杭州摇号网站分页显示,浏览起来非常的不方便,于是写了几行代码
将它给全部下载到一个文件中。代码很简单,先通过httpwatch观察,http
是如何拼接请求的,然后在代码中将链接拼接好,批量下载下来。
PrintStream ps = null; try { ps = new PrintStream(new FileOutputStream("company.txt")); } catch (FileNotFoundException e1) { e1.printStackTrace(); } for(int i = 1; i <= 40; i++){ HttpClient client = new DefaultHttpClient(); //http://apply.hzcb.gov.cn/apply/app/status/norm/unit //http://apply.hzcb.gov.cn/apply/app/status/norm/person HttpPost httppost = new HttpPost("http://apply.hzcb.gov.cn/apply/app/status/norm/unit"); httppost.setHeader("Referer","http://apply.hzcb.gov.cn/apply/app/status/norm/unit"); List<NameValuePair> params = new ArrayList<NameValuePair>(); String pageNo = new Integer(i).toString(); params.add(new BasicNameValuePair("pageNo", pageNo)); params.add(new BasicNameValuePair("issueNumber", "201405")); params.add(new BasicNameValuePair("applyCode", "")); httppost.setEntity(new UrlEncodedFormEntity(params)); HttpResponse response = client.execute(httppost); HttpEntity entity = response.getEntity(); // 在这里可以用Jsoup之类的工具对返回结果进行分析,以判断登录是否成功 String postResult = EntityUtils.toString(entity, "GBK"); Document document = Jsoup.parse(postResult); Elements carpersons = document.select("tr.content_data"); for(Element e : carpersons){ String id = ""; String name = ""; Elements props = e.select("td"); int count = 0; for(Element e1 : props){ if(count == 0) id = e1.text(); else name = e1.text(); count++; } System.out.println("id:" + id + " name:" + name); ps.println(id + " " + name); } } if (null != ps) { ps.close(); } }