136	if not title:
	137	title = self._og_search_title(webpage)
d16154d1	138
8fab6248	139	age_limit = self._rta_search(webpage) or 18
d16154d1 S	140
	141	duration = parse_duration(self._html_search_meta(
	142	'duration', webpage, 'duration', default=None))
	143
	144	def extract_field(pattern, name):
	145	return self._html_search_regex(pattern, webpage, name, default=None) if pattern else None
	146
	147	description = extract_field(self._DESCRIPTION_REGEX, 'description')
	148	uploader = extract_field(self._UPLOADER_REGEX, 'uploader')
	149	view_count = str_to_int(extract_field(self._VIEW_COUNT_REGEX, 'view count'))
	150	comment_count = str_to_int(extract_field(self._COMMENT_COUNT_REGEX, 'comment count'))
	151	average_rating = float_or_none(extract_field(self._AVERAGE_RATING_REGEX, 'average rating'))
	152
	153	categories_str = extract_field(self._CATEGORIES_REGEX, 'categories')
568d2f78	154	categories = [c.strip() for c in categories_str.split(',')] if categories_str is not None else []
d16154d1	155
1dba4a21	156	return {
	157	'id': video_id,
	158	'display_id': display_id,
1dba4a21	159	'title': title,
eb833b7f	160	'description': description,
1dba4a21	161	'thumbnail': thumbnail,
d16154d1	162	'thumbnails': thumbnails,
eb833b7f S	163	'duration': duration,
eb833b7f S	164	'age_limit': age_limit,
d16154d1 S	165	'uploader': uploader,
	166	'view_count': view_count,
	167	'comment_count': comment_count,
	168	'average_rating': average_rating,
	169	'categories': categories,
eb833b7f	170	'formats': formats,
1dba4a21	171	}
d16154d1 S	172
d16154d1 S	173
d6e9c270 S	174	class TNAFlixNetworkEmbedIE(TNAFlixNetworkBaseIE):
	175	_VALID_URL = r'https?://player\.(?:tna\|emp)flix\.com/video/(?P<id>\d+)'
	176
	177	_TITLE_REGEX = r'<title>([^<]+)</title>'
	178
	179	_TESTS = [{
	180	'url': 'https://player.tnaflix.com/video/6538',
	181	'info_dict': {
	182	'id': '6538',
	183	'display_id': '6538',
	184	'ext': 'mp4',
	185	'title': 'Educational xxx video',
ec85ded8	186	'thumbnail': r're:https?://.*\.jpg$',
d6e9c270 S	187	'age_limit': 18,
	188	},
	189	'params': {
	190	'skip_download': True,
	191	},
	192	}, {
	193	'url': 'https://player.empflix.com/video/33051',
	194	'only_matching': True,
	195	}]
	196
63719a8a S	197	@staticmethod
	198	def _extract_urls(webpage):
	199	return [url for _, url in re.findall(
	200	r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.(?:tna\|emp)flix\.com/video/\d+)\1',
	201	webpage)]
	202
d6e9c270	203
8cfbcfab S	204	class TNAEMPFlixBaseIE(TNAFlixNetworkBaseIE):
	205	_DESCRIPTION_REGEX = r'(?s)>Description:</[^>]+>(.+?)<'
	206	_UPLOADER_REGEX = r'<span>by\s*<a[^>]+\bhref=["\']/profile/[^>]+>([^<]+)<'
	207	_CATEGORIES_REGEX = r'(?s)<span[^>]*>Categories:</span>(.+?)</div>'
	208
	209
	210	class TNAFlixIE(TNAEMPFlixBaseIE):
d16154d1 S	211	_VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
d16154d1 S	212
b47a7501	213	_TITLE_REGEX = r'<title>(.+?) - (?:TNAFlix Porn Videos\|TNAFlix\.com)</title>'
d16154d1 S	214
	215	_TESTS = [{
	216	# anonymous uploader, no categories
	217	'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
8cfbcfab	218	'md5': '7e569419fe6d69543d01e6be22f5f7c4',
d16154d1 S	219	'info_dict': {
	220	'id': '553878',
	221	'display_id': 'Carmella-Decesare-striptease',
	222	'ext': 'mp4',
	223	'title': 'Carmella Decesare - striptease',
ec85ded8	224	'thumbnail': r're:https?://.*\.jpg$',
d16154d1 S	225	'duration': 91,
d16154d1 S	226	'age_limit': 18,
568d2f78	227	'categories': ['Porn Stars'],
d16154d1 S	228	}
	229	}, {
	230	# non-anonymous uploader, categories
	231	'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538',
6b18a24e	232	'md5': '0f5d4d490dbfd117b8607054248a07c0',
d16154d1 S	233	'info_dict': {
	234	'id': '6538',
	235	'display_id': 'Educational-xxx-video',
6b18a24e	236	'ext': 'mp4',
d16154d1 S	237	'title': 'Educational xxx video',
d16154d1 S	238	'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8',
ec85ded8	239	'thumbnail': r're:https?://.*\.jpg$',
d16154d1 S	240	'duration': 164,
	241	'age_limit': 18,
	242	'uploader': 'bobwhite39',
8cfbcfab	243	'categories': list,
d16154d1 S	244	}
	245	}, {
	246	'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632',
	247	'only_matching': True,
	248	}]
	249
	250
8cfbcfab	251	class EMPFlixIE(TNAEMPFlixBaseIE):
b7785cf1	252	_VALID_URL = r'https?://(?:www\.)?empflix\.com/(?:videos/(?P<display_id>.+?)-\|[^/]+/(?P<display_id_2>[^/]+)/video)(?P<id>[0-9]+)'
d16154d1	253
91055238 S	254	_HOST = 'emp'
91055238 S	255	_VKEY_SUFFIX = '-1'
d16154d1 S	256
	257	_TESTS = [{
	258	'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
8cfbcfab	259	'md5': 'bc30d48b91a7179448a0bda465114676',
d16154d1 S	260	'info_dict': {
	261	'id': '33051',
	262	'display_id': 'Amateur-Finger-Fuck',
	263	'ext': 'mp4',
	264	'title': 'Amateur Finger Fuck',
	265	'description': 'Amateur solo finger fucking.',
ec85ded8	266	'thumbnail': r're:https?://.*\.jpg$',
d16154d1 S	267	'duration': 83,
	268	'age_limit': 18,
	269	'uploader': 'cwbike',
	270	'categories': ['Amateur', 'Anal', 'Fisting', 'Home made', 'Solo'],
	271	}
	272	}, {
	273	'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
	274	'only_matching': True,
b7785cf1 S	275	}, {
	276	'url': 'https://www.empflix.com/amateur-porn/Amateur-Finger-Fuck/video33051',
	277	'only_matching': True,
d16154d1 S	278	}]
	279
	280
	281	class MovieFapIE(TNAFlixNetworkBaseIE):
	282	_VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P<id>[0-9a-f]+)/(?P<display_id>[^/]+)\.html'
	283
	284	_VIEW_COUNT_REGEX = r'<br>Views\s*<strong>([\d,.]+)</strong>'
	285	_COMMENT_COUNT_REGEX = r'<span[^>]+id="comCount"[^>]*>([\d,.]+)</span>'
	286	_AVERAGE_RATING_REGEX = r'Current Rating\s<br>\s<strong>([\d.]+)</strong>'
	287	_CATEGORIES_REGEX = r'(?s)<div[^>]+id="vid_info"[^>]>\s<div[^>]>.+?</div>(.?)<br>'
	288
	289	_TESTS = [{
	290	# normal, multi-format video
	291	'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html',
	292	'md5': '26624b4e2523051b550067d547615906',
	293	'info_dict': {
	294	'id': 'be9867c9416c19f54a4a',
	295	'display_id': 'experienced-milf-amazing-handjob',
	296	'ext': 'mp4',
	297	'title': 'Experienced MILF Amazing Handjob',
	298	'description': 'Experienced MILF giving an Amazing Handjob',
ec85ded8	299	'thumbnail': r're:https?://.*\.jpg$',
d16154d1 S	300	'age_limit': 18,
	301	'uploader': 'darvinfred06',
	302	'view_count': int,
	303	'comment_count': int,
	304	'average_rating': float,
	305	'categories': ['Amateur', 'Masturbation', 'Mature', 'Flashing'],
	306	}
	307	}, {
	308	# quirky single-format case where the extension is given as fid, but the video is really an flv
	309	'url': 'http://www.moviefap.com/videos/e5da0d3edce5404418f5/jeune-couple-russe.html',
	310	'md5': 'fa56683e291fc80635907168a743c9ad',
	311	'info_dict': {
	312	'id': 'e5da0d3edce5404418f5',
	313	'display_id': 'jeune-couple-russe',
	314	'ext': 'flv',
	315	'title': 'Jeune Couple Russe',
	316	'description': 'Amateur',
ec85ded8	317	'thumbnail': r're:https?://.*\.jpg$',
d16154d1 S	318	'age_limit': 18,
	319	'uploader': 'whiskeyjar',
	320	'view_count': int,
	321	'comment_count': int,
	322	'average_rating': float,
	323	'categories': ['Amateur', 'Teen'],
	324	}
	325	}]