這篇文章將為大家詳細講解有關(guān)如何使用java實現(xiàn)登錄之后抓取數(shù)據(jù)功能,小編覺得挺實用的,因此分享給大家做個參考,希望大家閱讀完這篇文章后可以有所收獲。
網(wǎng)站前端頁面設(shè)計會用DIV+CSS架構(gòu),布局出來的網(wǎng)站外觀簡潔大氣。HTML靜態(tài),H5高端網(wǎng)站建設(shè)+CSS3網(wǎng)站,自適應(yīng)電腦、手機、平板,符合用戶體驗的習慣,更容易與用戶產(chǎn)生互動。專業(yè)網(wǎng)站設(shè)計公司的服務(wù)理念是“高性價比建站,讓企業(yè)網(wǎng)站具備營銷價值,促進長期合作共贏模式”。
具體內(nèi)容如下:
首先需要一個jsoup的jar包,我用的1.6.0。。下載地址為:http://pan.baidu.com/s/1mgqOuHa
1,獲取網(wǎng)頁內(nèi)容(核心代碼,技術(shù)有限沒封裝)。
2,登錄之后抓取網(wǎng)頁數(shù)據(jù)(如何在請求中攜帶cookie)。
3,獲取網(wǎng)站的ajax請求方法(返回json)。
以上這三點我就用一個類全部包含(比較糙望見諒,直接copy代碼過去,應(yīng)該就可以用)
一,這個類分別有這上面的1,2,3三中方法,直接main方法可以進行測試
package com.minxinloan.black.web.utils; import java.io.BufferedReader; import java.io.ByteArrayOutputStream; import java.io.DataInputStream; import java.io.DataOutputStream; import java.io.File; import java.io.FileOutputStream; import java.io.FileWriter; import java.io.IOException; import java.io.InputStream; import java.io.InputStreamReader; import java.io.OutputStream; import java.io.PrintWriter; import java.net.HttpURLConnection; import java.net.URL; import java.net.URLConnection; import java.net.URLEncoder; import java.nio.charset.Charset; import java.util.ArrayList; import java.util.HashMap; import java.util.Iterator; import java.util.List; import java.util.Map; import java.util.Map.Entry; import java.util.StringTokenizer; import net.sf.json.JSONArray; import net.sf.json.JSONObject; import org.jsoup.Connection; import org.jsoup.Connection.Method; import org.jsoup.Jsoup; import org.jsoup.nodes.Document; import org.jsoup.nodes.Element; import org.jsoup.select.Elements; public class CookieUtil { public final static String CONTENT_TYPE = "Content-Type"; public static void main(String[] args) { //String loginURL = "http://www.p2peye.com/member.php?mod=logging&action=login&loginsubmit=yes&loginhash=Lsc66&username=puqiuxiaomao&password=a1234567"; String listURL = "http://www.p2peye.com/blacklist.php?p=2"; String logURL = "http://www.p2peye.com/member.php"; //********************************需要登錄的************************************************* try { Connection.Response res = Jsoup.connect(logURL) .data("mod","logging" ,"action","login" ,"loginsubmit","yes" ,"loginhash","Lsc66" ,"username","puqiuxiaomao" ,"password","a1234567") .method(Method.POST) .execute(); //這兒的SESSIONID需要根據(jù)要登錄的目標網(wǎng)站設(shè)置的session Cookie名字而定 Connection con=Jsoup.connect(listURL); //設(shè)置訪問形式(電腦訪問,手機訪問):直接百度都參數(shù)設(shè)置 con.header("User-Agent", "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)"); //把登錄信息的cookies保存如map對象里面 Mapmap=res.cookies(); Iterator > it =map.entrySet().iterator(); while(it.hasNext()){ Entry en= it.next(); //把登錄的信息放入請求里面 con =con.cookie(en.getKey(), en.getValue()); } //再次獲取Document對象。 Document objectDoc = con.get(); Elements elements = objectDoc.getAllElements();//獲取這個連接返回頁面的源碼內(nèi)容(不是源碼跟源碼差不多) for (Element element : elements) { //element是迭代出來的標簽:如: Elements elements2= element.getAllElements();// for (Element element2 : elements2) { element2.text(); element2.attr("href");//獲取標簽屬性。element2代表a標簽:href代表屬性 element2.text();//獲取標簽文本 } } //********************************不需要登錄的************************************************* String URL = "http://www.p2peye.com/blacklist.php?p=2"; Document conTemp = Jsoup.connect(URL).get(); Elements elementsTemps = conTemp.getAllElements(); for (Element elementsTemp : elementsTemps) { elementsTemp.text(); elementsTemp.attr("href");//獲取標簽屬性。element2代表a標簽:href代表屬性 elementsTemp.text();//獲取標簽文本 } //********************************ajax方法獲取內(nèi)容。。。*************************************************。 HttpURLConnection connection = null; BufferedReader reader = null; try { StringBuffer sb = new StringBuffer(); URL getUrl = new URL(URL); connection = (HttpURLConnection)getUrl.openConnection(); reader = new BufferedReader(new InputStreamReader( connection.getInputStream(),"utf-8")); String lines; while ((lines = reader.readLine()) != null) { sb.append(lines); }; List
二,這個是獲取驗證碼的類,可以研究下。(但你要要分析出網(wǎng)站的驗證碼的請求地址)
package com.minxinloan.black.web.utils; import java.io.BufferedReader; import java.io.DataInputStream; import java.io.DataOutputStream; import java.io.File; import java.io.FileOutputStream; import java.io.FileWriter; import java.io.InputStream; import java.io.InputStreamReader; import java.io.PrintWriter; import java.net.HttpURLConnection; import java.net.URL; import java.net.URLConnection; import java.nio.charset.Charset; import java.util.HashMap; import java.util.List; import java.util.Map; import java.util.StringTokenizer; public class Utils {//解析驗證碼的 public static Content getRandom(String method, String sUrl,// 要解析的url MapparamMap, // 存放用戶名和密碼的map Map requestHeaderMap,// 存放COOKIE的map boolean isOnlyReturnHeader, String path) { Content content = null; HttpURLConnection httpUrlConnection = null; InputStream in = null; try { URL url = new URL(sUrl); boolean isPost = "POST".equals(method); if (method == null || (!"GET".equalsIgnoreCase(method) && !"POST" .equalsIgnoreCase(method))) { method = "POST"; } URL resolvedURL = url; URLConnection urlConnection = resolvedURL.openConnection(); httpUrlConnection = (HttpURLConnection) urlConnection; httpUrlConnection.setRequestMethod(method); httpUrlConnection.setRequestProperty("Accept-Language", "zh-cn,zh;q=0.5"); // Do not follow redirects, We will handle redirects ourself httpUrlConnection.setInstanceFollowRedirects(false); httpUrlConnection.setDoOutput(true); httpUrlConnection.setDoInput(true); httpUrlConnection.setConnectTimeout(5000); httpUrlConnection.setReadTimeout(5000); httpUrlConnection.setUseCaches(false); httpUrlConnection.setDefaultUseCaches(false); httpUrlConnection.connect(); int responseCode = httpUrlConnection.getResponseCode(); if (responseCode == HttpURLConnection.HTTP_OK || responseCode == HttpURLConnection.HTTP_CREATED) { byte[] bytes = new byte[0]; if (!isOnlyReturnHeader) { DataInputStream ins = new DataInputStream( httpUrlConnection.getInputStream()); // 驗證碼的位置 DataOutputStream out = new DataOutputStream( new FileOutputStream(path + "/code.bmp")); byte[] buffer = new byte[4096]; int count = 0; while ((count = ins.read(buffer)) > 0) { out.write(buffer, 0, count); } out.close(); ins.close(); } String encoding = null; if (encoding == null) { encoding = getEncodingFromContentType(httpUrlConnection .getHeaderField("")); } content = new Content(sUrl, new String(bytes, encoding), httpUrlConnection.getHeaderFields()); } } catch (Exception e) { return null; } finally { if (httpUrlConnection != null) { httpUrlConnection.disconnect(); } } return content; } public static String getEncodingFromContentType(String contentType) { String encoding = null; if (contentType == null) { return null; } StringTokenizer tok = new StringTokenizer(contentType, ";"); if (tok.hasMoreTokens()) { tok.nextToken(); while (tok.hasMoreTokens()) { String assignment = tok.nextToken().trim(); int eqIdx = assignment.indexOf('='); if (eqIdx != -1) { String varName = assignment.substring(0, eqIdx).trim(); if ("charset".equalsIgnoreCase(varName)) { String varValue = assignment.substring(eqIdx + 1) .trim(); if (varValue.startsWith("\"") && varValue.endsWith("\"")) { // substring works on indices varValue = varValue.substring(1, varValue.length() - 1); } if (Charset.isSupported(varValue)) { encoding = varValue; } } } } } if (encoding == null) { return "UTF-8"; } return encoding; } // 這個是輸出 public static boolean inFile(String content, String path) { PrintWriter out = null; File file = new File(path); try { if (!file.exists()) { file.createNewFile(); } out = new PrintWriter(new FileWriter(file)); out.write(content); out.flush(); return true; } catch (Exception e) { e.printStackTrace(); } finally { out.close(); } return false; } public static String getHtmlReadLine(String httpurl) { String CurrentLine = ""; String TotalString = ""; InputStream urlStream; String content = ""; try { URL url = new URL(httpurl); HttpURLConnection connection = (HttpURLConnection) url .openConnection(); connection.connect(); System.out.println(connection.getResponseCode()); urlStream = connection.getInputStream(); BufferedReader reader = new BufferedReader( new InputStreamReader(urlStream, "utf-8")); while ((CurrentLine = reader.readLine()) != null) { TotalString += CurrentLine + "\n"; } content = TotalString; } catch (Exception e) { } return content; } } class Content { private String url; private String body; private Map > m_mHeaders = new HashMap >(); public Content(String url, String body, Map > headers) { this.url = url; this.body = body; this.m_mHeaders = headers; } public String getUrl() { return url; } public String getBody() { return body; } public Map > getHeaders() { return m_mHeaders; } }
關(guān)于“如何使用java實現(xiàn)登錄之后抓取數(shù)據(jù)功能”這篇文章就分享到這里了,希望以上內(nèi)容可以對大家有一定的幫助,使各位可以學到更多知識,如果覺得文章不錯,請把它分享出去讓更多的人看到。