Android 用 HttpClient 抓取 html 页面内容的方法

核心提示：用的类库为commons-httpclient-3.1.jar.有兴趣的下载去。代码如下:view sourceprint?01.private String getHtmlContent(final String url) {02. String result = "";// 返回的结果03. S

用的类库为commons-httpclient-3.1.jar.有兴趣的下载去。代码如下:

view sourceprint?01.private String getHtmlContent(final String url) {

02. String result = "";// 返回的结果

03. StringBuffer resultBuffer = new StringBuffer();

04. // 构造HttpClient的实例

05. HttpClient httpClient = new HttpClient();

06. // 创建GET方法的实例

07. GetMethod getMethod = new GetMethod(url);

08. // 使用系统提供的默认的恢复策略

09. getMethod.getParams().setParameter(HttpMethodParams.RETRY_HANDLER,

10. new DefaultHttpMethodRetryHandler());

11. // getMethod.getParams().setParameter(HttpMethodParams.HTTP_CONTENT_CHARSET,"GB2312");

12. getMethod.getParams().setContentCharset("GB2312");

13. try {

14. // 执行getMethod

15. int statusCode = httpClient.executeMethod(getMethod);

16. if (statusCode != HttpStatus.SC_OK) {

17. System.err.println("Method failed: "

18. + getMethod.getStatusLine());

19. }

20. // 流式读取

21. // 读取内容

22. // byte[] responseBody = getMethod.getResponseBody();

23. // 处理内容

24. // String result = new String(responseBody,"GBK");

25. // result = getMethod.getResponseBodyAsString();

26. // System.out.println(result);

27. // System.out.println(getMethod.getResponseCharSet());

28. // 推荐做法

29. BufferedReader in = new BufferedReader(new InputStreamReader(

30. getMethod.getResponseBodyAsStream(), getMethod

31. .getResponseCharSet()));

32. String inputLine = null;

33. while ((inputLine = in.readLine()) != null) {

34. resultBuffer.append(inputLine);

35. resultBuffer.append(" ");

36. }

37. result = new String(resultBuffer);

38. return result;