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/slate.com.txt | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/slate.com.txt (limited to 'inc/3rdparty/site_config/standard/slate.com.txt') diff --git a/inc/3rdparty/site_config/standard/slate.com.txt b/inc/3rdparty/site_config/standard/slate.com.txt new file mode 100644 index 00000000..e92f6a06 --- /dev/null +++ b/inc/3rdparty/site_config/standard/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 v1.2.3