From 9a69161c8646f63b4d9fa17c6ac3ab922d625859 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 27 Feb 2013 23:43:10 +0100 Subject: Initial commit --- salon.com.txt | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 salon.com.txt (limited to 'salon.com.txt') diff --git a/salon.com.txt b/salon.com.txt new file mode 100644 index 0000000..2b47f74 --- /dev/null +++ b/salon.com.txt @@ -0,0 +1,11 @@ +title: //meta[@property='og:title']/@content +author: (//span[@class="byline"]/a)[1] +date: //span[contains(@class, "toLocalTime")] +body: (//div[contains(@class, "articleInner")]//img[contains(@src, 'media.salon.com') and contains(@src, '460x')])[1] | //div[contains(@class, "articleContent") or contains(@class, "writerMeta")] + +prune: no + +# deal with singleton links +single_page_link: (//h1/a[contains(@href, '/singleton')])[1] + +test_url: http://www.salon.com/2011/10/25/occupying_the_rust_belt/singleton/ \ No newline at end of file -- cgit v1.3.1