X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/6d835d4d6903cf5e18ad01844736929e06d16004..70058ce8528073cc636f0b014032b9cde5807cb9:/youtube_dl/extractor/tube8.py diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py index 64a1e90..db93b01 100644 --- a/youtube_dl/extractor/tube8.py +++ b/youtube_dl/extractor/tube8.py @@ -1,93 +1,86 @@ from __future__ import unicode_literals -import json import re -from .common import InfoExtractor from ..utils import ( - compat_urllib_parse_urlparse, - compat_urllib_request, int_or_none, str_to_int, ) -from ..aes import aes_decrypt_text +from .keezmovies import KeezMoviesIE -class Tube8IE(InfoExtractor): +class Tube8IE(KeezMoviesIE): _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P[^/]+)/(?P\d+)' - _TESTS = [ - { - 'url': 'http://www.tube8.com/teen/kasia-music-video/229795/', - 'md5': '44bf12b98313827dd52d35b8706a4ea0', - '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, - } - }, - { - '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, + _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, + 'categories': ['Teen'], + 'tags': ['dancing'], }, - ] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - display_id = mobj.group('display_id') - - req = compat_urllib_request.Request(url) - req.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(req, display_id) + }, { + '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, + }] - flashvars = json.loads(self._html_search_regex( - r'var flashvars\s*=\s*({.+?})', webpage, 'flashvars')) + @staticmethod + def _extract_urls(webpage): + return re.findall( + r']+\bsrc=["\']((?:https?:)?//(?:www\.)?tube8\.com/embed/(?:[^/]+/)+\d+)', + webpage) - video_url = flashvars['video_url'] - if flashvars.get('encrypted') is True: - video_url = aes_decrypt_text(video_url, flashvars['video_title'], 32).decode('utf-8') - path = compat_urllib_parse_urlparse(video_url).path - format_id = '-'.join(path.split('/')[4].split('_')[:2]) + def _real_extract(self, url): + webpage, info = self._extract_info(url) - thumbnail = flashvars.get('image_url') + if not info['title']: + info['title'] = self._html_search_regex( + r'videoTitle\s*=\s*"([^"]+)', webpage, 'title') - title = self._html_search_regex( - r'videotitle\s*=\s*"([^"]+)', webpage, 'title') description = self._html_search_regex( - r'>Description:(.+?)<', webpage, 'description', fatal=False) + r'(?s)Description:\s*
(.+?)
', webpage, 'description', fatal=False) uploader = self._html_search_regex( - r'(?:)?([^<]+)(?:)?', + r'\s*(.+?)\s*<', webpage, 'uploader', fatal=False) - like_count = int_or_none(self._html_search_regex( - r"rupVar\s*=\s*'(\d+)'", webpage, 'like count', fatal=False)) - dislike_count = int_or_none(self._html_search_regex( - r"rdownVar\s*=\s*'(\d+)'", webpage, 'dislike count', fatal=False)) - view_count = self._html_search_regex( - r'Views: ([\d,\.]+)', webpage, 'view count', fatal=False) - if view_count: - view_count = str_to_int(view_count) - comment_count = self._html_search_regex( - r'(\d+)', webpage, 'comment count', fatal=False) - if comment_count: - comment_count = str_to_int(comment_count) + 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:\s*\s*
([\d,\.]+)', + webpage, 'view count', fatal=False)) + comment_count = str_to_int(self._search_regex( + r'(\d+)', + webpage, 'comment count', fatal=False)) + + category = self._search_regex( + r'Category:\s*\s*
\s*]+href=[^>]+>([^<]+)', + webpage, 'category', fatal=False) + categories = [category] if category else None + + tags_str = self._search_regex( + r'(?s)Tags:\s*\s*
(.+?)]+href=[^>]+>([^<]+)', tags_str)] if tags_str else None - return { - 'id': video_id, - 'display_id': display_id, - 'url': video_url, - 'title': title, + info.update({ 'description': description, - 'thumbnail': thumbnail, 'uploader': uploader, - 'format_id': format_id, 'view_count': view_count, 'like_count': like_count, 'dislike_count': dislike_count, 'comment_count': comment_count, - 'age_limit': 18, - } + 'categories': categories, + 'tags': tags, + }) + + return info