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 --- .../standard/scientificamerican.com.txt | 48 +++++++++++----------- 1 file changed, 24 insertions(+), 24 deletions(-) mode change 100644 => 100755 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 old mode 100644 new mode 100755 index d510407d..1b3f31cf --- a/inc/3rdparty/site_config/standard/scientificamerican.com.txt +++ b/inc/3rdparty/site_config/standard/scientificamerican.com.txt @@ -1,25 +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 +# +# 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