From ab19b46b88bb54971b973176976d8d189222a6d3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 17 Aug 2016 06:02:12 +0700 Subject: [PATCH] [extremetube] Modernize --- youtube_dl/extractor/extremetube.py | 73 +++++++---------------------- 1 file changed, 16 insertions(+), 57 deletions(-) diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py index 3403581fd..b4fd9334a 100644 --- a/youtube_dl/extractor/extremetube.py +++ b/youtube_dl/extractor/extremetube.py @@ -1,22 +1,17 @@ from __future__ import unicode_literals -import re - -from .common import InfoExtractor -from ..utils import ( - int_or_none, - sanitized_Request, - str_to_int, -) +from ..utils import str_to_int +from .keezmovies import KeezMoviesIE -class ExtremeTubeIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P[^/#?&]+)' +class ExtremeTubeIE(KeezMoviesIE): + _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?:(?P[^/]+)-)(?P\d+)' _TESTS = [{ 'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431', - 'md5': '344d0c6d50e2f16b06e49ca011d8ac69', + 'md5': '1fb9228f5e3332ec8c057d6ac36f33e0', 'info_dict': { - 'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431', + 'id': '652431', + 'display_id': 'music-video-14-british-euro-brit-european-cumshots-swallow', 'ext': 'mp4', 'title': 'Music Video 14 british euro brit european cumshots swallow', 'uploader': 'unknown', @@ -35,58 +30,22 @@ class ExtremeTubeIE(InfoExtractor): }] def _real_extract(self, url): - video_id = self._match_id(url) + webpage, info = self._extract_info(url) - req = sanitized_Request(url) - req.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(req, video_id) + if not info['title']: + info['title'] = self._search_regex( + r']+title="([^"]+)"[^>]*>', webpage, 'title') - video_title = self._html_search_regex( - r'

]*?title="([^"]+)"[^>]*>', webpage, 'title') uploader = self._html_search_regex( r'Uploaded by:\s*\s*(.+?)\s*', webpage, 'uploader', fatal=False) - view_count = str_to_int(self._html_search_regex( + view_count = str_to_int(self._search_regex( r'Views:\s*\s*([\d,\.]+)', webpage, 'view count', fatal=False)) - flash_vars = self._parse_json( - self._search_regex( - r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flash vars'), - video_id) - - formats = [] - for quality_key, video_url in flash_vars.items(): - height = int_or_none(self._search_regex( - r'quality_(\d+)[pP]$', quality_key, 'height', default=None)) - if not height: - continue - f = { - 'url': video_url, - } - mobj = re.search( - r'/(?P\d{3,4})[pP]_(?P\d+)[kK]_\d+', video_url) - if mobj: - height = int(mobj.group('height')) - bitrate = int(mobj.group('bitrate')) - f.update({ - 'format_id': '%dp-%dk' % (height, bitrate), - 'height': height, - 'tbr': bitrate, - }) - else: - f.update({ - 'format_id': '%dp' % height, - 'height': height, - }) - formats.append(f) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': video_title, - 'formats': formats, + info.update({ 'uploader': uploader, 'view_count': view_count, - 'age_limit': 18, - } + }) + + return info