From 8efd06aa428df6feed925396f4170a9ad8ca2b4d Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Fri, 24 Oct 2014 19:53:48 +0200 Subject: [PATCH] [motherless] Simplify --- youtube_dl/extractor/motherless.py | 36 +++++++++++++++++------------- 1 file changed, 20 insertions(+), 16 deletions(-) diff --git a/youtube_dl/extractor/motherless.py b/youtube_dl/extractor/motherless.py index 50083bd4a..3621ff99e 100644 --- a/youtube_dl/extractor/motherless.py +++ b/youtube_dl/extractor/motherless.py @@ -5,7 +5,7 @@ import re from .common import InfoExtractor from ..utils import ( - int_or_none, + str_to_int, unified_strdate, ) @@ -57,30 +57,34 @@ class MotherlessIE(InfoExtractor): } ] - def _real_extract(self,url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + def _real_extract(self, url): + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - 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') + 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') + view_count = str_to_int(self._html_search_regex( + r'Views\s+([^<]+)<', + webpage, 'view count', fatal=False)) + like_count = str_to_int(self._html_search_regex( + r'Favorited\s+([^<]+)<', + webpage, 'like count', fatal=False)) - upload_date = self._html_search_regex(r'Uploaded\s+([^<]+)<', webpage, 'upload_date') + 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') - comment_count = webpage.count('class="media-comment-contents"') - uploader_id = self._html_search_regex(r'"thumb-member-username">\s+\s+