From 9a69161c8646f63b4d9fa17c6ac3ab922d625859 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 27 Feb 2013 23:43:10 +0100 Subject: Initial commit --- slate.com.txt | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 slate.com.txt (limited to 'slate.com.txt') diff --git a/slate.com.txt b/slate.com.txt new file mode 100644 index 0000000..d5798e0 --- /dev/null +++ b/slate.com.txt @@ -0,0 +1,19 @@ +title: //h1[@class="sl-art-head-dek"] +body: //article//div[@class='sl-art-body']/div[contains(@class, 'body')] +strip: //div[@class="department_kicker"] +strip: //div[@id="insider_ad_wrapper" or @id="insider_ad_inner"] +strip: //div[@id="bottom_sponsored_links"] +strip: //div[@class="sl-art-ad-midflex"] +#strip: //dl +#strip: //p[em/a[contains(@href, 'facebook.com')]] +prune: no + +author: //div[@id='author_bio']//a[contains(@href, '/author/')] +author: //a[contains(@href, '/authors.')] + +date: substring-before(substring-after(//span[@class='sl-art-byline'], 'Posted '), ', at ') + +single_page_link: //a[@class='sl-art-sinpage'] + +test_url: http://www.slate.com/id/2274583/pagenum/all/ +test_url: http://www.slate.com/id/2293116/ \ No newline at end of file -- cgit v1.3.1