slashdot.org.script

垂直搜索的网络爬虫

FIND_NODE	... <div class="article">	[next][END_OF_DOCUMENT]
FIND_NODE	... <div class="title">	[next][END_OF_DOCUMENT]
STORE_TEXT	title	-1	-1	[next][END_OF_DOCUMENT]
FIND_NODE	... <div class="details"> 	[next][END_OF_DOCUMENT]
SAVE_TEXT	$details	-1	-1	[next][END_OF_DOCUMENT]
REGEXP	$details	/Posted\s+by\s*(.+)\s*on\s+(.+?[PA]M)\s*(.+)/s	[next][END_OF_DOCUMENT]
STORE_NODE	author	$1	[next][END_OF_DOCUMENT]
STORE_ISODATE	iso-date	EEE MMM dd, '@'hh:mma	$2	[GOTO_TASK	10][next]
STORE_ISODATE	iso-date	EEE MMM dd, ''yy hh:mm a	$2	[next][END_OF_DOCUMENT]
FIND_NODE	... <div class="body">	[next][END_OF_DOCUMENT]
STORE_TEXT	content	-1	-1	[next][END_OF_DOCUMENT]
SAVE_POS	$links_start	[next][END_OF_DOCUMENT]
FIND_NODE	... </div class="storylinks">	[next][GOTO_TASK	16]
SAVE_POS	$links_end	[next][END_OF_DOCUMENT]
STORE_LINKS	$links_start	$links_end	[GOTO_TASK	17][END_OF_DOCUMENT]
STORE_LINKS	-1	-1	[next][END_OF_DOCUMENT]
END_OF_ARTICLE		[next][END_OF_DOCUMENT]
GOTO_TASK	1	[][]