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/cw.com.tw.txt | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/cw.com.tw.txt (limited to 'inc/3rdparty/site_config/standard/cw.com.tw.txt') diff --git a/inc/3rdparty/site_config/standard/cw.com.tw.txt b/inc/3rdparty/site_config/standard/cw.com.tw.txt new file mode 100755 index 00000000..6e3a91ee --- /dev/null +++ b/inc/3rdparty/site_config/standard/cw.com.tw.txt @@ -0,0 +1,14 @@ +author://span[contains(@class,'reporter')] + +date://span[contains(@class,'date')] + +body://div[contains(@class,'mainContaner')] + +strip://div[contains(@class,'mainHeaer')] +strip://div[contains(@class,'keyW')] +strip://div[contains(@class,'wonderful')] +strip://div[contains(@class,'pages')] +strip://div[contains(@class,'Topics TopicsW3')] + +next_page_link://li[@class='pageNext']/a[contains(.,'下一頁')] +test_url: http://www.cw.com.tw/article/article.action?id=5032848 \ No newline at end of file -- cgit v1.2.3