爬虫配置文件

<?xml version="1.0" encoding="utf-8"?>
<template>
    <id>××××.com</id>
    <!--行政区域-->
    <page threads="false" dynamic="false" desc="index" setcookie="false" pattern="^http://www.×××××.com/search/category/\d+/\d+(/)?(r\d+)?(p\d+)?$">
        <enqueue>
            <xpath>//ul[@data-key='region']/li/a/@href</xpath>
            <xpath>//ul[@class='detail']/li[1]/a[1]/@href</xpath>
            <xpath>//div[@class='Pages']/a/@href</xpath>
        </enqueue>
    </page>
    <!--商品页-->
    <page threads="false" dynamic="false" desc="non-index" setcookie="false" pattern="^http://www.*****.com/shop/\d+(\?KID=\d+)?$">
        <check>
            <!--这个是无用的-->
            <xpath>//*[@id="pt1:pgl4"]</xpath>
            <pattern>\d+.00</pattern>
        </check>
    </page>
</template>

 

posted on 2014-08-29 10:21  雨渐渐  阅读(293)  评论(0编辑  收藏  举报

导航