X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/6d835d4d6903cf5e18ad01844736929e06d16004..9988a0c7b237b58c40b7fe12d1ffcd1a9b0e5741:/youtube_dl/extractor/tnaflix.py?ds=sidebyside diff --git a/youtube_dl/extractor/tnaflix.py b/youtube_dl/extractor/tnaflix.py index 4956f85..b3573c6 100644 --- a/youtube_dl/extractor/tnaflix.py +++ b/youtube_dl/extractor/tnaflix.py @@ -3,82 +3,325 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( - parse_duration, fix_xml_ampersands, + float_or_none, + int_or_none, + parse_duration, + str_to_int, + unescapeHTML, + xpath_text, ) -class TNAFlixIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/(?P[\w-]+)/(?P[\w-]+)/video(?P\d+)' +class TNAFlixNetworkBaseIE(InfoExtractor): + # May be overridden in descendants if necessary + _CONFIG_REGEX = [ + r'flashvars\.config\s*=\s*escape\("(?P[^"]+)"', + r']+name="config\d?" value="(?P[^"]+)"', + r'config\s*=\s*(["\'])(?P(?:https?:)?//(?:(?!\1).)+)\1', + ] + _HOST = 'tna' + _VKEY_SUFFIX = '' + _TITLE_REGEX = r']+name="title" value="([^"]+)"' + _DESCRIPTION_REGEX = r']+name="description" value="([^"]+)"' + _UPLOADER_REGEX = r']+name="username" value="([^"]+)"' + _VIEW_COUNT_REGEX = None + _COMMENT_COUNT_REGEX = None + _AVERAGE_RATING_REGEX = None + _CATEGORIES_REGEX = r']*>\s*]+class="infoTitle"[^>]*>Categories:\s*]+class="listView"[^>]*>(.+?)\s*' - _TITLE_REGEX = None - _DESCRIPTION_REGEX = r'

([^<]+)

' - _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"' + def _extract_thumbnails(self, flix_xml): - _TEST = { - 'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878', - 'md5': 'ecf3498417d09216374fc5907f9c6ec0', - 'info_dict': { - 'id': '553878', - 'display_id': 'Carmella-Decesare-striptease', - 'ext': 'mp4', - 'title': 'Carmella Decesare - striptease', - 'description': '', - 'thumbnail': 're:https?://.*\.jpg$', - 'duration': 91, - 'age_limit': 18, - } - } + 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') - display_id = mobj.group('display_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) - title = self._html_search_regex( - self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage) - description = self._html_search_regex( - self._DESCRIPTION_REGEX, webpage, 'description', fatal=False, default='') + cfg_url = self._proto_relative_url(self._html_search_regex( + self._CONFIG_REGEX, webpage, 'flashvars.config', default=None, + group='url'), 'http:') - age_limit = self._rta_search(webpage) + 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)) - duration = self._html_search_meta('duration', webpage, 'duration', default=None) - if duration: - duration = parse_duration(duration[1:]) + cfg_xml = self._download_xml( + cfg_url, display_id, 'Downloading metadata', + transform_source=fix_xml_ampersands, headers={'Referer': url}) - cfg_url = self._html_search_regex( - self._CONFIG_REGEX, webpage, 'flashvars.config') + formats = [] - cfg_xml = self._download_xml( - cfg_url, display_id, note='Downloading metadata', - transform_source=fix_xml_ampersands) + def extract_video_url(vl): + # Any URL modification now results in HTTP Error 403: Forbidden + return unescapeHTML(vl.text) - thumbnail = cfg_xml.find('./startThumb').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'), + }) - formats = [] for item in cfg_xml.findall('./quality/item'): - video_url = re.sub('speed=\d+', 'speed=', item.find('videoLink').text) - format_id = item.find('res').text - fmt = { - 'url': video_url, + 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, - } - m = re.search(r'^(\d+)', format_id) - if m: - fmt['height'] = int(m.group(1)) - formats.append(fmt) + '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\d+)' + + _TITLE_REGEX = r'([^<]+)' + + _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']+?src=(["\'])(?P(?:https?:)?//player\.(?:tna|emp)flix\.com/video/\d+)\1', + webpage)] + + +class TNAEMPFlixBaseIE(TNAFlixNetworkBaseIE): + _DESCRIPTION_REGEX = r'(?s)>Description:]+>(.+?)<' + _UPLOADER_REGEX = r'by\s*]+\bhref=["\']/profile/[^>]+>([^<]+)<' + _CATEGORIES_REGEX = r'(?s)]*>Categories:(.+?)' + + +class TNAFlixIE(TNAEMPFlixBaseIE): + _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P[^/]+)/video(?P\d+)' + + _TITLE_REGEX = r'(.+?) - (?:TNAFlix Porn Videos|TNAFlix\.com)' + + _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.+?)-|[^/]+/(?P[^/]+)/video)(?P[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$', + 'duration': 83, + 'age_limit': 18, + 'uploader': 'cwbike', + 'categories': ['Amateur', 'Anal', 'Fisting', 'Home made', 'Solo'], + } + }, { + 'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html', + 'only_matching': True, + }, { + 'url': 'https://www.empflix.com/amateur-porn/Amateur-Finger-Fuck/video33051', + 'only_matching': True, + }] + + +class MovieFapIE(TNAFlixNetworkBaseIE): + _VALID_URL = r'https?://(?:www\.)?moviefap\.com/videos/(?P[0-9a-f]+)/(?P[^/]+)\.html' + + _VIEW_COUNT_REGEX = r'
Views\s*([\d,.]+)' + _COMMENT_COUNT_REGEX = r']+id="comCount"[^>]*>([\d,.]+)' + _AVERAGE_RATING_REGEX = r'Current Rating\s*
\s*([\d.]+)' + _CATEGORIES_REGEX = r'(?s)]+id="vid_info"[^>]*>\s*]*>.+?(.*?)
' + + _TESTS = [{ + # normal, multi-format video + 'url': 'http://www.moviefap.com/videos/be9867c9416c19f54a4a/experienced-milf-amazing-handjob.html', + 'md5': '26624b4e2523051b550067d547615906', + 'info_dict': { + 'id': 'be9867c9416c19f54a4a', + 'display_id': 'experienced-milf-amazing-handjob', + 'ext': 'mp4', + 'title': 'Experienced MILF Amazing Handjob', + 'description': 'Experienced MILF giving an Amazing Handjob', + 'thumbnail': r're:https?://.*\.jpg$', + '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'], + } + }]