From 8804f10e6b580db38df7301a174cb48ea374f9eb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 17 Aug 2016 05:46:45 +0700 Subject: [PATCH] [tube8] Modernize --- youtube_dl/extractor/tube8.py | 60 ++++++----------------------------- 1 file changed, 10 insertions(+), 50 deletions(-) diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py index 1d9271d1e..4053f6c21 100644 --- a/youtube_dl/extractor/tube8.py +++ b/youtube_dl/extractor/tube8.py @@ -1,18 +1,13 @@ 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/', @@ -33,47 +28,17 @@ class Tube8IE(InfoExtractor): }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - display_id = mobj.group('display_id') + webpage, info = self._extract_info(url) - req = sanitized_Request(url) - req.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(req, display_id) + if not info['title']: + info['title'] = self._html_search_regex( + r'videoTitle\s*=\s*"([^"]+)', webpage, 'title') - 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)) @@ -86,18 +51,13 @@ def _real_extract(self, url): r'(\d+)', webpage, 'comment count', fatal=False)) - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, + 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, - } + }) + + return info