From 78ff59d052ba1f6763d1e2e7f3d1f72765325d9d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Petr=20P=C5=AFlp=C3=A1n?= Date: Sat, 28 Jun 2014 20:02:02 +0200 Subject: [PATCH] [Motherless] simplify --- youtube_dl/extractor/motherless.py | 58 ++++++++++++++---------------- youtube_dl/utils.py | 3 ++ 2 files changed, 29 insertions(+), 32 deletions(-) diff --git a/youtube_dl/extractor/motherless.py b/youtube_dl/extractor/motherless.py index 782651612..6229b2173 100644 --- a/youtube_dl/extractor/motherless.py +++ b/youtube_dl/extractor/motherless.py @@ -4,11 +4,13 @@ import re from .common import InfoExtractor -from ..utils import str_to_int +from ..utils import ( + int_or_none, + unified_strdate, +) class MotherlessIE(InfoExtractor): - """Information Extractor for Motherless""" _VALID_URL = r'http://(?:www\.)?motherless\.com/(?P[A-Z0-9]+)' _TESTS = [ { @@ -21,7 +23,7 @@ class MotherlessIE(InfoExtractor): 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'], 'upload_date': '20100913', 'uploader_id': 'famouslyfuckedup', - 'thumbnail': 'http://thumbs.motherlessmedia.com/thumbs/AC3FFE1.jpg', + 'thumbnail': 're:http://.*\.jpg', 'age_limit': 18, } }, @@ -35,7 +37,7 @@ class MotherlessIE(InfoExtractor): 'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen', 'game', 'hairy'], 'upload_date': '20140622', 'uploader_id': 'Sulivana7x', - 'thumbnail': 'http://thumbs.motherlessmedia.com/thumbs/532291B.jpg', + 'thumbnail': 're:http://.*\.jpg', 'age_limit': 18, } } @@ -47,46 +49,38 @@ def _real_extract(self,url): webpage = self._download_webpage(url, video_id) - title = self._html_search_regex(r'(?P<title>.+?) - MOTHERLESS.COM', webpage, 'title') - video_url = self._search_regex(r"__fileurl = '(?P[^']+)'", webpage, 'video_url') - thumbnail = self._og_search_thumbnail(webpage) - age_limit = self._rta_search(webpage) # Hint: it's 18 ;) - view_count = str_to_int(self._html_search_regex(r'Views(.+?)', webpage, - 'view_count', flags=re.DOTALL)) + title = self._html_search_regex(r'id="view-upload-title">\s+([^<]+)<', webpage, 'title') + + video_url = self._html_search_regex(r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video_url') + age_limit = self._rta_search(webpage) + + view_count = self._html_search_regex(r'Views\s+([^<]+)<', webpage, 'view_count') + + upload_date = self._html_search_regex(r'Uploaded\s+([^<]+)<', webpage, 'upload_date') + if 'Ago' in upload_date: + days = int(re.search(r'([0-9]+)', upload_date).group(1)) + upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d') + else: + upload_date = unified_strdate(upload_date) + + like_count = self._html_search_regex(r'Favorited\s+([^<]+)<', webpage, 'like_count') - like_count = str_to_int(self._html_search_regex(r'Favorited(.+?)', webpage, - 'like_count', flags=re.DOTALL)) comment_count = webpage.count('class="media-comment-contents"') - uploader_id = self._html_search_regex(r'