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/washingtonmonthly.com.txt | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/washingtonmonthly.com.txt (limited to 'inc/3rdparty/site_config/standard/washingtonmonthly.com.txt') diff --git a/inc/3rdparty/site_config/standard/washingtonmonthly.com.txt b/inc/3rdparty/site_config/standard/washingtonmonthly.com.txt old mode 100644 new mode 100755 index edf16422..8f8902a5 --- a/inc/3rdparty/site_config/standard/washingtonmonthly.com.txt +++ b/inc/3rdparty/site_config/standard/washingtonmonthly.com.txt @@ -1,10 +1,10 @@ -title://a[@class = 'headline-article'] - -author: substring-after(//div[@class = 'article']/p[@class = 'author'], 'By ') -date://div[@class = 'article']/span[@class = 'date'] -body://div[@class = 'article'] -single_page_link://a[@class = 'print'] -strip://p[@class = 'author'] -strip://a[@class = 'headline-article'] +title://a[@class = 'headline-article'] + +author: substring-after(//div[@class = 'article']/p[@class = 'author'], 'By ') +date://div[@class = 'article']/span[@class = 'date'] +body://div[@class = 'article'] +single_page_link://a[@class = 'print'] +strip://p[@class = 'author'] +strip://a[@class = 'headline-article'] strip://span[@class = 'date'] test_url: http://www.washingtonmonthly.com/magazine/julyaugust_2011/features/the_trinity_sisters030380.php \ No newline at end of file -- cgit v1.2.3