researchbuzz.script

垂直搜索的网络爬虫

FIND_NODE	... div class='blogbody' ...	[next][END_OF_DOCUMENT]
SAVE_POS	$blogbody_start		[next][next]
FIND_NODE	h3 class='date' ...	[GOTO_TASK	5][next]
FIND_NODE	h2 class='date' ...	[next][GOTO_TASK	8]
SAVE_TEXT	$date	-1	-1	[next][next]
STORE_NODE	date	$date		[next][next]
STORE_ISODATE	iso-date	MMMM dd, yyyy	$date	[next][next]
SET_POS	$blogbody_start			[next][next]
FIND_NODE	... h3 class='title'	[next][next]
STORE_TEXT	title	-1	-1	[next][next]
FIND_NODE	... /h3 class='title'	[next][next]
SAVE_POS	$content_start		[next][next]
FIND_NODE	... div class='posted'	[GOTO_TASK	14][next]
FIND_NODE	... span class='posted'	[next][next]
SAVE_POS	$content_end		[next][next]
STORE_TEXT	content	$content_start	$content_end	[next][next]
STORE_LINKS	$content_start	$content_end		[next][next]
END_OF_ARTICLE				[GOTO_TASK	1][GOTO_TASK	1]