尽量不要模拟浏览器去爬取资源,效率低且耗资源, selenium可以用不同的驱动,比如firefox,chrome和你提到的PhantomJS,还支持(模拟?)safari、安卓的浏览器等。
举例:例如在百度中搜索成语词典,显示如下,需要爬取所有的成语词汇。我们可以点击下一页查看,有经验的同学一眼就可以看出这里是使用JavaScript异步加载的。在网页源码上是找不到的。下面就介绍爬取所有词典的方法
通过firebug调试网页 可得js
以上四部便可以得到大致是一个json格式的内容,做到这一步,算是完成了一大部分的工作,由于为了方便解析内容,需要将网站稍作修改,这一步大家需要去尝试在此我将这部分(&cb=jQuery1102011321965302340686_1450094493974)去掉后,内容变成纯的json格式文档。接下来的和爬取静态网页的方法一样了
6. 第五步可以得到这样的网址:=1450094493985”>https://sp0.baidu.com/8aQDcjqpAAV3otqbppnN2DJv/api.php?resource_id=28204&from_mid=1&&format=json&ie=utf-8&oe=utf-8&query=%E6%88%90%E8%AF%AD%E8%AF%8D%E5%85%B8%E4%B8%8B%E8%BD%BD&sort_key=&sort_type=1&stat0=&stat1=&stat2=&stat3=&pn=30&rn=30&=1450094493985,pn=30,表示每页显示30个,我们需要改变pn的值来爬取所有的成语,具体操作是pn+=30。
格式化json可以解析得到成语内容
import java.io.BufferedReader; import java.io.ByteArrayOutputStream; import java.io.File; import java.io.FileNotFoundException; import java.io.IOException; import java.io.InputStream; import java.io.InputStreamReader; import java.io.PrintStream; import java.io.UnsupportedEncodingException; import java.net.HttpURLConnection; import java.net.MalformedURLException; import java.net.URL; import java.net.URLConnection; import org.json.JSONArray; import org.json.JSONObject; public class BaiduIdiomCrawer { public static void main(String[] args) { //BaiduIdiomCrawer test=new BaiduIdiomCrawer(); new BaiduIdiomCrawer().test01(); } public void test01() { //String myurl = "https://sp0.baidu.com/8aQDcjqpAAV3otqbppnN2DJv/api.php?resource_id=6848&from_mid=1&&format=json&ie=utf-8&oe=utf-8&query=%E6%88%90%E8%AF%AD&sort_key=&sort_type=1&stat0=&stat1=&stat2=&stat3=&pn=30&rn=30&cb=jQuery110206992364453617483_1449371069677&_=1449371069681"; //String myurl="https://sp0.baidu.com/8aQDcjqpAAV3otqbppnN2DJv/api.php?resource_id=6848&from_mid=1&&format=json&ie=utf-8&oe=utf-8&query=%E6%88%90%E8%AF%AD&sort_key=&sort_type=1&stat0=&stat1=&stat2=&stat3=&pn=30&rn=30&_=1449371069681"; String myurl; String content = new String(); StringBuffer sb = new StringBuffer(); try { String url2="https://sp0.baidu.com/8aQDcjqpAAV3otqbppnN2DJv/api.php?resource_id=" + "28204&from_mid=1&&format=json&ie=utf-8&oe=utf-8&" + "query=%E6%88%90%E8%AF%AD%E8%AF%8D%E5%85%B8%E4%B8%8B%E8%BD%BD&sort_key=&" + "sort_type=1&stat0=&stat1=&stat2=&stat3=&pn="; String url1="&rn=30&_=1449376371822"; //String url2="https://sp0.baidu.com/8aQDcjqpAAV3otqbppnN2DJv/api.php?resource_id=6848&from_mid=1&&format=json&ie=utf-8&oe=utf-8&query=%E6%88%90%E8%AF%AD&sort_key=&sort_type=1&stat0=&stat1=&stat2=&stat3=&pn="; //String url1="&rn=30&_=1449371069681"; for (int j = 0; j < 1098; j++) { myurl = url2 + j * 30 + url1; System.out.println(j); //content=this.downloadToString(myurl, "utf-8"); content=this.downloadToString(myurl); JSONObject jo = new JSONObject(content.toString()); JSONArray jsonarray = jo.getJSONArray("data"); if(j==690){ System.out.println(j); } JSONObject jo1 = jsonarray.getJSONObject(0); JSONArray jsonarray1 = jo1.getJSONArray("result"); for (int i = 0; i < jsonarray1.length(); i++) { JSONObject user = (JSONObject) jsonarray1.get(i); String userName = (String) user.get("ename"); //System.out.println(userName); sb.append(userName + "\n"); } } } catch (Exception e) { // TODO Auto-generated catch block e.printStackTrace(); } try { PrintStream ps=new PrintStream(new File("result.txt"),"utf-8"); ps.print(sb.toString()); ps.close(); } catch (FileNotFoundException e) { // TODO Auto-generated catch block e.printStackTrace(); } catch (UnsupportedEncodingException e) { // TODO Auto-generated catch block e.printStackTrace(); } System.out.println(sb.toString()); } public String downloadToString(String url, String charset) throws Exception { ByteArrayOutputStream output = new ByteArrayOutputStream(); try { HttpURLConnection http = (HttpURLConnection) (new URL(url)).openConnection(); http.setReadTimeout(5 * 60 * 1000); //http.setRequestProperty("User-Agent", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0)"); http.setRequestProperty("User-Agent","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.31 (KHTML, like Gecko) Chrome/26.1.141.64 Safari/537.31"); http.setRequestMethod("GET"); http.setUseCaches(false); InputStream input = http.getInputStream(); int ch = -1; while((ch = input.read()) != -1) output.write(ch); input.close(); } catch(Exception ex) { ex.printStackTrace(System.out); } return output.toString(charset); } public String downloadToString(String u){ StringBuffer sb = new StringBuffer(); try { URL url = new URL(u); URLConnection connection = url.openConnection(); InputStream is = connection.getInputStream(); InputStreamReader isr = new InputStreamReader(is,"UTF-8"); BufferedReader br = new BufferedReader(isr); String line; while((line=br.readLine())!=null){ sb.append(line); } br.close(); isr.close(); is.close(); } catch (MalformedURLException e) { // TODO Auto-generated catch block e.printStackTrace(); } catch (IOException e) { // TODO Auto-generated catch block e.printStackTrace(); } return sb.toString(); } }