selenium 爬虫 - 技术栈

selenium 可以动态爬取网页数据，就像真实用户操作浏览器一样，从终端用户的角度测试应用程序，WebDriver通过原生浏览器支持或者浏览器扩展直接控制浏览器

因为selenuim对浏览器的版本存在兼容问题，顾需要针对指定浏览器下载指定版本。

1、添加依赖

XML 复制代码

        <dependency>
            <groupId>org.seleniumhq.selenium</groupId>
            <artifactId>selenium-java</artifactId>
            <version>4.11.0</version>
        </dependency>
        <dependency>
            <groupId>com.google.guava</groupId>
            <artifactId>guava</artifactId>
            <version>32.1.2-jre</version>
        </dependency>

2、工具类

java 复制代码

import cn.hutool.core.collection.CollectionUtil;
import com.google.common.collect.Lists;
import lombok.RequiredArgsConstructor;
import lombok.extern.slf4j.Slf4j;
import org.openqa.selenium.By;
import org.openqa.selenium.WebDriver;
import org.openqa.selenium.WebElement;
import org.openqa.selenium.chrome.ChromeDriver;
import org.openqa.selenium.chrome.ChromeOptions;
import org.openqa.selenium.edge.EdgeDriver;
import org.openqa.selenium.edge.EdgeOptions;
import org.openqa.selenium.firefox.FirefoxDriver;
import org.openqa.selenium.firefox.FirefoxOptions;
import org.springframework.stereotype.Component;

import java.util.ArrayList;
import java.util.Collections;
import java.util.List;
import java.util.Map;

/**
 * Selenium 工具类
 *
 * @author kou
 */
@Slf4j
@RequiredArgsConstructor
@Component
public class SeleniumUtil {

    private final ReptileProperties reptileProperties;

    /**
     * 获取chromeDriver
     *
     * @return chromeDriver
     */
    public WebDriver chromeDriver() {

        // 加载驱动路径
        System.setProperty("webdriver.chrome.driver", "D:/chromedriver.exe");
        // Chrome默认不允许跨机器调试，需要给启动命令加上白名单
        System.setProperty("webdriver.chrome.whitelistedIps", "");

        ChromeOptions options = new ChromeOptions();
        // 开启一个实验性参数excludeSwitches，用来隐藏window.navigator.webdriver返回true,这个参数必须是List
        options.setExperimentalOption("useAutomationExtension", false);
        // 开启开发者模式
        options.setExperimentalOption("excludeSwitches", Lists.newArrayList("enable-automation"));
        // 发现主要是这句是关键
        options.addArguments("--disable-blink-features=AutomationControlled");
        // options.addArguments("--incognito");
        // options.addArguments("--disable-infobars");
        //options.addArguments("user-agent=Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36");
        options.addArguments("user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36");

        // 禁用沙箱
        options.addArguments("--no-sandbox");
        // 无头浏览器，这样不会打开浏览器窗口
        // options.addArguments("--headless");
        // options.addArguments("--disable-gpu");
        options.addArguments("--remote-allow-origins=*");

        // 初始化一个谷歌浏览器实例，实例名称叫driver
        WebDriver driver = new ChromeDriver(options);

        return driver;
    }

    /**
     * 获取edgeDriver
     *
     * @return edgeDriver
     */
    public WebDriver edgeDriver() {
        // 加载驱动路径
        System.setProperty("webdriver.edge.driver", "D:/msedgedriver.exe");

        EdgeOptions options = new EdgeOptions();
        // 开启一个实验性参数excludeSwitches，用来隐藏window.navigator.webdriver返回true,这个参数必须是List
        options.setExperimentalOption("useAutomationExtension", false);
        //开启开发者模式
        options.setExperimentalOption("excludeSwitches", Lists.newArrayList("enable-automation"));
        // 发现主要是这句是关键
        options.addArguments("--disable-blink-features=AutomationControlled");
        options.addArguments("--incognito", "--disable-infobars");
        // options.addArguments("user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36");
        options.addArguments("user-agent=Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36");

        // 禁用沙箱
        options.addArguments("--no-sandbox");
        // 无头浏览器，这样不会打开浏览器窗口
        // options.addArguments("--headless");
        options.addArguments("--disable-gpu");
        options.addArguments("--remote-allow-origins=*");

        // 初始化一个谷歌浏览器实例，实例名称叫driver
        WebDriver driver = new EdgeDriver(options);

        return driver;
    }

    /**
     * 获取firefoxDriver
     *
     * @return firefoxDriver
     */
    public WebDriver firefoxDriver() {
        // 加载驱动路径
        System.setProperty("webdriver.gecko.driver", "D:/geckodriver.exe");
        System.setProperty("webdriver.chrome.whitelistedIps", "");

        FirefoxOptions options = new FirefoxOptions();
        options.addArguments("user-agent=Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36");

        // 无头浏览器，这样不会打开浏览器窗口
        options.addArguments("--headless");

        // 初始化一个谷歌浏览器实例，实例名称叫driver
        WebDriver driver = new FirefoxDriver(options);

        return driver;
    }

    /**
     * 获取表头
     *
     * @param table 表格
     * @return 表头
     */
    public List<String> getTableHead(WebElement table) {

        log.info("开始解析表头...");
        // 获取表头
        WebElement head = table.findElement(By.tagName("thead"));
        if (null == head) {
            return Collections.emptyList();
        }
        List<WebElement> headths = head.findElements(By.tagName("th"));
        List<String> headList = new ArrayList<>(headths.size());
        headths.forEach(t -> {
            headList.add(t.getText());
        });
        log.info("表头解析完成！！！");
        return headList;
    }

    /**
     * 获取表数据
     *
     * @param table 表格
     * @return 表头
     */
    public List<List<String>> getTableBody(WebElement table) {

        log.info("开始解析表数据...");
        // 获取表头
        WebElement tbody = table.findElement(By.tagName("tbody"));
        if (null == tbody) {
            return Collections.emptyList();
        }
        // 获取body数据行
        List<WebElement> bodyTrs = tbody.findElements(By.tagName("tr"));
        if (CollectionUtil.isEmpty(bodyTrs)) {
            return Collections.emptyList();
        }
        List<List<String>> bodyDatas = new ArrayList<>(bodyTrs.size());
        bodyTrs.stream().forEach(r -> {
            List<WebElement> tds = r.findElements(By.tagName("td"));
            List<String> rows = new ArrayList<>(tds.size());
            tds.forEach(d -> {
                rows.add(d.getText());
            });
            bodyDatas.add(rows);
        });
        log.info("表数据解析完成！！！");
        return bodyDatas;
    }

    /**
     * 将参数转化为路径参数
     *
     * @param params 参数
     * @return 路径参数
     */
    public String convertPathParams(Map<String, Object> params) {

        if (CollectionUtil.isEmpty(params)) {
            return "";
        }
        StringBuffer path = new StringBuffer();

        for (Map.Entry<String, Object> p : params.entrySet()) {
            path.append(p.getKey()).append("=").append(p.getValue().toString()).append("&");
        }
        return path.substring(0, path.length() - 1);
    }

}

3、爬取数据

java 复制代码

import lombok.RequiredArgsConstructor;
import lombok.extern.slf4j.Slf4j;
import org.openqa.selenium.By;
import org.openqa.selenium.WebDriver;
import org.openqa.selenium.WebElement;
import org.openqa.selenium.support.ui.ExpectedCondition;
import org.openqa.selenium.support.ui.WebDriverWait;
import org.springframework.stereotype.Service;
import org.springframework.util.StringUtils;

import java.time.Duration;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.concurrent.TimeUnit;

/**
 * 数据接口实现类
 *
 * @author kou
 */
@Slf4j
@RequiredArgsConstructor
@Service
public class DataServiceImpl {


    private final SeleniumUtil seleniumUtil;

    /**
     * 获取页面数据
     *
     * @return 数据
     */
    @Override
    public Map<String, Object> getHtmlData() {
        try {

            Map<String, Object> data = new HashMap<>();
            
            String url = "url";
            Map<String, Object> params = new HashMap<>();
            params.put("pageNum", 1);
            params.put("pageSize", 1000);

            String fullUrl = url + seleniumUtil.convertPathParams(params);
            WebDriver driver = seleniumUtil.firefoxDriver();
            driver.get(fullUrl);

            // 打开一个站点
            log.info("开始访问：{}", fullUrl);
            driver.get(fullUrl);

            String title = driver.getTitle();
            log.info("网页：{}", title);

            // 获取表格数据
            WebElement table = driver.findElement(By.id("table"));
            //显式等待,针对某个元素等待,等待超时时间100s,2s检测一次
            WebDriverWait wait = new WebDriverWait(driver, Duration.ofSeconds(100), Duration.ofSeconds(2));
            // wait.until(ExpectedConditions.presenceOfElementLocated(By.id("table")));
            wait.until(new ExpectedCondition<WebElement>() {
                @Override
                public WebElement apply(WebDriver text) {
                    log.info("开始检查tbody数据是否已加载");
                    WebElement table = text.findElement(By.id("table")).findElement(By.tagName("tbody"));
                    if (!table.isDisplayed()) {
                        log.info("检查结果：tbody数据未加载完，等待加载...");
                        return null;
                    }
                    log.info("检查结果：tbody数据加载完成!!!");
                    return table;
                }
            });

            // 获取表头
            List<String> headList = seleniumUtil.getTableHead(table);
            List<List<String>> bodyList = seleniumUtil.getTableBody(table);
            data.put("header", headList);
            data.put("body", bodyList);
            driver.close();
            return data;
        } catch (Exception e) {
            throw new RuntimeException(e);
        }
    }

}