clickz.com.script

来自「垂直搜索的网络爬虫」· SCRIPT 代码 · 共 17 行

FIND_NODE	... <font face="Verdana,Arial,Helvetica,sans-serif" size="+1" color="#333366">	[next][END_OF_DOCUMENT]
STORE_TEXT	title	-1	-1	[next][END_OF_DOCUMENT]
FIND_NODE	... <font face="Verdana,Arial,Helvetica,sans-serif" color="#777744" size="-1">	[next][END_OF_DOCUMENT]
SAVE_TEXT	$meta	-1	-1	[next][END_OF_DOCUMENT]
REGEXP	$meta	/By\s+(.*)\s+\|\s+(.*)/i	[next][GOTO_TASK	8]
STORE_NODE	author	$1	[next][END_OF_DOCUMENT]
STORE_ISODATE	iso-date	MMM dd, yyyy	$2	[GOTO_TASK	9][END_OF_DOCUMENT]
STORE_ISODATE	iso-date	MMM dd, yyyy	$meta	[next][END_OF_DOCUMENT]
FIND_NODE	... #comment $value='content_start'	[next][END_OF_DOCUMENT]
SAVE_POS	$content_start	[next][END_OF_DOCUMENT]
FIND_NODE	... #comment $value='content_stop'	[next][END_OF_DOCUMENT]
SAVE_POS	$content_stop	[next][END_OF_DOCUMENT]
STORE_TEXT	content	$content_start	$content_stop	[next][END_OF_DOCUMENT]
STORE_LINKS	$content_start	$content_stop	[next][END_OF_DOCUMENT]
END_OF_ARTICLE		[next][END_OF_DOCUMENT]
END_OF_DOCUMENT		[next][END_OF_DOCUMENT]