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/livescience.com.txt | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/livescience.com.txt (limited to 'inc/3rdparty/site_config/standard/livescience.com.txt') diff --git a/inc/3rdparty/site_config/standard/livescience.com.txt b/inc/3rdparty/site_config/standard/livescience.com.txt new file mode 100755 index 00000000..5275d34a --- /dev/null +++ b/inc/3rdparty/site_config/standard/livescience.com.txt @@ -0,0 +1,20 @@ +title: //div[@class="album_title"]//h1 +author: substring-before(//div[@class='by_line'], ',') +date: substring-after(substring-before(//div[@class="album_time"], ' Time'), 'Date: ') +body: //div[@class="about_text"] + +strip: //div[@class='large_popper'] +strip: //span[contains(@id, 'mag_glass')] +strip: //span[contains(@class, 'img_overlay')] +strip: //td//span +strip: //div[@class="center_adsense"] +strip: //div[@class="article_info"]//div[@class='asset_section'] +strip: //div[@class="article_additional"] +strip: //div[contains(@style, 'overflow:hidden')] +strip: //div[@class="aa_text"] +strip: //div[@id='nointelliTXT'] + +prune: no +autodetect_on_failure: no + +test_url: http://www.livescience.com/34569-why-flowers-close-at-night-nyctinasty.html -- cgit v1.2.3