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/huffingtonpost.com.txt | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/huffingtonpost.com.txt (limited to 'inc/3rdparty/site_config/standard/huffingtonpost.com.txt') diff --git a/inc/3rdparty/site_config/standard/huffingtonpost.com.txt b/inc/3rdparty/site_config/standard/huffingtonpost.com.txt new file mode 100644 index 00000000..d40513b2 --- /dev/null +++ b/inc/3rdparty/site_config/standard/huffingtonpost.com.txt @@ -0,0 +1,16 @@ +title: //meta[@property="og:title"]/@content +body: //div[img[starts-with(@id, 'img_caption')]] | //div[@class="big_photo"] | //div[contains(@class, 'entry_body_text')] +date: //meta[@name="publish_date"]/@content +author: //a[@rel="author"] +author: //meta[@name="author"]/@content +prune: no +tidy: no +strip: //footer +strip_id_or_class: ps-slideshow +strip_id_or_class: fs-slideshow +strip: //p[contains(., 'Related on HuffPost:')] +# end early +replace_string(