Java之网络爬虫WebCollector2.1.2+selenium2.44+phantomjs2.1.1

一、简介

版本匹配： WebCollector2.12 + selenium2.44.0 + phantomjs 2.1.1 

动态网页爬取: WebCollector + selenium + phantomjs

说明：这里的动态网页指几种可能：1）需要用户交互，如常见的登录操作；2）网页通过JS / AJAX动态生成，如一个html里有<div id="test"></div>，通过JS生成<div id="test"><span>aaa</span></div>。

这里用了WebCollector 2进行爬虫，这东东也方便，不过要支持动态关键还是要靠另外一个API -- selenium 2（集成htmlunit 和 phantomjs）.

二、示例

/**  * Project Name:padwebcollector  * File Name:DiscussService.java  * Package Name:com.pad.service  * Date:2018年7月25日下午4:59:44  * Copyright (c) 2018 All Rights Reserved.  * */    package com.pad.service;  import java.util.ArrayList;import java.util.List;import org.openqa.selenium.By;import org.openqa.selenium.WebDriver;import org.openqa.selenium.WebElement;import org.openqa.selenium.phantomjs.PhantomJSDriver;import cn.edu.hfut.dmic.webcollector.crawler.DeepCrawler;import cn.edu.hfut.dmic.webcollector.model.Links;import cn.edu.hfut.dmic.webcollector.model.Page;import com.pad.entity.DiscussInfo;import com.pad.impl.DiscussInfoImpl;public class DiscussService extends DeepCrawler {        public DiscussService(String crawlPath) {        super(crawlPath);        // TODO Auto-generated constructor stub    }        @Override    public Links visitAndGetNextLinks(Page page) {        // TODO Auto-generated method stub        WebDriver driver = getWebDriver(page);        Analysis analysis = new Analysis();        List
     
       discusslist = new ArrayList();        List
      
        list = driver.findElements(By.className("content"));        int i = 1;        String r_msg = "观望";        for(WebElement el : list) {            if(!"".equals(el.getText().trim())){                r_msg = analysis.analysis(el.getText());            }                        DiscussInfo info = new DiscussInfo();            info.setLine_no(String.valueOf(i));            info.setResult_msg(r_msg);            info.setContent_msg(el.getText());            discusslist.add(info);            System.out.println(i+" "+el.getText());            i++;        }        driver.close();        driver.quit();                DiscussInfoImpl impl = new DiscussInfoImpl();        impl.saveData(discusslist);        return null;    }        public static WebDriver getWebDriver(Page page) {        System.setProperty("phantomjs.binary.path", "D:\\******\\phantomjs.exe");        WebDriver driver = new PhantomJSDriver();        driver.get(page.getUrl());        return driver;    }    public static void main(String[] args) {        DiscussService dis=new DiscussService("discuss");   　　　　 dis.addSeed("https://*******/index/0000012");        try {        dis.start(1);    } catch (Exception e) {        e.printStackTrace();    }    }}
      
     

注意：WebCollector2.12 和WebCollector2.7区别类 extends 继承分别为 DeepCrawler 和 BreadthCrawler；