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/politico.com.txt | 26 +++++++++------------- 1 file changed, 11 insertions(+), 15 deletions(-) (limited to 'inc/3rdparty/site_config/standard/politico.com.txt') diff --git a/inc/3rdparty/site_config/standard/politico.com.txt b/inc/3rdparty/site_config/standard/politico.com.txt index c5302d1b..d8f5e575 100755 --- a/inc/3rdparty/site_config/standard/politico.com.txt +++ b/inc/3rdparty/site_config/standard/politico.com.txt @@ -1,17 +1,13 @@ -title://div[contains(@class, "article")]/h1 -body://div[contains(@class,"story-text")] - -# Why doesn't this work? next_page_link://ul[contains(@class,"pagination")]/li/a[@rel="next"] - -next_page_link://ul[contains(@class,"pagination")]/li[contains(@class, "current")]/following-sibling::node()/a -next_page_link://div[contains(@class,"pagination")]/ol/li[contains(@class, "current")]/following-sibling::node()/a -date://meta[@name="publish_date"]/@content - -strip://div[contains(@class, "breadcrumbs")] -strip://a[contains(@class, "hidden")] -strip://div[contains(@class, "story-embed")] +title://div[contains(@class, "article")]/h1 +body://div[contains(@class,"story-text")] + +# Why doesn't this work? next_page_link://ul[contains(@class,"pagination")]/li/a[@rel="next"] + +next_page_link://ul[contains(@class,"pagination")]/li[contains(@class, "current")]/following-sibling::node()/a +date://meta[@name="publish_date"]/@content + +strip://div[contains(@class, "breadcrumbs")] +strip://a[contains(@class, "hidden")] +strip://div[contains(@class, "story-embed")] strip://div[contains(@class, "story-text")]//p/a[contains(text(), "Also on POLITICO:")]/.. -strip://div[contains(@class, "story-interrupt")] -strip://footer[contains(@class, "author-bio")] - test_url: http://www.politico.com/news/stories/0712/78105.html \ No newline at end of file -- cgit v1.2.3