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 --- smh.com.au.txt | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 smh.com.au.txt (limited to 'smh.com.au.txt') diff --git a/smh.com.au.txt b/smh.com.au.txt new file mode 100644 index 0000000..f647f81 --- /dev/null +++ b/smh.com.au.txt @@ -0,0 +1,14 @@ +body: //div[@id='content'] +title: //h1[@class='cN-headingPage'] +author: //h3[@class='authorName'] +date: //dd[@class='updated dtstamp'] + +strip: //ul[@class='social sponsored cfix'] +strip: //div[contains(@class, 'hiddenVisually')] +strip: //dd[@class='updated dtstamp'] +strip: //h3[@class='authorName'] +strip: //ul[@class='social cfix'] +strip: //div[contains(@id, 'adspot')] + +strip: //div[contains(@class, 'overlayPlayCountdown')] +strip: //div[@class='fdVideoWof']//span[@class='gone'] -- cgit v1.3.1