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/wmnf.org.txt | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/wmnf.org.txt (limited to 'inc/3rdparty/site_config/standard/wmnf.org.txt') diff --git a/inc/3rdparty/site_config/standard/wmnf.org.txt b/inc/3rdparty/site_config/standard/wmnf.org.txt old mode 100644 new mode 100755 index ffb6b2d1..1d403a91 --- a/inc/3rdparty/site_config/standard/wmnf.org.txt +++ b/inc/3rdparty/site_config/standard/wmnf.org.txt @@ -1,13 +1,13 @@ -title: //div[@class="bodyText"]/h1/text() -body: //div[@class="bodyText"] - -# author and date are separated by only a newline -# can't figure out how to tokenize that yet -author: //div[@class="bodyText"]/span[@class="info"]/text() -date: //div[@class="bodyText"]/span[@class="info"]/text() - -# strip metdata from body text -strip: //div[@class="bodyText"]/h1/text() -strip: //div[@class="bodyText"]/span[@class="info"] +title: //div[@class="bodyText"]/h1/text() +body: //div[@class="bodyText"] + +# author and date are separated by only a newline +# can't figure out how to tokenize that yet +author: //div[@class="bodyText"]/span[@class="info"]/text() +date: //div[@class="bodyText"]/span[@class="info"]/text() + +# strip metdata from body text +strip: //div[@class="bodyText"]/h1/text() +strip: //div[@class="bodyText"]/span[@class="info"] strip: //div[@class="bodyText"]/span[@class="info"] test_url: http://www.wmnf.org/news_stories/light-rail-advocates-join-forces-to-combat-opposition-in-pinellas \ No newline at end of file -- cgit v1.2.3