From 9a69161c8646f63b4d9fa17c6ac3ab922d625859 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 27 Feb 2013 23:43:10 +0100 Subject: Initial commit --- businessweek.com.txt | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) create mode 100644 businessweek.com.txt (limited to 'businessweek.com.txt') diff --git a/businessweek.com.txt b/businessweek.com.txt new file mode 100644 index 0000000..0308559 --- /dev/null +++ b/businessweek.com.txt @@ -0,0 +1,30 @@ +# story has several pages, should be detected +body: //div[@id='storyBody'] +body: //div[@id='article_body'] +body: //div[@id='story_body'] + +title://h1[@id='article_headline'] + +# article author +author: //p[@class='author']/a +# story author(s) +author: substring-after(//p[@class='byline'], 'By ') + +# article date +date: //span[@class='published_date'] +# story date +date: //span[@class='date'] + +date: substring-after(//div[contains(@class,'attributor')],'on') +strip_id_or_class: inset +strip: //p/span[@class='photoCredit'] +strip: //h1 + +strip_id_or_class: page_count +strip_id_or_class: tools +strip_id_or_class: pagination + +single_page_link: //li[@id='stPrint']/a + +test_url: http://www.businessweek.com/magazine/buyback-insurance-a-good-deal-for-retailers-07282011.html +test_url: http://www.businessweek.com/articles/2012-06-06/american-pain-the-largest-u-dot-s-dot-pill-mills-rise-and-fall \ No newline at end of file -- cgit v1.3.1