X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/03342304420e5daeb428ffdcc7bbd2bbfecfa61a..f16b10fb8c485cdd113f9a55a6a2f32c2d81d717:/youtube_dl/extractor/tube8.py diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py index 1d9271d..db93b01 100644 --- a/youtube_dl/extractor/tube8.py +++ b/youtube_dl/extractor/tube8.py @@ -2,17 +2,14 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( int_or_none, - sanitized_Request, 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/', @@ -26,78 +23,64 @@ class Tube8IE(InfoExtractor): 'title': 'Kasia music video', 'age_limit': 18, 'duration': 230, - } + 'categories': ['Teen'], + 'tags': ['dancing'], + }, }, { '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('id') - display_id = mobj.group('display_id') - - req = sanitized_Request(url) - req.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(req, display_id) + @staticmethod + def _extract_urls(webpage): + return re.findall( + r']+\bsrc=["\']((?:https?:)?//(?:www\.)?tube8\.com/embed/(?:[^/]+/)+\d+)', + webpage) - 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) + 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:\s*(.+?)\s*<', webpage, 'description', fatal=False) + r'(?s)Description:\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*', + 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)) - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, + 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 + + info.update({ 'description': description, - 'thumbnail': thumbnail, '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, - } + 'categories': categories, + 'tags': tags, + }) + + return info