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 --- .../site_config/standard/minnesota.publicradio.org.txt | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/minnesota.publicradio.org.txt (limited to 'inc/3rdparty/site_config/standard/minnesota.publicradio.org.txt') diff --git a/inc/3rdparty/site_config/standard/minnesota.publicradio.org.txt b/inc/3rdparty/site_config/standard/minnesota.publicradio.org.txt old mode 100644 new mode 100755 index 7e43d63c..773a627c --- a/inc/3rdparty/site_config/standard/minnesota.publicradio.org.txt +++ b/inc/3rdparty/site_config/standard/minnesota.publicradio.org.txt @@ -1,10 +1,10 @@ -title: //*[@class="article"]/h1 -date: //*[@class="article"]/div[@class="date"] - -# strip the title and date from the article text -strip: //*[@class="article"]/h1 -strip: //*[@class="article"]/div[@class="date"] - -# strip annoying
between metadata and article +title: //*[@class="article"]/h1 +date: //*[@class="article"]/div[@class="date"] + +# strip the title and date from the article text +strip: //*[@class="article"]/h1 +strip: //*[@class="article"]/div[@class="date"] + +# strip annoying
between metadata and article strip: //*[@class="article"]/div[@class="date"]/following-sibling::br test_url: http://minnesota.publicradio.org/display/web/2012/06/19/health/senators-want-health-care-ruling-on-tv/ \ No newline at end of file -- cgit v1.2.3