[爬虫][瑞雪采集云]-案列11：外卖平台店铺抓取

案列说明：

分类：外卖平台

案例：饿了么平台信息抓取

业务流程描述：

【1】业务描述

image

【2】元素技术定位

image

---

抓取方法论：

【1】【找】找到URL地址。

【2】【定】确定每页面的抓取的元素。

【3】【编】瑞雪采集云编码。

---

编码实现：

package com.rx.crawler.open.emm;

import java.util.List;

import com.ruixuesoft.crawler.open.Keys;
import com.ruixuesoft.crawler.open.RxCrawler;
import com.ruixuesoft.crawler.open.RxCrawlerException;
import com.ruixuesoft.crawler.open.RxDatabase;
import com.ruixuesoft.crawler.open.RxNode;
import com.ruixuesoft.crawler.open.RxResult;
import com.ruixuesoft.crawler.open.RxRule;
import com.ruixuesoft.crawler.open.RxTask;

public class EmmRule1 implements RxRule {

private RxCrawler crawler = null;
private String homeUrl = "https://www.ele.me/home/";
private RxNode currentNode = null;

@Override
public RxResult execute(RxTask task, RxCrawler crawler, RxDatabase database)
        throws RxCrawlerException {
    this.crawler = crawler;
    this.searchOp();
    this.login();
    this.selectType();
    return new RxResult(200);
}

private void searchOp() {
    this.crawler.open(this.homeUrl);
    this.crawler.sleepSeconds(1);
    String cityXpath = "/html/body/div/div/div/div[2]/div[1]/div[1]/a";
    this.currentNode = this.crawler.getNodeByXpath(cityXpath);
    this.currentNode.click();
    String inputCityXpath = "/html/body/div/div/div/div[2]/div[1]/div[1]/div/div/div[2]/div[2]/input";
    this.currentNode = this.crawler.getNodeByXpath(inputCityXpath);
    this.currentNode.input("上海");
    String lengentNode = "/html/body/div/div/div/div[2]/div[1]/div[1]/div/div/div[2]/div[2]/ul/li";
    this.currentNode = this.crawler.getNodeByXpath(lengentNode);
    this.currentNode.click();

    String AddXpath = "/html/body/div/div/div/div[2]/div[1]/div[2]/form/input";
    this.currentNode = this.crawler.getNodeByXpath(AddXpath);
    this.currentNode.input("上海市徐汇区罗秀路1115-1号");
    String lengXpath = "/html/body/div/div/div/div[2]/div[1]/div[2]/div/ul/li/p[1]";
    this.currentNode = this.crawler.getNodeByXpath(lengXpath);
    this.currentNode.click();
}

private void login() {
    String longinXpath = "/html/body/div[4]/div[3]/div[2]/div[3]/a";
    this.currentNode = this.crawler.getNodeByXpath(longinXpath);
    this.currentNode.click();
    String passWordXpath = "/html/body/div[1]/div[1]/div[1]/div/a[2]";
    this.currentNode = this.crawler.getNodeByXpath(passWordXpath);
    this.currentNode.click();
    String namePath = "/html/body/div[1]/div[1]/div[2]/form/section[1]/input";
    this.currentNode = this.crawler.getNodeByXpath(namePath);
    this.currentNode.input("15566898605");
    String passPath = "/html/body/div[1]/div[1]/div[2]/form/section[2]/input";
    this.currentNode = this.crawler.getNodeByXpath(passPath);
    this.currentNode.input("1q22w#22E4r0221");

    String longinXpath1 = "/html/body/div[1]/div[1]/div[2]/form/button";
    this.currentNode = this.crawler.getNodeByXpath(longinXpath1);
    this.currentNode.click();

    this.crawler.back();
    this.crawler.back();
}

private void type(String type) {
    // String type1 = "/html/body/div[4]/div[3]/div[1]/div/a[8]";
    this.currentNode = this.crawler.getNodeByXpath(type);
    this.currentNode.click();
    String xpath = "//div[@class='rstblock-content']";
    this.crawler.pressKeys(1, Keys.PAGE_DOWN);
    this.crawler.sleepSeconds(1);
    this.crawler.pressKeys(1, Keys.PAGE_DOWN);
    this.crawler.sleepSeconds(1);
    this.crawler.pressKeys(1, Keys.PAGE_DOWN);
    this.crawler.sleepSeconds(1);

    List nodeList = this.crawler.getNodeListByXpath(xpath);
    System.out.println("size->" + nodeList.size());
    nodeList.forEach(rxnode -> System.out.println(rxnode.getText()));
    this.crawler.sleepSeconds(5);
}

private void selectType() {
    // 美食
    System.out.println("-----------------美食-----------------");
    this.type("/html/body/div[4]/div[3]/div[1]/div/a[2]");
    System.out.println("-----------------美食-----------------");
    // 果蔬生鲜
    System.out.println("-----------------果蔬生鲜-----------------");
    this.type("/html/body/div[4]/div[3]/div[1]/div/a[8]");
    System.out.println("-----------------果蔬生鲜-----------------");
    // 商店超市
    System.out.println("-----------------商店超市-----------------");
    this.type("/html/body/div[4]/div[3]/div[1]/div/a[9]");
    System.out.println("-----------------商店超市-----------------");
    // 鲜花绿植
    System.out.println("-----------------鲜花绿植-----------------");
    this.type("/html/body/div[4]/div[3]/div[1]/div/a[10]");

    System.out.println("-----------------鲜花绿植-----------------");
    // 医药健康
    System.out.println("-----------------医药健康-----------------");
    this.type("/html/body/div[4]/div[3]/div[1]/div/a[11]");
    System.out.println("-----------------医药健康-----------------");
}}

总结：

【1】瑞雪采集云外卖业务抓取。
【2】瑞雪采集云业务流程处理过程。
【3】Xpath技术相对路径。

www.web2data.com