phantomJs使用总结

下载

下载 | PhantomJS

maven依赖

      <!--phantomjsdriver-->
        <dependency>
            <groupId>com.codeborne</groupId>
            <artifactId>phantomjsdriver</artifactId>
            <version>1.2.1</version>
        </dependency>

 使用封装

PhantomJsUtils

import org.apache.commons.io.FileUtils;
import org.openqa.selenium.Cookie;
import org.openqa.selenium.OutputType;
import org.openqa.selenium.WebDriver;
import org.openqa.selenium.phantomjs.PhantomJSDriver;
import org.openqa.selenium.phantomjs.PhantomJSDriverService;
import org.openqa.selenium.remote.DesiredCapabilities;

import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.concurrent.TimeUnit;

public class PhantomJsUtils {
    private static DesiredCapabilities dcaps = new DesiredCapabilities();
    private static final String ua = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36 baidu/3.2.1";
    private static boolean isLinux = false;

    static {

        String os = System.getProperty("os.name");
        String path = null;
        if (os.toLowerCase().contains("windows")) {
            path = "D:\\phantomjs-2.1.1-windows\\bin\\phantomjs.exe";
            System.setProperty("webdriver.chrome.driver", path);
        } else {
            path = "./phantomjs/phantomjs";
            System.setProperty("webdriver.chrome.driver", path);
            isLinux = true;
        }

        // 必要参数
        System.setProperty("phantomjs.binary.path", path);
//        DesiredCapabilities dcaps = new DesiredCapabilities();
        //ssl证书支持
        dcaps.setCapability("acceptSslCerts", true);
        //截屏支持
        dcaps.setCapability("takesScreenshot", true);

        //css搜索支持
        dcaps.setCapability("cssSelectorsEnabled", true);
        //js支持
        dcaps.setJavascriptEnabled(true);
        //驱动支持
        dcaps.setCapability(PhantomJSDriverService.PHANTOMJS_EXECUTABLE_PATH_PROPERTY,
                path);

        //ua
        dcaps.setCapability("phantomjs.page.settings.userAgent", ua);
        dcaps.setCapability("phantomjs.page.customHeaders.User-Agent", ua);

        //设置连接超时
        System.setProperty("sun.net.client.defaultConnectTimeout", "50");
        System.setProperty("sun.net.client.defaultReadTimeout", "50");


        //优化
        List<String> cli = new ArrayList<>();
        cli.add("--load-images=" + true);
//        cli.add("--output-encoding=" + "utf-8");
        cli.add("--disk-cache=yes");
        cli.add("--ignore-ssl-errors=true");
        cli.add("--debug=false");

        dcaps.setCapability(PhantomJSDriverService.PHANTOMJS_CLI_ARGS, cli);
        //代理
       /* String ip = "192.168.6.1:1984";
        // 启用磁盘缓存（在桌面服务缓存存储位置，默认为false）。也接受：[yes|no]。
        // --ignore-ssl-errors=[true|false]忽略SSL错误，例如过期或自签名证书错误（默认为false）。也接受：[yes|no]。
        // --proxy=address:port指定要使用的代理服务器（例如--proxy=192.168.1.42:8080）。
        String[] values = { "--disk-cache=yes", "--ignore-ssl-errors=true", "--proxy=" + ip };
        dcaps.setCapability(PhantomJSDriverService.PHANTOMJS_CLI_ARGS, values);*/
    }

    public static PhantomJSDriver initDriver() {
        PhantomJSDriver driver = new PhantomJSDriver(dcaps);
        //设置隐性等待（作用于全局）
        driver.manage().timeouts()
                .pageLoadTimeout(20, TimeUnit.SECONDS)
                .implicitlyWait(20, TimeUnit.SECONDS);
        return driver;
    }

    /**
     * 使用代理
     * @param proxy ip:port
     * @return
     */
    public static PhantomJSDriver initDriver(String proxy) {
        DesiredCapabilities dcaps = new DesiredCapabilities();
        String os = System.getProperty("os.name");
        String path = null;
        if (os.toLowerCase().contains("windows")) {
            path = "D:\\phantomjs-2.1.1-windows\\bin\\phantomjs.exe";
            System.setProperty("webdriver.chrome.driver", path);
        } else {
            path = "./phantomjs/phantomjs";
            System.setProperty("webdriver.chrome.driver", path);
            isLinux = true;
        }

        // 必要参数
        System.setProperty("phantomjs.binary.path", path);
//        DesiredCapabilities dcaps = new DesiredCapabilities();
        //ssl证书支持
        dcaps.setCapability("acceptSslCerts", true);
        //截屏支持
        dcaps.setCapability("takesScreenshot", true);

        //css搜索支持
        dcaps.setCapability("cssSelectorsEnabled", true);
        //js支持
        dcaps.setJavascriptEnabled(true);
        //驱动支持
        dcaps.setCapability(PhantomJSDriverService.PHANTOMJS_EXECUTABLE_PATH_PROPERTY,
                path);
        //ua
        dcaps.setCapability("phantomjs.page.settings.userAgent", ua);
        dcaps.setCapability("phantomjs.page.customHeaders.User-Agent", ua);
        //设置连接超时
        System.setProperty("sun.net.client.defaultConnectTimeout", "50");
        System.setProperty("sun.net.client.defaultReadTimeout", "50");
        //优化
        List<String> cli = new ArrayList<>();
        cli.add("--load-images=" + true);
//        cli.add("--output-encoding=" + "utf-8");
        cli.add("--disk-cache=yes");
        cli.add("--ignore-ssl-errors=true");
        cli.add("--debug=false");

        dcaps.setCapability(PhantomJSDriverService.PHANTOMJS_CLI_ARGS, cli);
        //代理
//        String ip = "192.168.6.1:1984";
        // 启用磁盘缓存（在桌面服务缓存存储位置，默认为false）。也接受：[yes|no]。
        // --ignore-ssl-errors=[true|false]忽略SSL错误，例如过期或自签名证书错误（默认为false）。也接受：[yes|no]。
        // --proxy=address:port指定要使用的代理服务器（例如--proxy=192.168.1.42:8080）。
        String[] values = { "--disk-cache=yes", "--ignore-ssl-errors=true", "--proxy=" + proxy };
        dcaps.setCapability(PhantomJSDriverService.PHANTOMJS_CLI_ARGS, values);

        PhantomJSDriver driver = new PhantomJSDriver(dcaps);
        //设置隐性等待（作用于全局）
        driver.manage().timeouts()
                .pageLoadTimeout(50, TimeUnit.SECONDS)
                .implicitlyWait(50, TimeUnit.SECONDS);
        return driver;
    }


    public static void close(WebDriver driver) {
        if (driver != null) {
            try {
                driver.quit();
            } catch (Exception e) {
                System.out.println("close error");
            }
        }

    }

    /**
     * 整页截图
     *
     * @param driver
     * @param destPath
     * @throws IOException
     */
    public static void screenshot(WebDriver driver, String destPath) throws IOException {
        File dfile = new File(destPath);
        if(dfile.exists()){
            dfile.delete();
        }
        File outFile = ((PhantomJSDriver) driver).getScreenshotAs(OutputType.FILE);
        FileUtils.moveFile(outFile, new File(destPath));

    }

    public static String getCookieStr(WebDriver driver) {
//        driver.navigate().refresh();
        String cookieStr = null;
        for (Cookie ck : driver.manage().getCookies()) {
            cookieStr += (ck.getName() + "=" + ck.getValue() + ";" + ck.getDomain() + ";" + ck.getPath() + ";" + ck.getExpiry() + ";" + ck.isSecure() + ";");
//            cookieStr += ck.getName() + "=" + ck.getValue()+";";
        }

        return cookieStr.substring(0, cookieStr.length() - 1).replaceFirst("null", "");
    }


    public static void main(String[] args) {
        WebDriver driver = initDriver("192.168.6.1:1984");
        String url = "https://en.wikipedia.org/wiki/China";
        driver.get(url);
        System.out.println(driver.getPageSource());

        close(driver);

    }
}

来源

phantomJs_Selenium_java 最全配置访问_菜鸡java程序员的博客-CSDN博客

Selenium+Phantomjs做Java爬虫_西红柿丶番茄的博客-CSDN博客_java phantomjs selenium