X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/bc5059672e222ec4df4fe3983c399c0d0fca84d5..e5a601f21d25b8806d04be9671c8772e331e3bda:/youtube_dl/extractor/tube8.py diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py index 4d9d41d..1d9271d 100644 --- a/youtube_dl/extractor/tube8.py +++ b/youtube_dl/extractor/tube8.py @@ -1,63 +1,103 @@ -import os +from __future__ import unicode_literals + import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( - compat_urllib_parse_urlparse, - compat_urllib_request, -) -from ..aes import ( - aes_decrypt_text + int_or_none, + sanitized_Request, + str_to_int, ) +from ..aes import aes_decrypt_text + class Tube8IE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?Ptube8\.com/[^/]+/[^/]+/(?P[0-9]+)/?)' - _TEST = { - u'url': u'http://www.tube8.com/teen/kasia-music-video/229795/', - u'file': u'229795.mp4', - u'md5': u'e9e0b0c86734e5e3766e653509475db0', - u'info_dict': { - u"description": u"hot teen Kasia grinding", - u"uploader": u"unknown", - u"title": u"Kasia music video", - u"age_limit": 18, + _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P[^/]+)/(?P\d+)' + _TESTS = [{ + 'url': 'http://www.tube8.com/teen/kasia-music-video/229795/', + 'md5': '65e20c48e6abff62ed0c3965fff13a39', + 'info_dict': { + 'id': '229795', + 'display_id': 'kasia-music-video', + 'ext': 'mp4', + 'description': 'hot teen Kasia grinding', + 'uploader': 'unknown', + 'title': 'Kasia music video', + 'age_limit': 18, + 'duration': 230, } - } + }, { + 'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') - url = 'http://www.' + mobj.group('url') + video_id = mobj.group('id') + display_id = mobj.group('display_id') - req = compat_urllib_request.Request(url) + req = sanitized_Request(url) req.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(req, video_id) - - video_title = self._html_search_regex(r'videotitle ="([^"]+)', webpage, u'title') - video_description = self._html_search_regex(r'>Description:(.+?)<', webpage, u'description', fatal=False) - video_uploader = self._html_search_regex(r'>Submitted by:(?:\s|<[^>]*>)*(.+?)<', webpage, u'uploader', fatal=False) - thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, u'thumbnail', fatal=False) - if thumbnail: - thumbnail = thumbnail.replace('\\/', '/') - - video_url = self._html_search_regex(r'"video_url":"([^"]+)', webpage, u'video_url') - if webpage.find('"encrypted":true')!=-1: - password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password') - video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8') - path = compat_urllib_parse_urlparse(video_url).path - extension = os.path.splitext(path)[1][1:] - format = path.split('/')[4].split('_')[:2] - format = "-".join(format) + webpage = self._download_webpage(req, display_id) + + flashvars = self._parse_json( + self._search_regex( + r'flashvars\s*=\s*({.+?});\r?\n', webpage, 'flashvars'), + video_id) + + formats = [] + for key, video_url in flashvars.items(): + if not isinstance(video_url, compat_str) or not video_url.startswith('http'): + continue + height = self._search_regex( + r'quality_(\d+)[pP]', key, 'height', default=None) + if not height: + continue + if flashvars.get('encrypted') is True: + video_url = aes_decrypt_text( + video_url, flashvars['video_title'], 32).decode('utf-8') + formats.append({ + 'url': video_url, + 'format_id': '%sp' % height, + 'height': int(height), + }) + self._sort_formats(formats) + + thumbnail = flashvars.get('image_url') + + title = self._html_search_regex( + r'videoTitle\s*=\s*"([^"]+)', webpage, 'title') + description = self._html_search_regex( + r'>Description:\s*(.+?)\s*<', webpage, 'description', fatal=False) + uploader = self._html_search_regex( + r'\s*(.+?)\s*<', + webpage, 'uploader', fatal=False) + duration = int_or_none(flashvars.get('video_duration')) + + like_count = int_or_none(self._search_regex( + r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False)) + dislike_count = int_or_none(self._search_regex( + r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False)) + view_count = str_to_int(self._search_regex( + r'Views: ([\d,\.]+)\s*', + webpage, 'view count', fatal=False)) + comment_count = str_to_int(self._search_regex( + r'(\d+)', + webpage, 'comment count', fatal=False)) return { 'id': video_id, - 'uploader': video_uploader, - 'title': video_title, + 'display_id': display_id, + 'title': title, + 'description': description, 'thumbnail': thumbnail, - 'description': video_description, - 'url': video_url, - 'ext': extension, - 'format': format, - 'format_id': format, + 'uploader': uploader, + 'duration': duration, + 'view_count': view_count, + 'like_count': like_count, + 'dislike_count': dislike_count, + 'comment_count': comment_count, 'age_limit': 18, + 'formats': formats, }