标签：
试想一下，如果每天要收集100页网页数据甚至更多。如果采用人工收集会吐血，用程序去收集也就成为一个不二的选择。首先肯定会想到说用java、php、C#等高级语言，但这偏偏又有个登陆和验证码，搞到无所适从。还在为收集web端的数据感到苦恼吗？很高兴，你找对地方了。
应用场景：
1、需要每天大量重复收集web端的数据
2、web页面数据需要登陆后才能采集
3、web页面存在翻页
解决方案：
手工登陆，然后采用chrome插件的方式进行收集。当然你会说用selenium等自动化测试的方法进行收集更cool，而且可以每天自动收集，完全的自动化不用人工参与。但是作为chrome的忠实脑残粉，再者只需要前端的js、服务器端的接收文件、数据库就可以完美解决这一问题。再加上部署和操作简单。 脑残粉总有很多理由的嘛。好吧，就算是一种憋屈的曲线救国和实现方式吧。
思路：
帮助手册：http://open.chrome.360.cn/extension_dev/overview.html
实例：
抓取某电商后台订单数据
1、创建一个项目文件夹并引入所需文件：如D:\tool\chrome_server_plugin
jquery-2.1.1.min.js、icon.png
2、创建background.html
<html><head>
</head></html>
3、创建配置文件manifest.json文件
{
"name": "获取某电商后台订单信息",
"version": "1.0",
"manifest_version": 2,
"description": "*********获取某电商后台订单信息*********",
"browser_action": {
"default_icon": "icon.png"
},
"permissions": [
"webNavigation",
"tabs",
"contextMenus",
"http://服务器接受数据url/"
],
"background": {
"scripts": ["eventPage.js","jquery-2.1.1.min.js"]
},
"content_scripts": [
{
"matches": ["http://抓取页面url/*"],
"js": ["jquery-2.1.1.min.js", "contentscript.js"]
}
]
}
4、创建前端js文件contentscript.js
var totalPage;
var page = 0;
//注册前台页面监听事件
chrome.extension.onMessage.addListener(
function(request, sender, sendResponse) {
totalPage = $("input[name=totalPage]").val();
console.log("totalPage----------" + totalPage);
//console.log("msg----------contentscript.js" + request.greeting);
getOrderInfo( sendResponse );
});
//获取订单信息
function getOrderInfo( sendResponse ){
var flag = false;
payMoney = [];//货款金额
orderTime = [];//下单时间
$("tr[class=head] span").each(function(index){
spantxt = ‘‘;
spantxt = $(this).text();
if(spantxt.indexOf(‘货款金额：‘) > -1){
money = spantxt.substr(5);
//console.log(index + "---------payMoney-------货款金额：" + money);
payMoney.push(money);
}else if(spantxt.indexOf(‘下单时间：‘) > -1){
time = spantxt.substr(5);
//console.log(index + "---------orderTime-------下单时间：" + time);
orderTime.push(time);
}
});
paytype = [];//物流方式
yunfei = [];//运费
$("td[class=p-values]").each(function(index){
tdtxt = ‘‘;
tdtxt = $(this).text();
if(tdtxt.indexOf(‘货到付款‘) > -1){
paytype.push(‘货到付款‘);
}else{
paytype.push(‘在线支付‘);
}
yf_index = tdtxt.indexOf(‘运费:‘);
if(yf_index > -1){
temp = tdtxt.substr(yf_index);
temp_yf = temp.substr(3);
//console.log(index + "---------yunfei-------"+ temp +"===" + temp_yf);
yunfei.push(temp_yf);
}else{
yunfei.push(0);
}
//console.log(index + "---------tdtxt-------" + tdtxt);
});
orderStatus = [];//订单状态
users = [];//买家账号
remark = [];//备注
$("tr[class=content] td[class=t-c]").each(function(index){
tdtxt = ‘‘;
tdtxt = $(this).text().replace(/[\r\n]\ +/g,"");//将回车，换行，空格去掉
temp = index % 5;
if(1 == temp){
orderStatus.push(tdtxt);
//console.log(index + "---------statu-------" + tdtxt);
}else if(2 == temp){
users.push(tdtxt);
//console.log(index + "---------users-------" + tdtxt);
}else if(3 == temp){
remark.push(tdtxt);
//console.log(index + "---------remark-------" + tdtxt);
}
});
express = [];//快递单号
$("tr[class=content] td div[style=‘text-align: center;‘]").each(function(index){
tdtxt = ‘‘;
tdtxt = $(this).text().replace(/[\r\n]\ +/g,"");//将回车，换行，空格去掉
express.push(tdtxt);
//console.log( "============快递单号=======" + tdtxt);
});
orderInfo = [];
splitstr = "@_@";
$("tr[class=head] a[track=orderinfopagebeta]").each(function(index){
orderid = $(this).text();
//console.log("---------orderid-------" + orderid);
mycomment = $("a[id=comment_" + orderid + "]").attr(‘style‘).replace(/[\r\n]\ +/g,"");
if("display: block;" == mycomment){
mycomment = ‘已评价‘;
}else if(‘display:none;‘ == mycomment){
mycomment = ‘未评价‘;
}
tempshopid = $("img[id=remarkFlag_" + orderid + "]").attr(‘onclick‘);
shopidIndex = tempshopid.indexOf(",");
shopid = tempshopid.substr(shopidIndex + 1).replace(/[\)\;]/g,"");
//console.log("---------shopid-------" + shopid);
orderdesc = shopid + splitstr + orderid + splitstr + mycomment + splitstr + payMoney[index] + splitstr + orderTime[index] + splitstr + paytype[index] + splitstr + yunfei[index] + splitstr + orderStatus[index] + splitstr + users[index] + splitstr + remark[index] + splitstr + express[index];
console.log("---------orderdesc-------" + orderdesc);
orderInfo.push(orderdesc);
});
//chrome.extension.sendMessage({"orderInfo": orderInfo}, function(response) {});
page = parseInt($("a[class=current]").text());
totalPage = parseInt($("input[name=totalPage]").val());
console.log(page + "--page-----------totalPage---" + totalPage);
if(page < totalPage && page < 100){
console.log("---------next-------");
sendMsg( orderInfo, "next" );
$(‘a.next‘)[1].click();
}else{
console.log("---------end-------");
sendMsg( orderInfo, "end" );
}
//
}
//将获取内容传递给后台文件进行处理
function sendMsg( msg, cmd){
chrome.extension.sendMessage({"msg": msg, "cmd": cmd}, function(response) {});
}
5、创建后台处理js文件eventPage.js
var flag = false;
var currentTabId;
chrome.browserAction.onClicked.addListener(function(tab) {
counter = 40;
console.log(‘Turning ‘ + tab.url);
flag = true;
currentTabId = tab.id;
chrome.tabs.getSelected(null, function(tab) {
sendMsg(tab.id);
});
});
chrome.webNavigation.onCompleted.addListener(function( tab ){
console.log(‘加载完成***‘ + tab.tabId );
if( flag ){
sendMsg( tab.tabId );
}
});
chrome.extension.onMessage.addListener(
function(request, sender, sendResponse) {
console.log("*******evenPage.js***chrome.extension.onMessage.addListener");
articleData = request;
$.ajax({
url: "服务器接受数据URL/getOrderinfo.php",
cache: false,
type: "POST",
data: {‘orderinfo‘: request.msg.join("#$#")},
dataType: "json"
}).done(function(msg) {
console.log(‘*******************json*************‘ + msg.sql );
chrome.tabs.sendMessage(currentTabId, {"cmd":"end"},
function(response) {
console.log(response);
});
}).fail(function(jqXHR, textStatus) {
articleData.firstAccess = textStatus;
});
cmd = request.cmd;
if(‘end‘ == cmd){
flag = false;//确保不会自动运行
}
});
function sendSku2Info(colores){
chrome.tabs.query(
{active: true, currentWindow: true}, function(tabs) {
chrome.tabs.sendMessage(tabs[0].id, {"cmd":"ok", "sku": colores},
function(response) {
console.log(response);
});
});
}
function sendMsg( tabid ){
console.log(tabid + "--sendMsg()----eventPage.js");
chrome.tabs.sendMessage(tabid, {greeting: "start working"}, function(response) {
});
}
4、创建服务器接收文件getOrderInfo.php（放在服务器哦，亲！）
<?php
header("Content-type:text/html; charset=utf-8");
//include("./includes/global.php");
echo "***********************";
$con = mysql_connect("localhost","root","root");
echo "==============";
if (!$con)
{
die(‘Could not connect: ‘ . mysql_error());
}
mysql_select_db("test", $con);
//var_dump($_REQUEST);
$orderinfo = $_POST[‘orderinfo‘];
$orderArr = explode(‘#$#‘, $orderinfo);
print_r($orderArr);
$sql_value = array();
$split = "‘, ‘";
foreach($orderArr as $myorder){
$value = explode(‘@_@‘, $myorder);
echo "===========" . $value[10] ."</br>";
$sql = "INSERT INTO test(venderId, orderid, pingjia, money, ordertime, paytype, yunfei, orderstatu, user, remark, express) VALUES ";
$sql .= "(‘" . $value[0] . $split . $value[1] . $split . $value[2] . $split . $value[3] . $split . $value[4] . $split . $value[5] . $split . $value[6] . $split . $value[7] . $split . $value[8] . $split . $value[9] . $split . $value[10] . "‘) ON DUPLICATE KEY UPDATE remark = ‘" . $value[9] . "‘, pingjia = ‘" . $value[2] . "‘, orderstatu = ‘" . $value[7] . "‘, express = ‘" . $value[10] . "‘";
mysql_query($sql);
}
mysql_close($con);
?>
5、创建数据库表
CREATE TABLE `test` (
`id` int(10) unsigned NOT NULL AUTO_INCREMENT COMMENT ‘id‘,
`venderId` int(10) NOT NULL DEFAULT ‘0‘ COMMENT ‘商家ID‘,
`orderid` bigint(20) NOT NULL DEFAULT ‘0‘ COMMENT ‘订单ID‘,
`pingjia` varchar(100) NOT NULL DEFAULT ‘‘ COMMENT ‘订单发出后的状态（是否评价）‘,
`money` decimal(10,2) NOT NULL DEFAULT ‘0.00‘ COMMENT ‘订单金额‘,
`ordertime` varchar(100) NOT NULL DEFAULT ‘‘ COMMENT ‘下单时间‘,
`paytype` varchar(100) NOT NULL DEFAULT ‘‘ COMMENT ‘付款方式‘,
`yunfei` decimal(10,2) NOT NULL DEFAULT ‘0.00‘ COMMENT ‘运费‘,
`orderstatu` varchar(100) NOT NULL DEFAULT ‘‘ COMMENT ‘订单状态‘,
`user` varchar(255) NOT NULL DEFAULT ‘‘ COMMENT ‘订单用户‘,
`remark` varchar(255) NOT NULL DEFAULT ‘‘ COMMENT ‘备注‘,
`express` varchar(255) NOT NULL DEFAULT ‘‘ COMMENT ‘物流方式和运单号‘,
`shop_id` int(10) unsigned NOT NULL DEFAULT ‘0‘ COMMENT ‘店铺表ID‘,
`shop_name` varchar(255) NOT NULL DEFAULT ‘‘ COMMENT ‘店铺名称‘,
`stattime` int(11) NOT NULL DEFAULT ‘0‘ COMMENT ‘下单年月日‘,
PRIMARY KEY (`id`),
UNIQUE KEY `orderid` (`orderid`)
) ENGINE=MyISAM AUTO_INCREMENT=1 DEFAULT CHARSET=utf8 COMMENT=‘‘
注意：各文件中红色部分需要手工修改，此外如果修改js文件名，请在manifest.json中修改相应的配置信息即可。
插件加载步骤：
此示例仅供参考，有理解不到位或错误的还请指出。
标签：
原文地址：http://www.cnblogs.com/rwxwsblog/p/4490530.html
