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/cbsnews.com.txt | 29 ++++++++++++----------- 1 file changed, 15 insertions(+), 14 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/cbsnews.com.txt (limited to 'inc/3rdparty/site_config/standard/cbsnews.com.txt') diff --git a/inc/3rdparty/site_config/standard/cbsnews.com.txt b/inc/3rdparty/site_config/standard/cbsnews.com.txt old mode 100644 new mode 100755 index 4ba3da19..04d20230 --- a/inc/3rdparty/site_config/standard/cbsnews.com.txt +++ b/inc/3rdparty/site_config/standard/cbsnews.com.txt @@ -1,14 +1,15 @@ -date: //meta[@name="published"]/@content -date: //div[@class="timeLine"] -title: //div[@id='contentBody']//h1 -author: //dl[@class="storyBlogByline"]/dd/a -body: //div[@id='storyMediaBox'] | //div[contains(@class, 'storyText')] - -# Content Pruning -strip: //div[@class="scrollingArrows"] -strip: //div[@class="timeLine"] -strip: //dl[@class="storyBlogByline"] - -prune: no - -test_url: http://www.cbsnews.com/8301-201_162-57366361/rescued-americans-dad-proud-of-the-u.s/ \ No newline at end of file +date: //meta[@name="published"]/@content +date: //div[@class="timeLine"] +title: //div[@id='contentBody']//h1 +author: //dl[@class="storyBlogByline"]/dd/a +body: //div[@id='storyMediaBox'] | //div[contains(@class, 'storyText')] + +# Content Pruning +strip: //div[@class="scrollingArrows"] +strip: //div[@class="timeLine"] +strip: //dl[@class="storyBlogByline"] +strip: //span[@class='image-credit'] + +prune: no + +test_url: http://www.cbsnews.com/8301-201_162-57366361/rescued-americans-dad-proud-of-the-u.s/ -- cgit v1.2.3