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 --- .../site_config/standard/articles.washingtonpost.com.txt | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/articles.washingtonpost.com.txt (limited to 'inc/3rdparty/site_config/standard/articles.washingtonpost.com.txt') diff --git a/inc/3rdparty/site_config/standard/articles.washingtonpost.com.txt b/inc/3rdparty/site_config/standard/articles.washingtonpost.com.txt new file mode 100755 index 00000000..a76c2d02 --- /dev/null +++ b/inc/3rdparty/site_config/standard/articles.washingtonpost.com.txt @@ -0,0 +1,11 @@ +body: //div[contains(@class, "article_body")] +# print view +body: //div[@id='print_facet']//div[@id='body'] + +tidy: no +prune: no + +single_page_link: concat(substring-before(//div[@id="echo_container_a"]/@guid, '_story.html'), '_print.html') + +test_url: http://articles.washingtonpost.com/2011-10-22/world/35279694_1_germany-acts-german-leaders-chancellor-angela-merkel +test_url: http://articles.washingtonpost.com/2013-05-31/opinions/39658000_1_chemical-weapons-mass-destruction-cartels \ No newline at end of file -- cgit v1.2.3