google.blognewschannel.script

垂直搜索的网络爬虫

FIND_NODE	... <div class="post">	[next][END_OF_DOCUMENT]
FIND_NODE	... <h3 class="storytitle" 	[next][END_OF_DOCUMENT]
STORE_TEXT	title	-1	-1	[next][END_OF_DOCUMENT]
FIND_NODE	... <div class="storycontent"> 	[next][END_OF_DOCUMENT]
STORE_TEXT	content	-1	-1	[next][END_OF_DOCUMENT]
STORE_LINKS	-1	-1	[next][END_OF_DOCUMENT]
FIND_NODE	... <div class="meta">	[next][END_OF_DOCUMENT]
SAVE_POS	$date_start	[next][END_OF_DOCUMENT]
FIND_NODE	... <ul class="post-categories"> 	[next][END_OF_DOCUMENT]
SAVE_POS	$date_end	[next][END_OF_DOCUMENT]
SAVE_TEXT	$date_line	$date_start	$date_end	[next][END_OF_DOCUMENT]
REGEXP	$date_line	/Posted:\s*(.+) by (.+)/s	[next][END_OF_DOCUMENT]
STORE_ISODATE	iso-date	MMM dd',' yyyy	$1	[next][next]
STORE_ISODATE	iso-date	MM/dd/yyyy	$1	[next][next]
END_OF_ARTICLE		[next][END_OF_DOCUMENT]
GOTO_TASK	1	[][]
END_OF_DOCUMENT		[next][END_OF_DOCUMENT]