From 9a69161c8646f63b4d9fa17c6ac3ab922d625859 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 27 Feb 2013 23:43:10 +0100 Subject: Initial commit --- post-gazette.com.txt | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) create mode 100644 post-gazette.com.txt (limited to 'post-gazette.com.txt') diff --git a/post-gazette.com.txt b/post-gazette.com.txt new file mode 100644 index 0000000..baa9d69 --- /dev/null +++ b/post-gazette.com.txt @@ -0,0 +1,26 @@ +title: //div[@class='story_headline'] +author: substring-before(substring-after(//div[@class='story_byline'],'By'),'/') +date: //div[@class='story_lastupdate'] +body: //div[@id='story'] +strip: //div[@class='story_byline'] +strip: //div[@class='story_lastupdate'] +strip: //div[@class='story_headline'] +strip: //div[@id='abuse'] +strip: //h2 +strip: //div[@class='pagenumbers_wrap'] +strip: //ul[@class='pagenumbers'] +strip: //div[starts-with(., 'To report inappropriate comments')] + +strip_id_or_class: story_share +strip_id_or_class: OUTBRAIN +strip_id_or_class: story_box_right +strip: //div[a[@href='http://www.post-gazette.com/pg/12062/1213990-42.stm']] +strip: //ul[@id='pikame']/li[position()>1] + +prune: no +tidy: no + +single_page_link: //a[contains(@href, '?p=0')] + +test_url: http://www.post-gazette.com/stories/sports/penguins/pens-crosby-expects-to-return-thursday-226648/ +test_url: http://www.post-gazette.com/stories/sports/pirates/pirates-fork-over-changes-for-fans-at-pnc-park-629789 \ No newline at end of file -- cgit v1.3.1