From ae7246e7d57654381fb629be46662f8e4ded615f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 1 Sep 2014 01:08:19 +0700 Subject: [PATCH] [sunporno] Extract all formats and metadata --- youtube_dl/extractor/sunporno.py | 31 +++++++++++++++++++++---------- 1 file changed, 21 insertions(+), 10 deletions(-) diff --git a/youtube_dl/extractor/sunporno.py b/youtube_dl/extractor/sunporno.py index 2a193dee3..c7a46eb71 100644 --- a/youtube_dl/extractor/sunporno.py +++ b/youtube_dl/extractor/sunporno.py @@ -6,6 +6,8 @@ from ..utils import ( parse_duration, int_or_none, + qualities, + determine_ext, ) @@ -19,6 +21,7 @@ class SunPornoIE(InfoExtractor): 'ext': 'flv', 'title': 'md5:0a400058e8105d39e35c35e7c5184164', 'description': 'md5:a31241990e1bd3a64e72ae99afb325fb', + 'thumbnail': 're:^https?://.*\.jpg$', 'duration': 302, } } @@ -29,29 +32,37 @@ def _real_extract(self, url): webpage = self._download_webpage(url, video_id) - video_url = self._html_search_regex( - r'videoSource\s*=\s*\'([^<]*)', webpage, 'title') - - description = self._html_search_regex( - r'([^<]+)', webpage, 'title') + description = self._html_search_meta('description', webpage, 'description') thumbnail = self._html_search_regex( - r'poster="([^"]*)"', webpage, 'thumbnail', fatal=False) + r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False) duration = parse_duration(self._search_regex( r'Duration: (\d+:\d+)', webpage, 'duration', fatal=False)) view_count = int_or_none(self._html_search_regex( r'(\d+)', webpage, 'view count', fatal=False)) + comment_count = int_or_none(self._html_search_regex( + r'(\d+) Comments?', webpage, 'comment count', fatal=False)) + + formats = [] + quality = qualities(['mp4', 'flv']) + for video_url in re.findall(r'