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/tnr.com.txt | 32 +++++++++++++-------------- 1 file changed, 16 insertions(+), 16 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/tnr.com.txt (limited to 'inc/3rdparty/site_config/standard/tnr.com.txt') diff --git a/inc/3rdparty/site_config/standard/tnr.com.txt b/inc/3rdparty/site_config/standard/tnr.com.txt old mode 100644 new mode 100755 index 65a1899f..199f5d13 --- a/inc/3rdparty/site_config/standard/tnr.com.txt +++ b/inc/3rdparty/site_config/standard/tnr.com.txt @@ -1,17 +1,17 @@ -title: //div[contains(@class, 'article_detail')]/div[@class='entry_header']/h1 -title: //div[contains(@class, 'article_detail')]//h1 -title: //h1 - -body: //div[contains(@class, 'article_detail')] - -author: //div[@class='article_detail']/div[@class='entry_header']/li/div[@class='author']//h3 -author: div[@class='author']//h3 -strip: //div[contains(@class, 'field-field-book-cover')] - -date: translate(//*[@class='post_date' and contains(., ' 20')], '|', '') - -prune: no - -single_page_link: //a[@class='print-page'] - +title: //div[contains(@class, 'article_detail')]/div[@class='entry_header']/h1 +title: //div[contains(@class, 'article_detail')]//h1 +title: //h1 + +body: //div[contains(@class, 'article_detail')] + +author: //div[@class='article_detail']/div[@class='entry_header']/li/div[@class='author']//h3 +author: div[@class='author']//h3 +strip: //div[contains(@class, 'field-field-book-cover')] + +date: translate(//*[@class='post_date' and contains(., ' 20')], '|', '') + +prune: no + +single_page_link: //a[@class='print-page'] + test_url: http://www.tnr.com/blog/jonathan-chait/92991/did-obama-get-rolled \ No newline at end of file -- cgit v1.2.3