HttpClient抓取動態頁面

本文轉載自查看原文 2015-09-01 14:59 1885 網絡爬蟲

編寫不易，轉載請注明（http://shihlei.iteye.com/blog/2067707）！

一概述

? ? HttpClient適合處理靜態資源，網絡爬蟲等類似應用很大程度需要處理動態網頁（內容有js填充，如百度圖片，body里基本沒有數據，碰到最麻煩的是新浪微博列表頁）。將網頁下載后，結合JS和Dom模型還原網頁，我目前還未攻破，但在下載層還原網頁，HtmlUnit是一種解決方案，雖然對JS的支持還是不完美。

? ? HtmlUnit其實是自動化測試工具，集成了下載（HttpClient），Dom（NekoHtml），驅動JS（Rhino）。有一定的網頁渲染能力，由於會驅動Dom，會消耗些CPU，內存。

? ?本文描述HTMLUnit請求響應，設置cookies，設置代理，驅動JS等方法。

二版本

<dependency>
	<groupId>net.sourceforge.htmlunit</groupId>
	<artifactId>htmlunit</artifactId>
	<version>2.14</version>
</dependency>

三典型功能

1）打開google搜索百度

/**
 * 打開google 搜索百度
 * 
 * @param args
 * @throws Exception
 */
public static void main(String[] args) throws Exception {
	String url = "http://www.google.com.hk";

	final WebClient webClient = new WebClient();
	HtmlPage htmlPage = webClient.getPage(url);

	// HtmlUnit dom模型
	// 獲取表單 ,獲得form標簽name屬性=f
	HtmlForm form = htmlPage.getFormByName("f");
	// 獲取輸入框, 獲取 input標簽 ，name屬性=q
	HtmlTextInput text = form.getInputByName("q");
	// 搜索百度
	text.setText("baidu");
	// 獲取提交按鈕
	HtmlSubmitInput button = form.getInputByName("btnG");
	// 提交表單
	HtmlPage listPage = button.click();

	System.out.println(listPage.asXml());
         
      webClient.closeAllWindows();
}

2）獲取動態頁面

/**
 * 獲取百度圖片js后的內容
 * 
 * @throws Exception
 */
public void demo2() throws Exception {
	String url = "http://image.baidu.com/i?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=result&fr=&sf=1&fmq=1400328281672_R&pv=&ic=0&nc=1&z=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&word=html";

	final WebClient webClient = new WebClient();

	// 1 啟動JS
	webClient.getOptions().setJavaScriptEnabled(true);
	// 2 禁用Css，可避免自動二次請求CSS進行渲染
	webClient.getOptions().setCssEnabled(false);
	// 3 啟動客戶端重定向
	webClient.getOptions().setRedirectEnabled(true);

	// 4 js運行錯誤時，是否拋出異常
	webClient.getOptions().setThrowExceptionOnScriptError(false);
	// 5 設置超時
	webClient.getOptions().setTimeout(50000);
	
	HtmlPage htmlPage = webClient.getPage(url);
	// 等待JS驅動dom完成獲得還原后的網頁
	webClient.waitForBackgroundJavaScript(10000);
	// 網頁內容
	System.out.println(htmlPage.asXml());
	webClient.closeAllWindows();
}

四樣例

（1）請求響應

/**
 * Get請求
 * @param url
 * @return
 * @throws Exception
 */
public static byte[] sendGetRequest(String url) throws Exception{
        WebClient webClient = new WebClient();
	WebRequest webRequest = new WebRequest(new URL(url));
	webRequest.setHttpMethod(HttpMethod.GET);
	return sendRequest(webClient,webRequest);
}

/**
 * Post 請求
 * 
 * @param url
 * @param params
 * @return
 * @throws Exception
 */
public static byte[] sendPostRequest(String url,Map<String,String> params) throws Exception{
        WebClient webClient = new WebClient();
	WebRequest webRequest = new WebRequest(new URL(url));
	webRequest.setHttpMethod(HttpMethod.POST);
	if (params != null && params.size() > 0) {
		for (Entry<String, String> param : params.entrySet()) {
			webRequest.getRequestParameters().add(new NameValuePair(param.getKey(), param.getValue()));
		}
	}
	return sendRequest(webClient,webRequest);
}

//底層請求
private static byte[] sendRequest(WebClient webClient,WebRequest webRequest) throws Exception{
	byte[] responseContent = null;
	Page page = webClient.getPage(webRequest);
	
	WebResponse webResponse = page.getWebResponse();
	
	int status = webResponse.getStatusCode();
	
	System.out.println("Charset : " + webResponse.getContentCharset());

	System.out.println("ContentType : " + webResponse.getContentType());

	// 讀取數據內容
	if (status==200) {
		if (page.isHtmlPage()) {
			// 等待JS執行完成，包括遠程JS文件請求，Dom處理
		     webClient.waitForBackgroundJavaScript(10000);
                     // 使用JS還原網頁
		     responseContent = ((HtmlPage) page).asXml().getBytes();
		} else {
			InputStream bodyStream = webResponse.getContentAsStream();
			responseContent = ByteStreams.toByteArray(bodyStream);
			bodyStream.close();
		}
	}
	// 關閉響應流
	webResponse.cleanUp();

	return responseContent;
}

（2）配置JS，CSS，超時，重定向

private void configWebClient(WebClient webClient) {
	// 設置webClient的相關參數
	// 1 啟動JS
	webClient.getOptions().setJavaScriptEnabled(true);
	// 2 禁用Css，可避免自動二次請求CSS進行渲染
	webClient.getOptions().setCssEnabled(false);
	// 3 啟動客戶端重定向
	webClient.getOptions().setRedirectEnabled(true);

	// 4 js運行錯誤時，是否拋出異常
	webClient.getOptions().setThrowExceptionOnScriptError(false);
	// 5 設置超時
	webClient.getOptions().setTimeout(timeout);
}

（3）代理

private void setProxy(WebClient webClient,HttpProxy proxy) {
	ProxyConfig proxyConfig = webClient.getOptions().getProxyConfig();
	proxyConfig.setProxyHost(proxy.getHost());
	proxyConfig.setProxyPort(proxy.getPort());

	DefaultCredentialsProvider credentialsProvider = (DefaultCredentialsProvider) webClient
			.getCredentialsProvider();
	credentialsProvider.addCredentials(proxy.getUser(), proxy.getPassword());
}

?輔助類：

package x.http.core;


/**
 * Http代理
 * 
 * @author shilei
 * 
 */
public class HttpProxy {
	private String proxy = "http";
	private String host;
	private int port;
	private String user;
	private String password;
	public String getProxy() {
		return proxy;
	}
	public void setProxy(String proxy) {
		this.proxy = proxy;
	}
	public String getHost() {
		return host;
	}
	public void setHost(String host) {
		this.host = host;
	}
	public int getPort() {
		return port;
	}
	public void setPort(int port) {
		this.port = port;
	}
	public String getUser() {
		return user;
	}
	public void setUser(String user) {
		this.user = user;
	}
	public String getPassword() {
		return password;
	}
	public void setPassword(String password) {
		this.password = password;
	}
}

（4）Cookies：可以用於認證數據設置

1）設置Cookies

private void setCookies(WebClient webClient,String domain, Map<String, String> cookies) {
	if (cookies != null && cookies.size() > 0) {
		webClient.getCookieManager().setCookiesEnabled(true);// enable
																// cookies
		for (Entry<String, String> c : cookies.entrySet()) {
			Cookie cookie = new Cookie(domain, c.getKey(), c.getValue());
			webClient.getCookieManager().addCookie(cookie);
		}
	}
}

2）獲取響應Cookies

private Map<String, String> getResponseCookies(WebClient webClient) {
	Set<Cookie> cookies = webClient.getCookieManager().getCookies();
	Map<String, String> responseCookies = Maps.newHashMap();
	for (Cookie c : cookies) {
		responseCookies.put(c.getName(), c.getValue());
	}
	return responseCookies;
}

3）刪除所有Cookies

/**
 * 清除所有cookie
 */
public void clearCookies(WebClient webClient) {
	webClient.getCookieManager().clearCookies();
}

?（5）驅動JS：

可實現自動化流程，如驅動表單提交，獲取表單提交后的頁面

如登錄后頁面：

public void doWeb(Page page) {
	if (page instanceof HtmlPage) {
		StringBuilder js = new StringBuilder();
		js.append("document.getElementsByName('username')[1].value='").append(WeiboAccount.USERNAME)
				.append("';");
		js.append("document.getElementsByName('password')[1].value='").append(WeiboAccount.PASSWORD)
				.append("';");
		js.append("document.getElementsByClassName('W_btn_g')[1].click();");
		HtmlPage htmlPage = (HtmlPage) page;
		htmlPage.executeJavaScript(js.toString());
	}
}

?附錄：完整代碼

package x.http.simple.htmlunit;

import java.io.IOException;
import java.io.InputStream;
import java.net.URL;
import java.util.Map;
import java.util.Map.Entry;
import java.util.Set;

import x.http.core.HttpProxy;

import com.gargoylesoftware.htmlunit.DefaultCredentialsProvider;
import com.gargoylesoftware.htmlunit.HttpMethod;
import com.gargoylesoftware.htmlunit.Page;
import com.gargoylesoftware.htmlunit.ProxyConfig;
import com.gargoylesoftware.htmlunit.WebClient;
import com.gargoylesoftware.htmlunit.WebRequest;
import com.gargoylesoftware.htmlunit.WebResponse;
import com.gargoylesoftware.htmlunit.html.HtmlForm;
import com.gargoylesoftware.htmlunit.html.HtmlPage;
import com.gargoylesoftware.htmlunit.html.HtmlSubmitInput;
import com.gargoylesoftware.htmlunit.html.HtmlTextInput;
import com.gargoylesoftware.htmlunit.util.Cookie;
import com.gargoylesoftware.htmlunit.util.NameValuePair;
import com.google.common.collect.Maps;
import com.google.common.io.ByteStreams;

public class HtmlUnitDemo {

	private WebClient webClient = null;

	private int timeout = 50000;

	public HtmlUnitDemo() {
		this(null);
	}

	/**
	 * Get請求
	 * 
	 * @param url
	 * @return
	 * @throws Exception
	 */
	public byte[] sendGetRequest(String url) throws Exception {
		WebRequest webRequest = new WebRequest(new URL(url));
		webRequest.setHttpMethod(HttpMethod.GET);
		return sendRequest(webRequest);
	}

	/**
	 * Post 請求
	 * 
	 * @param url
	 * @param params
	 * @return
	 * @throws Exception
	 */
	public byte[] sendPostRequest(String url, Map<String, String> params) throws Exception {
		WebRequest webRequest = new WebRequest(new URL(url));
		webRequest.setHttpMethod(HttpMethod.POST);
		if (params != null && params.size() > 0) {
			for (Entry<String, String> param : params.entrySet()) {
				webRequest.getRequestParameters().add(new NameValuePair(param.getKey(), param.getValue()));
			}
		}
		return sendRequest(webRequest);
	}

	// 底層請求
	private byte[] sendRequest(WebRequest webRequest) throws Exception {
		byte[] responseContent = null;
		Page page = webClient.getPage(webRequest);

		WebResponse webResponse = page.getWebResponse();

		int status = webResponse.getStatusCode();

		System.out.println("Charset : " + webResponse.getContentCharset());

		System.out.println("ContentType : " + webResponse.getContentType());

		// 讀取數據內容
		if (status == 200) {
			if (page.isHtmlPage()) {
				// 等待JS執行完成
				webClient.waitForBackgroundJavaScript(100000);
				responseContent = ((HtmlPage) page).asXml().getBytes();
			} else {
				InputStream bodyStream = webResponse.getContentAsStream();
				responseContent = ByteStreams.toByteArray(bodyStream);
				bodyStream.close();
			}
		}
		// 關閉響應流
		webResponse.cleanUp();

		return responseContent;
	}

	public HtmlUnitDemo(HttpProxy proxy) {
		webClient = new WebClient();
		configWebClient();
		// 設置代理
		if (proxy != null) {
			setProxy(proxy);
		}
	}

	private void configWebClient() {
		// 設置webClient的相關參數
		// 1 啟動JS
		webClient.getOptions().setJavaScriptEnabled(true);
		// 2 禁用Css，可避免自動二次請求CSS進行渲染
		webClient.getOptions().setCssEnabled(false);
		// 3 啟動客戶端重定向
		webClient.getOptions().setRedirectEnabled(true);

		// 4 js運行錯誤時，是否拋出異常
		webClient.getOptions().setThrowExceptionOnScriptError(false);
		// 5 設置超時
		webClient.getOptions().setTimeout(timeout);
	}

	private void setProxy(HttpProxy proxy) {
		ProxyConfig proxyConfig = webClient.getOptions().getProxyConfig();
		proxyConfig.setProxyHost(proxy.getHost());
		proxyConfig.setProxyPort(proxy.getPort());

		DefaultCredentialsProvider credentialsProvider = (DefaultCredentialsProvider) webClient
				.getCredentialsProvider();
		credentialsProvider.addCredentials(proxy.getUser(), proxy.getPassword());
	}

	@SuppressWarnings("unused")
	private Map<String, String> getResponseCookies() {
		Set<Cookie> cookies = webClient.getCookieManager().getCookies();
		Map<String, String> responseCookies = Maps.newHashMap();
		for (Cookie c : cookies) {
			responseCookies.put(c.getName(), c.getValue());
		}
		return responseCookies;
	}

	@SuppressWarnings("unused")
	private void setCookies(String domain, Map<String, String> cookies) {
		if (cookies != null && cookies.size() > 0) {
			webClient.getCookieManager().setCookiesEnabled(true);// enable
																	// cookies
			for (Entry<String, String> c : cookies.entrySet()) {
				Cookie cookie = new Cookie(domain, c.getKey(), c.getValue());
				webClient.getCookieManager().addCookie(cookie);

				System.out.println("Set Cookies : " + c.getKey() + " | " + c.getValue());
			}
		}
	}

	/**
	 * 清除所有cookie
	 */
	public void clearCookies() {
		webClient.getCookieManager().clearCookies();
	}

	public void shutdown() throws IOException {
		webClient.closeAllWindows();
	}

	/**
	 * 打開google 搜索百度
	 * 
	 * @param args
	 * @throws Exception
	 */
	public void demo() throws Exception{
		String url = "http://www.google.com.hk";

		final WebClient webClient = new WebClient();
		HtmlPage htmlPage = webClient.getPage(url);

		// HtmlUnit dom模型
		// 獲取表單 ,獲得form標簽name屬性=f
		HtmlForm form = htmlPage.getFormByName("f");
		// 獲取輸入框, 獲取 input標簽 ，name屬性=q
		HtmlTextInput text = form.getInputByName("q");
		// 搜索百度
		text.setText("baidu");
		// 獲取提交按鈕
		HtmlSubmitInput button = form.getInputByName("btnG");
		// 提交表單
		HtmlPage listPage = button.click();

		System.out.println(listPage.asXml());
		webClient.closeAllWindows();
	}
	/**
	 * 打開google 搜索百度
	 * 
	 * @param args
	 * @throws Exception
	 */
	public static void main(String[] args) throws Exception {
		String url = "http://www.google.com.hk";

		HtmlUnitDemo htmlUnit = new HtmlUnitDemo();
		byte[] getResponse = htmlUnit.sendGetRequest(url);
		System.out.println("Get Body : " + new String(getResponse, "utf-8"));
		byte[] postResponse = htmlUnit.sendPostRequest(url, null);
		System.out.println("Get Body : " + new String(postResponse, "utf-8"));

		htmlUnit.shutdown();
	}
}

免責聲明！

本站轉載的文章為個人學習借鑒使用，本站對版權不負任何法律責任。如果侵犯了您的隱私權益，請聯系本站郵箱yoyou2525@163.com刪除。

猜您在找 Java爬蟲系列二：使用HttpClient抓取頁面HTML 使用Selenium來抓取動態加載的頁面 Selenium及Headless Chrome抓取動態HTML頁面 Splash抓取javaScript動態渲染頁面玩玩小爬蟲——抓取動態頁面使用Selenium來抓取動態加載的頁面 C#利用phantomJS抓取AjAX動態頁面 Python-爬蟲-動態渲染頁面抓取-（Selenium）的使用 python爬蟲之動態渲染頁面抓取-（Selenium）的使用 python爬蟲14--Selenium動態渲染頁面抓取