From 4e067ceabd705201a16b4c92cf4b23f3b990326c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Sun, 13 Jul 2014 10:15:40 +0200 Subject: updated specific configuration for parsing --- inc/3rdparty/site_config/standard/theguardian.com.txt | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/theguardian.com.txt (limited to 'inc/3rdparty/site_config/standard/theguardian.com.txt') diff --git a/inc/3rdparty/site_config/standard/theguardian.com.txt b/inc/3rdparty/site_config/standard/theguardian.com.txt new file mode 100755 index 00000000..c803e4e4 --- /dev/null +++ b/inc/3rdparty/site_config/standard/theguardian.com.txt @@ -0,0 +1,13 @@ +title: //div[@id='main-article-info']//h1 +body: //div[@id='article-wrapper'] +date: //li[@class='publication']//time[@pubdate] | //li[@class='publication']//data[@pubdate] +strip: //div[contains(@class, 'email-subscription')] +strip: //div[contains(@class, 'kindleWidget')] +#strip: //a[not(text())] +strip_id_or_class: pocket-btn +author: //li[@class='byline'] +prune: no +tidy: no +test_url: http://www.theguardian.com/world/2013/oct/04/nsa-gchq-attack-tor-network-encryption +test_url: http://www.theguardian.com/world/2013/oct/03/edward-snowden-files-john-lanchester +test_url: http://www.theguardian.com/commentisfree/2014/jun/15/britishness-search-identity-my-part-in-camerons-odyssey \ No newline at end of file -- cgit v1.2.3