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/nfl.com.txt | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/nfl.com.txt (limited to 'inc/3rdparty/site_config/standard/nfl.com.txt') diff --git a/inc/3rdparty/site_config/standard/nfl.com.txt b/inc/3rdparty/site_config/standard/nfl.com.txt old mode 100644 new mode 100755 index 70f92473..956b288f --- a/inc/3rdparty/site_config/standard/nfl.com.txt +++ b/inc/3rdparty/site_config/standard/nfl.com.txt @@ -1,11 +1,11 @@ -# doesn't look like selecting an attribute value works? -# author: //meta[@id="authorName"]@value - -author: substring-after(//li[@id="article-hdr-meta-author"]/text(), "By ") -date: //abbr[@id="article-time"] -title: //div[@id="article-hdr"]/h1 -body: //div[@class="articleText"] - -# strip miscellaneous teasers & etc +# doesn't look like selecting an attribute value works? +# author: //meta[@id="authorName"]@value + +author: substring-after(//li[@id="article-hdr-meta-author"]/text(), "By ") +date: //abbr[@id="article-time"] +title: //div[@id="article-hdr"]/h1 +body: //div[@class="articleText"] + +# strip miscellaneous teasers & etc strip: //div[@class="removeformobile"] test_url: http://www.nfl.com/news/story/09000d5d82388707/article/close-shave-chiefs-haley-perseveres-through-rough-start?module=HP11_content_stream \ No newline at end of file -- cgit v1.2.3