From 81bce8244b3d0e29918117a0fdcf40589e184ba9 Mon Sep 17 00:00:00 2001 From: Tim Groeneveld Date: Tue, 10 Mar 2015 11:50:15 +1100 Subject: Add some other missing news sites that do not always correctly work. * business.time.com * galwayindependent.com * help.fivefilters.org * ippmedia.com * mitchellrepublic.com * news.menshealth.com * planetsave.com * yourerie.com --- business.time.com.txt | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 business.time.com.txt (limited to 'business.time.com.txt') diff --git a/business.time.com.txt b/business.time.com.txt new file mode 100644 index 0000000..5502bea --- /dev/null +++ b/business.time.com.txt @@ -0,0 +1,17 @@ +# 2011-10-25 - carlo@... - Initial setup. + +single_page_link: //li[@class='print']/a/@href + +title: //h1 +author: //meta[@name="byline"]/@content +date: //meta[@name="date"]/@content + +strip: //span[@class="see"] +strip: //div[@class="byline"] +strip: //div[@id="date2"] +strip: //h1 +strip: //div[@class='post-rail-ad'] +strip: //div[@class='post-rail-content'] +strip: //aside[@class='post-rail'] + +test_url: http://www.time.com/time/specials/packages/article/0,28804,2094921_2094923_2094924,00.html -- cgit v1.3.1