diff --git a/yt_dlp/extractor/tnaflix.py b/yt_dlp/extractor/tnaflix.py index 8cbfeb7fb..eceaadb30 100644 --- a/yt_dlp/extractor/tnaflix.py +++ b/yt_dlp/extractor/tnaflix.py @@ -1,3 +1,5 @@ +import re + from .common import InfoExtractor from ..compat import compat_str from ..utils import ( @@ -7,6 +9,7 @@ from ..utils import ( parse_duration, str_to_int, unescapeHTML, + url_basename, xpath_text, ) @@ -18,9 +21,6 @@ class TNAFlixNetworkBaseIE(InfoExtractor): r']+name="config\d?" value="(?P[^"]+)"', r'config\s*=\s*(["\'])(?P(?:https?:)?//(?:(?!\1).)+)\1', ] - _HOST = 'tna' - _VIDEO_XML_URL = 'https://www.tnaflix.com/cdn/cdn.php?file={}.fid&key={}&VID={}&nomp4=1&catID=0&rollover=1&startThumb=12&embed=0&utm_source=0&multiview=0&premium=1&country=0user=0&vip=1&cd=0&ref=0&alpha' - _VKEY_SUFFIX = '' _TITLE_REGEX = r']+name="title" value="([^"]+)"' _DESCRIPTION_REGEX = r']+name="description" value="([^"]+)"' _UPLOADER_REGEX = r']+name="username" value="([^"]+)"' @@ -71,11 +71,7 @@ class TNAFlixNetworkBaseIE(InfoExtractor): def _real_extract(self, url): mobj = self._match_valid_url(url) - video_id = mobj.group('id') - - def extract_field(pattern, name): - return self._html_search_regex(pattern, webpage, name, default=None) if pattern else None - + video_id, host = mobj.group('id', 'host') for display_id_key in ('display_id', 'display_id_2'): if display_id_key in mobj.groupdict(): display_id = mobj.group(display_id_key) @@ -86,122 +82,138 @@ class TNAFlixNetworkBaseIE(InfoExtractor): webpage = self._download_webpage(url, display_id) + # check for MovieFap-style config cfg_url = self._proto_relative_url(self._html_search_regex( self._CONFIG_REGEX, webpage, 'flashvars.config', default=None, group='url'), 'http:') + query = {} - if not cfg_url: - vkey = extract_field(r']+\bid="vkey"\b[^>]+\bvalue="([^"]+)"', 'vkey') - nkey = extract_field(r']+\bid="nkey"\b[^>]+\bvalue="([^"]+)"', 'nkey') - vid = extract_field(r']+\bid="VID"\b[^>]+\bvalue="([^"]+)"', 'vid') - if vkey and nkey and vid: - cfg_url = self._proto_relative_url(self._VIDEO_XML_URL.format(vkey, nkey, vid), 'http:') - + # check for TNAFlix-style config 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, headers={'Referer': url}) - - 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, + if inputs.get('vkey') and inputs.get('nkey'): + cfg_url = f'https://www.{host}.com/cdn/cdn.php' + query.update({ + 'file': inputs['vkey'], + 'key': inputs['nkey'], + 'VID': video_id, + 'premium': '1', + 'vip': '1', + 'alpha': '', + }) + + formats, json_ld = [], {} + + # TNAFlix and MovieFap extraction + if cfg_url: + cfg_xml = self._download_xml( + cfg_url, display_id, 'Downloading metadata', + transform_source=fix_xml_ampersands, headers={'Referer': url}, query=query) + + 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, + }) + + thumbnails = self._extract_thumbnails(cfg_xml) or [] + thumbnails.append({ + 'url': self._proto_relative_url(xpath_text(cfg_xml, './startThumb', 'thumbnail'), 'http:') }) - 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)) - - 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')) + # check for EMPFlix-style JSON and extract + else: + player = self._download_json( + f'http://www.{host}.com/ajax/video-player/{video_id}', video_id, + headers={'Referer': url}).get('html', '') + for mobj in re.finditer(r'\d+)' + _VALID_URL = r'https?://player\.(?Ptnaflix|empflix)\.com/video/(?P\d+)' _EMBED_REGEX = [r']+?src=(["\'])(?P(?:https?:)?//player\.(?:tna|emp)flix\.com/video/\d+)\1'] - _TITLE_REGEX = r'([^<]+)' - _TESTS = [{ 'url': 'https://player.tnaflix.com/video/6538', 'info_dict': { 'id': '6538', 'display_id': '6538', 'ext': 'mp4', - 'title': 'Educational xxx video', + 'title': 'Educational xxx video (G Spot)', + 'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8', 'thumbnail': r're:https?://.*\.jpg$', 'age_limit': 18, + 'duration': 164, + 'uploader': 'bobwhite39', + 'categories': list, }, 'params': { 'skip_download': True, }, }, { - 'url': 'https://player.empflix.com/video/33051', + 'url': 'http://player.empflix.com/video/33051', 'only_matching': True, }] + def _real_extract(self, url): + mobj = self._match_valid_url(url) + video_id, host = mobj.group('id', 'host') + return self.url_result(f'http://www.{host}.com/category/{video_id}/video{video_id}') + class TNAEMPFlixBaseIE(TNAFlixNetworkBaseIE): _DESCRIPTION_REGEX = r'(?s)>Description:]+>(.+?)<' @@ -210,7 +222,7 @@ class TNAEMPFlixBaseIE(TNAFlixNetworkBaseIE): class TNAFlixIE(TNAEMPFlixBaseIE): - _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P[^/]+)/video(?P\d+)' + _VALID_URL = r'https?://(?:www\.)?(?Ptnaflix)\.com/[^/]+/(?P[^/]+)/video(?P\d+)' _TITLE_REGEX = r'(.+?) - (?:TNAFlix Porn Videos|TNAFlix\.com)' @@ -226,17 +238,17 @@ class TNAFlixIE(TNAEMPFlixBaseIE): 'thumbnail': r're:https?://.*\.jpg$', 'duration': 91, 'age_limit': 18, - 'categories': ['Porn Stars'], + 'categories': list, } }, { # non-anonymous uploader, categories 'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538', - 'md5': '0f5d4d490dbfd117b8607054248a07c0', + 'md5': 'add5a9fa7f4da53d3e9d0845ac58f20c', 'info_dict': { 'id': '6538', 'display_id': 'Educational-xxx-video', 'ext': 'mp4', - 'title': 'Educational xxx video', + 'title': 'Educational xxx video (G Spot)', 'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8', 'thumbnail': r're:https?://.*\.jpg$', 'duration': 164, @@ -251,14 +263,11 @@ class TNAFlixIE(TNAEMPFlixBaseIE): class EMPFlixIE(TNAEMPFlixBaseIE): - _VALID_URL = r'https?://(?:www\.)?empflix\.com/(?:videos/(?P.+?)-|[^/]+/(?P[^/]+)/video)(?P[0-9]+)' - - _HOST = 'emp' - _VKEY_SUFFIX = '-1' + _VALID_URL = r'https?://(?:www\.)?(?Pempflix)\.com/(?:videos/(?P.+?)-|[^/]+/(?P[^/]+)/video)(?P[0-9]+)' _TESTS = [{ - 'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html', - 'md5': 'bc30d48b91a7179448a0bda465114676', + 'url': 'http://www.empflix.com/amateur-porn/Amateur-Finger-Fuck/video33051', + 'md5': 'd761c7b26601bd14476cd9512f2654fc', 'info_dict': { 'id': '33051', 'display_id': 'Amateur-Finger-Fuck', @@ -268,20 +277,20 @@ class EMPFlixIE(TNAEMPFlixBaseIE): 'thumbnail': r're:https?://.*\.jpg$', 'duration': 83, 'age_limit': 18, - 'uploader': 'cwbike', - 'categories': ['Amateur', 'Anal', 'Fisting', 'Home made', 'Solo'], + 'uploader': None, + 'categories': list, } }, { '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', + 'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html', 'only_matching': True, }] class MovieFapIE(TNAFlixNetworkBaseIE): - _VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P[0-9a-f]+)/(?P[^/]+)\.html' + _VALID_URL = r'https?://(?:www\.)?(?Pmoviefap)\.com/videos/(?P[0-9a-f]+)/(?P[^/]+)\.html' _VIEW_COUNT_REGEX = r'
Views\s*([\d,.]+)' _COMMENT_COUNT_REGEX = r']+id="comCount"[^>]*>([\d,.]+)' @@ -323,5 +332,6 @@ class MovieFapIE(TNAFlixNetworkBaseIE): 'comment_count': int, 'average_rating': float, 'categories': ['Amateur', 'Teen'], - } + }, + 'skip': 'This video does not exist', }]