4.2Kettle数据抽取——HTML网页的数据抽取

基于数据库技术的HTML网页抽取技术的研究经过了人工、半自动化和全自动化方法的三个阶段。

人工方法，通过程序员人工分析出网页的模板，借助一定的编程语言，针对具体的问题生成具体的包装器。

半自动化方法，应用网页模板抽取数据，从而生成具体包装器的部分被计算机接管，而网页模板的分析仍然需要人工参与。

自动化方法中，网页模板的分析部分也交给了计算机进行，仅仅需要很少的人工参与或完全不需要人工参与，因而更加适合大规模、系统化、持续性的Web数据抽取。

下面通过人工方法实现HTML网页数据的抽取。这里以抽取“豆瓣电影排行榜”网页的超链接数据为例，演示如何抽取网页数据并保存至数据库mysql中的数据表html中。

1.打开kettle工具，创建转换html_extract，并添加如下控件及Hop连接线

2.配置“自定义常量数据”控件

3.配置HTTP client控件

4.配置“Java代码”控件

import java.util.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.sql.DriverManager;
import java.sql.SQLException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import com.mysql.jdbc.Connection;
import com.mysql.jdbc.PreparedStatement;
import java.io.InputStream;
import java.io.RandomAccessFile;
import java.net.URL;
import java.net.URLConnection;
 
private String result;
private String contents;
private Connection connection = null;
 
public boolean processRow(StepMetaInterface smi, StepDataInterface sdi) throws KettleException {
  if (first) {
    first = false;
 
    /* TODO: Your code here. (Using info fields)
    FieldHelper infoField = get(Fields.Info, "info_field_name");
    RowSet infoStream = findInfoRowSet("info_stream_tag");
    Object[] infoRow = null;
    int infoRowCount = 0;
    // Read all rows from info step before calling getRow() method, which returns first row from any
    // input rowset. As rowMeta for info and input steps varies getRow() can lead to errors.
    while((infoRow = getRowFrom(infoStream)) != null){
      // do something with info data
      infoRowCount++;
    }
    */
  }
	try{
 
		URL url = new URL("https://movie.douban.com/");
 
		URLConnection conn = url.openConnection();
 
		conn.setRequestProperty("accept","*/*");
 
		conn.setRequestProperty("connection","Keep-Alive");
 
		conn.setRequestProperty("user-agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36");
		conn.connect();
 
		InputStream input = conn.getInputStream();
		byte[] buffer = new byte[1024];
		int hasRead;
		int length = 0;
 
		String msg = "";
 
        //输出到一个txt文件中
        //FileWriter fw = new FileWriter("D:\\豆瓣电影排行榜.txt");
		RandomAccessFile raf = new RandomAccessFile("D:\\output\\豆瓣电影排行榜.txt","rw");
 
		while((hasRead =input.read(buffer)) != -1)
		{
			raf.write(buffer);
			length += hasRead;
			System.out.println("爬取进度："+length);
		}
		raf.close();
		logDebug("爬取完成！");
 
 
	} catch (Exception e) {
		logDebug("异常");
		e.printStackTrace();
	}
 
 
  Object[] r = getRow();
 
  if (r == null) {
    setOutputDone();
    return false;
  }
 
  // It is always safest to call createOutputRow() to ensure that your output row's Object[] is large
  // enough to handle any new fields you are creating in this step.
  r = createOutputRow(r, data.outputRowMeta.size());
 
  /* TODO: Your code here. (See Sample)
  // Get the value from an input field
  String foobar = get(Fields.In, "a_fieldname").getString(r);
  foobar += "bar";
    
  // Set a value in a new output field
  get(Fields.Out, "output_fieldname").setValue(r, foobar);
  */
  // Send the row on to the next step.
  putRow(data.outputRowMeta, r);
 
  return true;
}

 

5.运行转换html_extract

 成功！