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/computerworld.com.txt | 42 +++++++++++----------- 1 file changed, 21 insertions(+), 21 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/computerworld.com.txt (limited to 'inc/3rdparty/site_config/standard/computerworld.com.txt') diff --git a/inc/3rdparty/site_config/standard/computerworld.com.txt b/inc/3rdparty/site_config/standard/computerworld.com.txt old mode 100644 new mode 100755 index 8e1f3e11..7f20a4da --- a/inc/3rdparty/site_config/standard/computerworld.com.txt +++ b/inc/3rdparty/site_config/standard/computerworld.com.txt @@ -1,22 +1,22 @@ -title: //meta[@name='headline']/@content -date: //meta[@name='date']/@content -author: //meta[@name='author']/@content -body: //div[contains(@class, 'article')] -body://div[@id="article_body"] - -strip_id_or_class: banner -strip: //noscript -strip: //div[@style='width:1px;height:130px;float:right;'] -strip: //div[@class='storyby'] -strip_image_src: twitter_icon -strip_image_src: rss_bug - -tidy: no -prune: no - -next_page_link://div[@id="next_page"]/a - -single_page_link: concat('http://www.computerworld.com/s/article/print/', substring-after(//link[@rel='canonical']/@href, '/s/article/')) - -test_url: http://www.computerworld.com/s/article/9224348/Apple_s_new_OS_X_tightens_screws_on_some_malware +title: //meta[@name='headline']/@content +date: //meta[@name='date']/@content +author: //meta[@name='author']/@content +body: //div[contains(@class, 'article')] +body://div[@id="article_body"] + +strip_id_or_class: banner +strip: //noscript +strip: //div[@style='width:1px;height:130px;float:right;'] +strip: //div[@class='storyby'] +strip_image_src: twitter_icon +strip_image_src: rss_bug + +tidy: no +prune: no + +next_page_link://div[@id="next_page"]/a + +single_page_link: concat('http://www.computerworld.com/s/article/print/', substring-after(//link[@rel='canonical']/@href, '/s/article/')) + +test_url: http://www.computerworld.com/s/article/9224348/Apple_s_new_OS_X_tightens_screws_on_some_malware test_url: http://www.computerworld.com/s/article/9227679/Windows_8_Release_Preview_Updated_but_still_uneasy \ No newline at end of file -- cgit v1.2.3