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/techcrunch.com.txt | 34 +++++++++++----------- 1 file changed, 17 insertions(+), 17 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/techcrunch.com.txt (limited to 'inc/3rdparty/site_config/standard/techcrunch.com.txt') diff --git a/inc/3rdparty/site_config/standard/techcrunch.com.txt b/inc/3rdparty/site_config/standard/techcrunch.com.txt old mode 100644 new mode 100755 index f436acb5..1509c46e --- a/inc/3rdparty/site_config/standard/techcrunch.com.txt +++ b/inc/3rdparty/site_config/standard/techcrunch.com.txt @@ -1,18 +1,18 @@ -body: //div[contains(@class, 'media-container') or contains(@class, 'body-copy')] - -author: //a[@class="name"] - -date: //div[@class="post-time"] - -title: //h1[@class="headline"] -strip_id_or_class: module-crunchbase - -# The following is for the mobile site -body: //div[@id="singlentry"] -author: substring-after(//span[@class="single-post-meta-top"],'rsaquo; ') -date: substring-before(//div[@class="single-post-meta-top"],' @') -title: //a[@class="sh2"] - -prune: no - +body: //div[contains(@class, 'media-container') or contains(@class, 'body-copy')] + +author: //a[@class="name"] + +date: //div[@class="post-time"] + +title: //h1[@class="headline"] +strip_id_or_class: module-crunchbase + +# The following is for the mobile site +body: //div[@id="singlentry"] +author: substring-after(//span[@class="single-post-meta-top"],'rsaquo; ') +date: substring-before(//div[@class="single-post-meta-top"],' @') +title: //a[@class="sh2"] + +prune: no + test_url: http://techcrunch.com/2011/10/18/apples-insanely-great-q1-2012/ \ No newline at end of file -- cgit v1.2.3