X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/848723ea972c09f28787db91d8c06e98a274ab89..201856721e6959e772b5e5ddee42d4d75d966703:/youtube_dl/extractor/fourtube.py diff --git a/youtube_dl/extractor/fourtube.py b/youtube_dl/extractor/fourtube.py index 8db7fc6..be4e813 100644 --- a/youtube_dl/extractor/fourtube.py +++ b/youtube_dl/extractor/fourtube.py @@ -3,20 +3,123 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_b64decode, + compat_str, + compat_urllib_parse_unquote, + compat_urlparse, +) from ..utils import ( - compat_urllib_request, - unified_strdate, - str_to_int, + int_or_none, parse_duration, + parse_iso8601, + str_or_none, + str_to_int, + try_get, + unified_timestamp, + url_or_none, ) -from youtube_dl.utils import clean_html -class FourTubeIE(InfoExtractor): - IE_NAME = '4tube' - _VALID_URL = r'https?://(?:www\.)?4tube\.com/videos/(?P\d+)' +class FourTubeBaseIE(InfoExtractor): + def _extract_formats(self, url, video_id, media_id, sources): + token_url = 'https://%s/%s/desktop/%s' % ( + self._TKN_HOST, media_id, '+'.join(sources)) + + parsed_url = compat_urlparse.urlparse(url) + tokens = self._download_json(token_url, video_id, data=b'', headers={ + 'Origin': '%s://%s' % (parsed_url.scheme, parsed_url.hostname), + 'Referer': url, + }) + formats = [{ + 'url': tokens[format]['token'], + 'format_id': format + 'p', + 'resolution': format + 'p', + 'quality': int(format), + } for format in sources] + self._sort_formats(formats) + return formats + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + kind, video_id, display_id = mobj.group('kind', 'id', 'display_id') + + if kind == 'm' or not display_id: + url = self._URL_TEMPLATE % video_id + + webpage = self._download_webpage(url, video_id) + + title = self._html_search_meta('name', webpage) + timestamp = parse_iso8601(self._html_search_meta( + 'uploadDate', webpage)) + thumbnail = self._html_search_meta('thumbnailUrl', webpage) + uploader_id = self._html_search_regex( + r'', + webpage, 'uploader id', fatal=False) + uploader = self._html_search_regex( + r'', + webpage, 'uploader', fatal=False) + + categories_html = self._search_regex( + r'(?s)>\s*Categories / Tags\s*.*?', + webpage, 'categories', fatal=False) + categories = None + if categories_html: + categories = [ + c.strip() for c in re.findall( + r'(?s)
  • (.*?)', categories_html)] + + view_count = str_to_int(self._search_regex( + r']+itemprop="interactionCount"[^>]+content="UserPlays:([0-9,]+)">', + webpage, 'view count', default=None)) + like_count = str_to_int(self._search_regex( + r']+itemprop="interactionCount"[^>]+content="UserLikes:([0-9,]+)">', + webpage, 'like count', default=None)) + duration = parse_duration(self._html_search_meta('duration', webpage)) + + media_id = self._search_regex( + r']+data-id=(["\'])(?P\d+)\1[^>]+data-quality=', webpage, + 'media id', default=None, group='id') + sources = [ + quality + for _, quality in re.findall(r']+data-quality=(["\'])(.+?)\1', webpage)] + if not (media_id and sources): + player_js = self._download_webpage( + self._search_regex( + r']id=(["\'])playerembed\1[^>]+src=(["\'])(?P.+?)\2', + webpage, 'player JS', group='url'), + video_id, 'Downloading player JS') + params_js = self._search_regex( + r'\$\.ajax\(url,\ opts\);\s*\}\s*\}\)\(([0-9,\[\] ]+)\)', + player_js, 'initialization parameters') + params = self._parse_json('[%s]' % params_js, video_id) + media_id = params[0] + sources = ['%s' % p for p in params[2]] + + formats = self._extract_formats(url, video_id, media_id, sources) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'categories': categories, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'timestamp': timestamp, + 'like_count': like_count, + 'view_count': view_count, + 'duration': duration, + 'age_limit': 18, + } + - _TEST = { +class FourTubeIE(FourTubeBaseIE): + IE_NAME = '4tube' + _VALID_URL = r'https?://(?:(?Pwww|m)\.)?4tube\.com/(?:videos|embed)/(?P\d+)(?:/(?P[^/?#&]+))?' + _URL_TEMPLATE = 'https://www.4tube.com/videos/%s/video' + _TKN_HOST = 'token.4tube.com' + _TESTS = [{ 'url': 'http://www.4tube.com/videos/209733/hot-babe-holly-michaels-gets-her-ass-stuffed-by-black', 'md5': '6516c8ac63b03de06bc8eac14362db4f', 'info_dict': { @@ -26,70 +129,181 @@ class FourTubeIE(InfoExtractor): 'uploader': 'WCP Club', 'uploader_id': 'wcp-club', 'upload_date': '20131031', + 'timestamp': 1383263892, 'duration': 583, - } - } + 'view_count': int, + 'like_count': int, + 'categories': list, + 'age_limit': 18, + }, + }, { + 'url': 'http://www.4tube.com/embed/209733', + 'only_matching': True, + }, { + 'url': 'http://m.4tube.com/videos/209733/hot-babe-holly-michaels-gets-her-ass-stuffed-by-black', + 'only_matching': True, + }] + + +class FuxIE(FourTubeBaseIE): + _VALID_URL = r'https?://(?:(?Pwww|m)\.)?fux\.com/(?:video|embed)/(?P\d+)(?:/(?P[^/?#&]+))?' + _URL_TEMPLATE = 'https://www.fux.com/video/%s/video' + _TKN_HOST = 'token.fux.com' + _TESTS = [{ + 'url': 'https://www.fux.com/video/195359/awesome-fucking-kitchen-ends-cum-swallow', + 'info_dict': { + 'id': '195359', + 'ext': 'mp4', + 'title': 'Awesome fucking in the kitchen ends with cum swallow', + 'uploader': 'alenci2342', + 'uploader_id': 'alenci2342', + 'upload_date': '20131230', + 'timestamp': 1388361660, + 'duration': 289, + 'view_count': int, + 'like_count': int, + 'categories': list, + 'age_limit': 18, + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://www.fux.com/embed/195359', + 'only_matching': True, + }, { + 'url': 'https://www.fux.com/video/195359/awesome-fucking-kitchen-ends-cum-swallow', + 'only_matching': True, + }] + + +class PornTubeIE(FourTubeBaseIE): + _VALID_URL = r'https?://(?:(?Pwww|m)\.)?porntube\.com/(?:videos/(?P[^/]+)_|embed/)(?P\d+)' + _URL_TEMPLATE = 'https://www.porntube.com/videos/video_%s' + _TKN_HOST = 'tkn.porntube.com' + _TESTS = [{ + 'url': 'https://www.porntube.com/videos/teen-couple-doing-anal_7089759', + 'info_dict': { + 'id': '7089759', + 'ext': 'mp4', + 'title': 'Teen couple doing anal', + 'uploader': 'Alexy', + 'uploader_id': '91488', + 'upload_date': '20150606', + 'timestamp': 1433595647, + 'duration': 5052, + 'view_count': int, + 'like_count': int, + 'age_limit': 18, + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://www.porntube.com/videos/squirting-teen-ballerina-ecg_1331406', + 'info_dict': { + 'id': '1331406', + 'ext': 'mp4', + 'title': 'Squirting Teen Ballerina on ECG', + 'uploader': 'Exploited College Girls', + 'uploader_id': '665', + 'channel': 'Exploited College Girls', + 'channel_id': '665', + 'upload_date': '20130920', + 'timestamp': 1379685485, + 'duration': 851, + 'view_count': int, + 'like_count': int, + 'age_limit': 18, + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://www.porntube.com/embed/7089759', + 'only_matching': True, + }, { + 'url': 'https://m.porntube.com/videos/teen-couple-doing-anal_7089759', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) + video_id, display_id = mobj.group('id', 'display_id') - video_id = mobj.group('id') - webpage_url = 'http://www.4tube.com/videos/' + video_id - webpage = self._download_webpage(webpage_url, video_id) - - self.report_extraction(video_id) - - playlist_json = self._html_search_regex(r'var playerConfigPlaylist\s+=\s+([^;]+)', webpage, 'Playlist') - media_id = self._search_regex(r'idMedia:\s*(\d+)', playlist_json, 'Media Id') - sources = self._search_regex(r'sources:\s*\[([^\]]*)\]', playlist_json, 'Sources').split(',') - title = self._search_regex(r'title:\s*"([^"]*)', playlist_json, 'Title') - thumbnail_url = self._search_regex(r'image:\s*"([^"]*)', playlist_json, 'Thumbnail', fatal=False) - - uploader_str = self._search_regex(r'Uploaded by(.*?)', webpage, 'uploader', fatal=False) - mobj = re.search(r'(?P[^<]+)', uploader_str) - (uploader, uploader_id) = (mobj.group('name'), mobj.group('id')) if mobj else (clean_html(uploader_str), None) - - upload_date = None - view_count = None - duration = None - description = self._html_search_meta('description', webpage, 'description') - if description: - upload_date = self._search_regex(r'Published Date: (\d{2} [a-zA-Z]{3} \d{4})', description, 'upload date', - fatal=False) - if upload_date: - upload_date = unified_strdate(upload_date) - view_count = self._search_regex(r'Views: ([\d,\.]+)', description, 'view count', fatal=False) - if view_count: - view_count = str_to_int(view_count) - duration = parse_duration(self._search_regex(r'Length: (\d+m\d+s)', description, 'duration', fatal=False)) - - token_url = "http://tkn.4tube.com/{0}/desktop/{1}".format(media_id, "+".join(sources)) - headers = { - b'Content-Type': b'application/x-www-form-urlencoded', - b'Origin': b'http://www.4tube.com', - } - token_req = compat_urllib_request.Request(token_url, b'{}', headers) - tokens = self._download_json(token_req, video_id) + webpage = self._download_webpage(url, display_id) - formats = [{ - 'url': tokens[format]['token'], - 'format_id': format + 'p', - 'resolution': format + 'p', - 'quality': int(format), - } for format in sources] + video = self._parse_json( + self._search_regex( + r'INITIALSTATE\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', + webpage, 'data', group='value'), video_id, + transform_source=lambda x: compat_urllib_parse_unquote( + compat_b64decode(x).decode('utf-8')))['page']['video'] - self._sort_formats(formats) + title = video['title'] + media_id = video['mediaId'] + sources = [compat_str(e['height']) + for e in video['encodings'] if e.get('height')] + formats = self._extract_formats(url, video_id, media_id, sources) + + thumbnail = url_or_none(video.get('masterThumb')) + uploader = try_get(video, lambda x: x['user']['username'], compat_str) + uploader_id = str_or_none(try_get( + video, lambda x: x['user']['id'], int)) + channel = try_get(video, lambda x: x['channel']['name'], compat_str) + channel_id = str_or_none(try_get( + video, lambda x: x['channel']['id'], int)) + like_count = int_or_none(video.get('likes')) + dislike_count = int_or_none(video.get('dislikes')) + view_count = int_or_none(video.get('playsQty')) + duration = int_or_none(video.get('durationInSeconds')) + timestamp = unified_timestamp(video.get('publishedAt')) return { 'id': video_id, 'title': title, 'formats': formats, - 'thumbnail': thumbnail_url, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'upload_date': upload_date, + 'thumbnail': thumbnail, + 'uploader': uploader or channel, + 'uploader_id': uploader_id or channel_id, + 'channel': channel, + 'channel_id': channel_id, + 'timestamp': timestamp, + 'like_count': like_count, + 'dislike_count': dislike_count, 'view_count': view_count, 'duration': duration, 'age_limit': 18, - 'webpage_url': webpage_url, - } \ No newline at end of file + } + + +class PornerBrosIE(FourTubeBaseIE): + _VALID_URL = r'https?://(?:(?Pwww|m)\.)?pornerbros\.com/(?:videos/(?P[^/]+)_|embed/)(?P\d+)' + _URL_TEMPLATE = 'https://www.pornerbros.com/videos/video_%s' + _TKN_HOST = 'token.pornerbros.com' + _TESTS = [{ + 'url': 'https://www.pornerbros.com/videos/skinny-brunette-takes-big-cock-down-her-anal-hole_181369', + 'md5': '6516c8ac63b03de06bc8eac14362db4f', + 'info_dict': { + 'id': '181369', + 'ext': 'mp4', + 'title': 'Skinny brunette takes big cock down her anal hole', + 'uploader': 'PornerBros HD', + 'uploader_id': 'pornerbros-hd', + 'upload_date': '20130130', + 'timestamp': 1359527401, + 'duration': 1224, + 'view_count': int, + 'categories': list, + 'age_limit': 18, + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://www.pornerbros.com/embed/181369', + 'only_matching': True, + }, { + 'url': 'https://m.pornerbros.com/videos/skinny-brunette-takes-big-cock-down-her-anal-hole_181369', + 'only_matching': True, + }]