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 --- .../standard/scientificamerican.com.txt | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/scientificamerican.com.txt (limited to 'inc/3rdparty/site_config/standard/scientificamerican.com.txt') diff --git a/inc/3rdparty/site_config/standard/scientificamerican.com.txt b/inc/3rdparty/site_config/standard/scientificamerican.com.txt new file mode 100644 index 00000000..d510407d --- /dev/null +++ b/inc/3rdparty/site_config/standard/scientificamerican.com.txt @@ -0,0 +1,25 @@ +# +# After site revisions at SciAm, this configuration does +# not work, especially for multi-page articles. For +# every article there is now a "Print" link which +# is far more reliable. So this configuration should be +# removed or disabled. +# 2/3/13 +# + +# meta data +title://h1[@class = 'articleTitle'] +author:substring-after(//span[@class = 'byline'],'By ') +date:substring-before(//span[@class = 'datestamp'],'|') + +#body content +body://div[@id = 'articleContent'] +#next_page_link://li[@id = 'flairPagination']/a[last()] + +single_page_link: //a[contains(@href, 'print=true')] + +#cleanup +strip://div[@class = 'fsgBooks'] + +test_url: http://www.scientificamerican.com/article.cfm?id=do-brain-scans-comatose-patients-reveal-conscious-state +test_url: http://www.scientificamerican.com/article.cfm?id=solar-wind-transforms-venus-into-shape-of-comet \ No newline at end of file -- cgit v1.2.3