searchenginelowdown.com.script

来自「垂直搜索的网络爬虫」· SCRIPT 代码 · 共 18 行

FIND_NODE	... div class="Post" ...		[next][END_OF_DOCUMENT]
SAVE_POS	$content_start				[next][END_OF_DOCUMENT]
FIND_NODE	... span class="PostTitle"		[next][GOTO_TASK	7]
STORE_TEXT	title	-1	-1			[next][END_OF_DOCUMENT]
FIND_NODE	... /span class="PostTitle"		[next][GOTO_TASK	7]
SAVE_POS	$content_start				[next][END_OF_DOCUMENT]
FIND_NODE	... span class="PostFooter"		[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]
FIND_NODE	div class="DateHeader" ...		[next][END_OF_DOCUMENT]
SAVE_TEXT	$date	-1	-1			[next][END_OF_DOCUMENT]
STORE_NODE	date	$date				[next][END_OF_DOCUMENT]
STORE_ISODATE	iso-date	MMMMM dd',' yyyy	$date	[next][END_OF_DOCUMENT]
SET_POS	$content_end					[next][END_OF_DOCUMENT]
END_OF_ARTICLE						[next][END_OF_DOCUMENT]
GOTO_TASK	1					[][]