DFdou's Blog Life is short,Be yourself.

Android-用HttpClient抓取html页面内容

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

private String getHtmlContent(final String url) {
		String result = "";// 返回的结果
		StringBuffer resultBuffer = new StringBuffer();
		// 构造HttpClient的实例
		HttpClient httpClient = new HttpClient();
		// 创建GET方法的实例
		GetMethod getMethod = new GetMethod(url);
		// 使用系统提供的默认的恢复策略
		getMethod.getParams().setParameter(HttpMethodParams.RETRY_HANDLER,
				new DefaultHttpMethodRetryHandler());
		// getMethod.getParams().setParameter(HttpMethodParams.HTTP_CONTENT_CHARSET,"GB2312");
		getMethod.getParams().setContentCharset("GB2312");
		try {
			// 执行getMethod
			int statusCode = httpClient.executeMethod(getMethod);
			if (statusCode != HttpStatus.SC_OK) {
				System.err.println("Method failed: "
						+ getMethod.getStatusLine());
			}
			// 流式读取
			// 读取内容
			// byte[] responseBody = getMethod.getResponseBody();
			// 处理内容
			// String result = new String(responseBody,"GBK");
			// result = getMethod.getResponseBodyAsString();
			// System.out.println(result);
			// System.out.println(getMethod.getResponseCharSet());
			// 推荐做法
			BufferedReader in = new BufferedReader(new InputStreamReader(
					getMethod.getResponseBodyAsStream(), getMethod
							.getResponseCharSet()));
			String inputLine = null;
			while ((inputLine = in.readLine()) != null) {
				resultBuffer.append(inputLine);
				resultBuffer.append("\n");
			}
			result = new String(resultBuffer);
			return result;
		} catch (HttpException e) {
			// 发生致命的异常，可能是协议不对或者返回的内容有问题
			System.out.println("Please check your provided http address!");
			e.printStackTrace();
		} catch (IOException e) {
			// 发生网络异常
			e.printStackTrace();
		} finally {
			// 释放连接
			getMethod.releaseConnection();
		}
		return result;
	}