From 9a96ce202194bb7ddc33f2fe61e8f25e8555f473 Mon Sep 17 00:00:00 2001 From: Tim Groeneveld Date: Tue, 10 Mar 2015 11:33:44 +1100 Subject: Add a bunch of Australian news sites. * au.businessinsider.com * au.news.yahoo.com * brokernews.com.au * choice.com.au * cnet.com.au * dailytelegraph.com.au * designbuildsource.com.au * gizmodo.com.au * heraldsun.com.au * itnews.com.au * marketingmag.com.au * moneymanagement.com.au * news.com.au * news.ninemsn.com.au * perthnow.com.au * smh.com.au * smh.drive.com.au * sunshinecoastdaily.com.au * theaustralian.com.au * watoday.com.au * weeklytimesnow.com.au * westernadvocate.com.au --- sunshinecoastdaily.com.au.txt | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 sunshinecoastdaily.com.au.txt (limited to 'sunshinecoastdaily.com.au.txt') diff --git a/sunshinecoastdaily.com.au.txt b/sunshinecoastdaily.com.au.txt new file mode 100644 index 0000000..bf5e918 --- /dev/null +++ b/sunshinecoastdaily.com.au.txt @@ -0,0 +1,10 @@ +body: //section//article//p + +strip: //aside +strip: //div[@class='margin-top-15'] +strip: //p[@class='tags'] + +author: //span[@class='byline']//ul[@class='piped']//li[1] +date: //span[@class='byline']//ul[@class='piped']//li[2] + +parser: html5lib -- cgit v1.3.1