1、贴出主要代码。这个不是python，python只涉及了服务端对信息提取结果的接受。主体是java + android + js。由于淘宝各模块都是二级子域名，不能只在一个页面完成所有请求，ajax不能跨域。需要加载不同的页面。以下是主要部分。js内容使用服务端分发。
这样做好处，即使不使用微服务，单台机器也能满足1000个用户在同一分钟提交账号密码请求登录，简化后台编写复杂度和减小服务器压力。密码 验证码的校验也更及时。
2、不是爬自己的信息，是获取别人 任意账号 + 密码的淘宝个人信息，如果是为了拿到自己的信息，搞这么多七七八八的那是闲的蛋疼。具体账号 密码是哪来的，置顶第一篇有介绍。
package com.touna.crawlmodule; import android.graphics.Bitmap;
import android.net.http.SslError;
import android.support.v7.app.AppCompatActivity;
import android.os.Bundle;
import android.util.Log;
import android.view.View;
import android.webkit.CookieManager;
import android.webkit.JavascriptInterface;
import android.webkit.SslErrorHandler;
import android.webkit.ValueCallback;
import android.webkit.WebChromeClient;
import android.webkit.WebSettings;
import android.webkit.WebView;
import android.webkit.WebViewClient;
import org.json.JSONObject; import com.xx.httprequest.CrawlResultSender;
import com.xx.view.LogUtil;
import com.xx.view.ViewUtil;
import com.xx.view.WebViewTimer; public class TaobaoActivity extends AppCompatActivity {
private static final String TAG = "MainActivity";
private static final String LOGINPAGEURL = "https://login.m.taobao.com/login.htm";//移动端登陆页面
private static final String MOBILEINDEXPAGEURL = "http://h5.m.taobao.com/mlapp/mytaobao.html";//移动端淘宝个人用户首页
private static final String PCINDEXPAGEURL = "https://www.taobao.com/";
private static final String BINDPAGEURL = "http://member1.taobao.com/member/fresh/account_management.htm";
private static final String COLLECTIONURL = "https://shoucang.taobao.com/nodejs/item_collect_chunk.htm";//收藏页面url
private static final String ADDRESSURL = "https://member1.taobao.com/member/fresh/deliver_address.htm";//收货地址url
private static final String MYPATHURL = "https://lu.taobao.com/newMyPath.htm";//我的足迹url
private static final String BOUGHTSHOPSURL = "https://favorite.taobao.com/list_bought_shops_n.htm";//已经购买的店铺
private static final String BOUGHTITEMSURL = "https://buyertrade.taobao.com/trade/itemlist/list_bought_items.htm";//已经购买的物品
private static final String SHOPCARTURL = "https://cart.taobao.com/cart.htm";//购物车URL
private static final String SAFESETTINGURL = "http://member1.taobao.com/member/fresh/certify_info.htm";//安全信息设置
private static final String TRADEINFOURL = "http://member1.taobao.com/member/fresh/account_profile.htm";//交易信息url
private static final String PERSONALINFOURL = "https://i.taobao.com/user/baseInfoSet.htm";//个人资料url
private static final String POINTSURL = "https://pages.tmall.com/wow/jifen/act/point-details";//积分URL
private static final String WEIBOURL = "http://member1.taobao.com/member/fresh/weibo_bind_management.htm";//绑定微博URL
private static final String REFUSEURL = "https://refund2.tmall.com/dispute/buyerDisputeList.htm?type=1&disputeType=1";//退货管理URL
private static final String HUABEIURL = "https://i.taobao.com/my_taobao.htm";//支付宝余额和花呗额度
private JSONObject dataJson=new JSONObject(); @Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_taobo);
startWebView();
} private void startWebView() {
WebView webView = findViewById(R.id.taobaoView);
final WebSettings settings = webView.getSettings();
settings.setUseWideViewPort(true);
settings.setLayoutAlgorithm(WebSettings.LayoutAlgorithm.NARROW_COLUMNS);
settings.setLoadWithOverviewMode(true);
settings.setJavaScriptEnabled(true);
webView.addJavascriptInterface(new JsInterface(), "JsInterface");
settings.setJavaScriptEnabled(true);
settings.setLoadWithOverviewMode(true);
settings.setSupportZoom(true);
settings.setDomStorageEnabled(true);
settings.setCacheMode(WebSettings.LOAD_NO_CACHE);
settings.setAllowFileAccess(true);
settings.setUseWideViewPort(true);
settings.setSupportMultipleWindows(true);
settings.setLoadsImagesAutomatically(true);
//settings.setBlockNetworkImage(false);
settings.setDefaultTextEncodingName("GBK");
webView.setVerticalScrollBarEnabled(true);
webView.setHorizontalScrollBarEnabled(true);
settings.setUserAgentString("Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36");
webView.setWebChromeClient(new WebChromeClient());
startWebViewClient(webView);
webView.loadUrl(LOGINPAGEURL);
} /**
* @param view WebView对象
* 初始化webviewClient
*/
private void startWebViewClient(WebView view) {
view.setWebViewClient(new WebViewClient() {
@Override
public void onReceivedSslError(WebView view, SslErrorHandler handler, SslError error) {
handler.proceed();
} @Override
public void onPageStarted(final WebView view, String url, Bitmap favicon) {
Log.e(TAG, "onPageStarted: " + url);
if (url.contains(LOGINPAGEURL)){
view.setVisibility(View.GONE);
}
} /**
* @param view 浏览器对象
* @param url 浏览器地址
*/
@Override
public void onPageFinished(final WebView view, String url) {
Log.e(TAG, "onPageFinished: " + url);
if (url.contains(LOGINPAGEURL)) {
ViewUtil.injectScriptFile(view, "loginPage/taobaoInit.js");
view.loadUrl("javascript:initLoginPage()");
new WebViewTimer(view, 300){
@Override
public void operateView(){
view.setVisibility(View.VISIBLE);
}
};
} if (url.contains(MOBILEINDEXPAGEURL)) {
//view.getSettings().setUserAgentString("Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36");
ViewUtil.setNoImage(view); //关闭图片
view.loadUrl(PCINDEXPAGEURL);
}
if (PCINDEXPAGEURL.equals(url)) {
view.loadUrl(REFUSEURL);
}
if (url.contains(REFUSEURL)) {
ViewUtil.injectScriptFile(view, "jquery.min.js"); //此处需要jquery!
ViewUtil.injectScriptFromInternet(view, "taobao/refund.js");
view.loadUrl("javascript:window.JsInterface.getReturnString(extractRefund());");
view.loadUrl(POINTSURL);
}
if (url.contains(POINTSURL)) {
Log.e(TAG, "onPageFinished: inject");
ViewUtil.injectScriptFromInternet(view, "taobao/point.js");
view.loadUrl("javascript:window.JsInterface.getReturnString(extractPoint());");
view.loadUrl(PERSONALINFOURL);
}
if (url.contains(PERSONALINFOURL)) {
ViewUtil.injectScriptFromInternet(view, "taobao/personalInformation.js");
view.loadUrl("javascript:window.JsInterface.getReturnString(extractPersonalInformation());");
view.loadUrl(COLLECTIONURL);
}
if (url.contains(COLLECTIONURL)) {
ViewUtil.injectScriptFromInternet(view, "taobao/collect.js");
view.loadUrl("javascript:window.JsInterface.getReturnString(extractCollect());");
view.loadUrl(ADDRESSURL);
}
if (url.contains(ADDRESSURL)) {
ViewUtil.injectScriptFromInternet(view, "taobao/delivery.js");
view.loadUrl("javascript:window.JsInterface.getReturnString(extractDelivery());");
view.loadUrl(MYPATHURL);
}
if (url.contains(MYPATHURL)) {
ViewUtil.injectScriptFromInternet(view, "taobao/footprint.js");
view.loadUrl("javascript:window.JsInterface.getReturnString(extractFootprint());");
view.loadUrl(BOUGHTSHOPSURL);
}
if (url.contains(BOUGHTSHOPSURL)) {
ViewUtil.injectScriptFromInternet(view, "taobao/havaboughtStore.js");
view.loadUrl("javascript:window.JsInterface.getReturnString(extractHaveBoughtStore());");
view.loadUrl(BOUGHTITEMSURL);
}
if (url.contains(BOUGHTITEMSURL)) {
ViewUtil.injectScriptFromInternet(view, "taobao/havebought.js");
view.loadUrl("javascript:window.JsInterface.getReturnString(extractHaveBought());");
view.loadUrl(SHOPCARTURL);
}
if (url.contains(SHOPCARTURL)) {
ViewUtil.injectScriptFromInternet(view, "taobao/shoppingCart.js");
view.loadUrl("javascript:window.JsInterface.getReturnString(extractShoppingCart());");
view.loadUrl(SAFESETTINGURL);
}
if (url.contains(SAFESETTINGURL)) {
ViewUtil.injectScriptFromInternet(view, "taobao/safeSettings.js");
view.loadUrl("javascript:window.JsInterface.getReturnString(extractSafeSettings());");
view.loadUrl(TRADEINFOURL);
}
if (url.contains(TRADEINFOURL)) {
ViewUtil.injectScriptFromInternet(view, "taobao/tradeInfo.js");
view.loadUrl("javascript:window.JsInterface.getReturnString(extractTradeInfo());");
view.loadUrl(WEIBOURL);
}
if (url.contains(WEIBOURL)) {
ViewUtil.injectScriptFromInternet(view, "taobao/weibo.js");
view.loadUrl("javascript:window.JsInterface.getReturnString(extractWeibo());");
view.loadUrl(BINDPAGEURL); }
if (url.contains(BINDPAGEURL)) {
ViewUtil.injectScriptFromInternet(view, "taobao/alipayBinding.js");
view.loadUrl("javascript:window.JsInterface.getReturnString(extractAlipay());");
view.loadUrl(HUABEIURL);
} if (url.contains(HUABEIURL)) {
ViewUtil.injectScriptFromInternet(view, "taobao/huabei.js");
view.loadUrl("javascript:clickHuabei1()"); new WebViewTimer(view, 2000){
@Override
public void operateView(){
view.loadUrl("javascript:clickHuabei2()");
}
}; new WebViewTimer(view, 4000){
@Override
public void operateView(){
view.evaluateJavascript("extractHuabei()", new ValueCallback<String>() {
@Override
public void onReceiveValue(String s) {
Log.e(TAG, "onReceiveValue: "+s );
String jsonStr = ViewUtil.getStrLikeJson(s);
ViewUtil.reconsituteJSon(jsonStr, dataJson);
ViewUtil.showLargeLog(dataJson.toString());
CrawlResultSender.sendToweb("taobao", dataJson.toString());
}
});
}
};
}
}
});
} class JsInterface {
private static final String TAG = "JSInterface";
@JavascriptInterface
public void getReturnString(String returnValue) throws Exception{
Log.e(TAG,"当前项返回值是： " + returnValue);
ViewUtil.reconsituteJSon(returnValue,dataJson);
}
}
}
贴出其中一个js实例，例如提取用户所收藏物品。这里不是用直接翻页，使用的是ajax以提升效率，ajax一定需要同步方式。由于此接口是返回的页面不是json，可以用css选择器。
/**
* Created by ㄟ(▔=▔)ㄏ on 2018/1/5.
*/
/*
* https://shoucang.taobao.com/nodejs/item_collect_chunk.htm?ifAllTag=0&tab=0&tagId=&categoryCount=0&type=0&tagName=&categoryName=&needNav=false&startRow=0
* 提取收藏的宝贝
* */
function myajax(opt) {
opt = opt || {};
opt.type = opt.type.toUpperCase() || 'POST';
opt.url = opt.url || '';
opt.async = opt.async || false;
opt.data = opt.data || null;
opt.success = opt.success || function () {};
var xmlHttp = null;
if (XMLHttpRequest) {
xmlHttp = new XMLHttpRequest();
}
else {
xmlHttp = new ActiveXObject('Microsoft.XMLHTTP');
}
var params = [];
for (var key in opt.data){
params.push(key + '=' + opt.data[key]);
}
var postData = params.join('&');
if (opt.type.toUpperCase() === 'POST') {
xmlHttp.open(opt.type, opt.url, opt.async);
xmlHttp.setRequestHeader('Content-Type', 'application/x-www-form-urlencoded;charset=utf-8');
xmlHttp.send(postData);
}
else if (opt.type.toUpperCase() === 'GET') {
xmlHttp.open(opt.type, opt.url + '?' + postData, opt.async);
xmlHttp.send(null);
}
return xmlHttp;
} function extractCollect() { var collectList = [];
function extractCollectInner(p) {
console.debug("当前是第 " + p + "页");
var p = p || 0;
var startRow = p*30 ;
var url = 'https://shoucang.taobao.com/nodejs/item_collect_chunk.htm?ifAllTag=0&tab=0&tagId=&categoryCount=0&type=0&tagName=&categoryName=&needNav=false&startRow='+ startRow;
var htmlObj = myajax({
type: 'GET',
url: url ,
async: false
});
var htmlStr = htmlObj.responseText;
if (htmlStr.indexOf("J_FavListItem") > 0) { //判断页面是否为空不能继续翻页了
var collectSelectorList = document.querySelectorAll('li.J_FavListItem'); //使用原生js的querySelector css选择器方法
for (var i=0; i< collectSelectorList.length; i++) {
console.debug(i);
var collectName = collectSelectorList[i].querySelector('a.img-item-title-link').title;
var collectUrl = collectSelectorList[i].querySelector('a.img-item-title-link').href;
var collectPriceElement = collectSelectorList[i].querySelector('.g_price strong');
collectPriceElement ? collectPrice = collectPriceElement.innerText : collectPrice = "宝贝已失效"; //三元运算符，找不到价格元素，说明该宝贝已失效
var collectObj = {'collectName': collectName, 'collectUrl': collectUrl,'collectPrice':collectPrice};
console.info(collectObj);
collectList.push(collectObj);
}
console.info(url);
if (p < 3){ //最多只翻3页，每页30个收藏
extractCollectInner(p + 1); //翻页回调自己
}
}
return '{"collectInfo":' + JSON.stringify(collectList) + '}';
} return extractCollectInner();
} //extractCollect();
这就是唯一登录淘宝获取信息的方法，不管是什么语言java py，不管是用httpclient urlconnection还是urllib requests 想达到 本篇的目的，可能性为0。不服不信的可以用httpclient urllib试试，光是一个接口登录淘宝，网上就在悬赏5万人民币了，就不说提取信息了，单是把这个接口登录淘宝解决，相当于几个月的工资了。