From ac4d114214d820b20e18518a2dbc809337e39043 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Fri, 6 Dec 2013 10:13:03 +0100 Subject: [add] new specific configuration files --- inc/3rdparty/site_config/standard/salon.com.txt | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/salon.com.txt (limited to 'inc/3rdparty/site_config/standard/salon.com.txt') diff --git a/inc/3rdparty/site_config/standard/salon.com.txt b/inc/3rdparty/site_config/standard/salon.com.txt new file mode 100644 index 00000000..04f8afd5 --- /dev/null +++ b/inc/3rdparty/site_config/standard/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 v1.2.3