blog.searchenginewatch.com.script

垂直搜索的网络爬虫

FIND_NODE	... <h2> 	[next][END_OF_DOCUMENT]
STORE_TEXT	title	-1	-1	[next][END_OF_DOCUMENT]
FIND_NODE	... </h2> 	[next][END_OF_DOCUMENT]
SAVE_POS	$content_start	[next][END_OF_DOCUMENT]
FIND_NODE	... <div class="posted">	[next][END_OF_DOCUMENT]
SAVE_POS	$content_end	[next][END_OF_DOCUMENT]
STORE_TEXT	content	$content_start	$content_end	[next][END_OF_DOCUMENT]
STORE_LINKS	$content_start	$content_end	[next][END_OF_DOCUMENT]
SAVE_TEXT	$meta	-1	-1	[next][END_OF_DOCUMENT]
STORE_NODE	meta	$meta	[next][END_OF_DOCUMENT]
REGEXP	$meta	/.*on\s+(\S+\s+\d+,\s*\d+)\s+.*/	[next][END_OF_DOCUMENT]
STORE_ISODATE	iso-date	MMM. dd',' yyyy	$1	[GOTO_TASK	14][next]
STORE_ISODATE	iso-date	MMM dd',' yyyy	$1	[next][END_OF_DOCUMENT]
END_OF_ARTICLE		[next][END_OF_DOCUMENT]
GOTO_TASK	1	[][]