From 1723edb1a589190b8a91af12bd7dadaa50e26549 Mon Sep 17 00:00:00 2001 From: CkuT Date: Wed, 15 Oct 2014 20:17:07 +0200 Subject: [PATCH] Few improvements --- youtube_dl/extractor/sexykarma.py | 51 +++++++++++++++++++++++++------ 1 file changed, 41 insertions(+), 10 deletions(-) diff --git a/youtube_dl/extractor/sexykarma.py b/youtube_dl/extractor/sexykarma.py index cd2668872..ac7745e74 100644 --- a/youtube_dl/extractor/sexykarma.py +++ b/youtube_dl/extractor/sexykarma.py @@ -2,42 +2,73 @@ from __future__ import unicode_literals from .common import InfoExtractor - +import re +import datetime class SexyKarmaIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?sexykarma\.com/gonewild/video/(?P[a-zA-Z0-9\-]+)(.html)' + _VALID_URL = r'https?://(?:www\.)?sexykarma\.com/gonewild/video/.+\-(?P[a-zA-Z0-9\-]+)(.html)' _TESTS = [{ 'url': 'http://www.sexykarma.com/gonewild/video/taking-a-quick-pee-yHI70cOyIHt.html', 'md5': 'b9798e7d1ef1765116a8f516c8091dbd', 'info_dict': { - 'id': 'taking-a-quick-pee-yHI70cOyIHt', + 'id': 'yHI70cOyIHt', 'ext': 'mp4', 'title': 'Taking a quick pee.', - 'uploader': 'wildginger7', + 'uploader_id': 'wildginger7', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': int, + 'view_count': int, + 'upload_date': '20141007', } }, { 'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html', 'md5': 'dd216c68d29b49b12842b9babe762a5d', 'info_dict': { - 'id': 'pot-pixie-tribute-8Id6EZPbuHf', + 'id': '8Id6EZPbuHf', 'ext': 'mp4', 'title': 'pot_pixie tribute', - 'uploader': 'banffite', + 'uploader_id': 'banffite', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': int, + 'view_count': int, + 'upload_date': '20141013', } }] def _real_extract(self, url): video_id = self._match_id(url) - # TODO more code goes here, for example ... webpage = self._download_webpage(url, video_id) + title = self._html_search_regex(r'

(.*?)', webpage, 'title') - uploader = self._html_search_regex(r'class="aupa">\n*(.*?)', webpage, 'uploader') + uploader_id = self._html_search_regex(r'class="aupa">\n*(.*?)', webpage, 'uploader') url = self._html_search_regex(r'

[\n\s]*Time: [\n\s]*(.+)\n*', webpage, 'duration') + duration = self._to_seconds(str_duration) + + str_views = self._html_search_regex(r'[\n\s]*Views: [\n\s]*(.+)', webpage, 'view_count') + view_count = int(str_views) + # print view_count + + date = self._html_search_regex(r'class="aup">Added: (.*?)', webpage, 'date') + d = datetime.datetime.strptime(date, '%B %d, %Y') + upload_date = d.strftime('%Y%m%d') return { 'id': video_id, 'title': title, - 'uploader': uploader, - 'url': url + 'uploader_id': uploader_id, + 'url': url, + 'thumbnail': thumbnail, + 'duration': duration, + 'view_count': view_count, + 'upload_date': upload_date, } + + def _to_seconds(self, timestr): + seconds= 0 + for part in timestr.split(':'): + seconds= seconds*60 + int(part) + return seconds