google.weblogsinc.com.script

来自「垂直搜索的网络爬虫」· SCRIPT 代码 · 共 16 行

FIND_NODE	... <div id=~/p\d+/>	[next][END_OF_DOCUMENT]
FIND_NODE	... <h2>	[next][END_OF_DOCUMENT]
STORE_TEXT	title	-1	-1	[next][END_OF_DOCUMENT]
FIND_NODE	... <p class="byline">	[next][END_OF_DOCUMENT]
SAVE_TEXT	$meta	-1	-1	[next][END_OF_DOCUMENT]
REGEXP	$meta	/Posted\s+(.*) by/	[next][END_OF_DOCUMENT]
STORE_ISODATE	iso-date	MMM dd'th' yyyy hh:mma	$1	[GOTO_TASK	11][next]
STORE_ISODATE	iso-date	MMM dd'rd' yyyy hh:mma	$1	[GOTO_TASK	11][next]
STORE_ISODATE	iso-date	MMM dd'nd' yyyy hh:mma	$1	[GOTO_TASK	11][next]
STORE_ISODATE	iso-date	MMM dd'st' yyyy hh:mma	$1	[GOTO_TASK	11][END_OF_DOCUMENT]
FIND_NODE	... <div class="post">	[next][END_OF_DOCUMENT]
STORE_TEXT	content	-1	-1	[next][END_OF_DOCUMENT]
STORE_LINKS	-1	-1	[next][END_OF_DOCUMENT]
END_OF_ARTICLE		[next][END_OF_DOCUMENT]
GOTO_TASK	1	[][]