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/fnal.gov.txt | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/fnal.gov.txt (limited to 'inc/3rdparty/site_config/standard/fnal.gov.txt') diff --git a/inc/3rdparty/site_config/standard/fnal.gov.txt b/inc/3rdparty/site_config/standard/fnal.gov.txt old mode 100644 new mode 100755 index 7faa6bfc..e404ccb8 --- a/inc/3rdparty/site_config/standard/fnal.gov.txt +++ b/inc/3rdparty/site_config/standard/fnal.gov.txt @@ -1,15 +1,15 @@ -title: normalize(//h1) - -author: //td/p[position()=last()]/em - -# I swear, this is really the best way to do this -date: normalize(//td[contains(@style, "color: #ffffff")]) - -# my god, it's full of tables -body: /table/tbody/tr[5]//table/tbody//table/tbody/tr/td -strip: //h1 - -# the following two lines strip the byline at the end of the article (the byline is a

that consists of an em dash and then some text in an ). I have no idea why I can't just strip //p[position()=last()], but trying to do so includes a bunch of other crap in the output. -strip: //p[position()=last()]/em +title: normalize(//h1) + +author: //td/p[position()=last()]/em + +# I swear, this is really the best way to do this +date: normalize(//td[contains(@style, "color: #ffffff")]) + +# my god, it's full of tables +body: /table/tbody/tr[5]//table/tbody//table/tbody/tr/td +strip: //h1 + +# the following two lines strip the byline at the end of the article (the byline is a

that consists of an em dash and then some text in an ). I have no idea why I can't just strip //p[position()=last()], but trying to do so includes a bunch of other crap in the output. +strip: //p[position()=last()]/em strip: //p[position()=last()]/child::text() test_url: http://www.fnal.gov/pub/today/archive_2011/today11-11-09_MuonDepartmentReadMore.html \ No newline at end of file -- cgit v1.2.3