Capture over 10 thousand items, links, product names, prices, and images of customers ~~~ Version 1

 

Version 1 cannot be output to txt, and there are still some unclear display errors,

 

For example:

Need to block

 

 

Market price: >Market price ￥299</> <Class =

Price: >Price $99</Span>

 

</Div>

</LI>

<

 

Some messy symbol items in, Leave the market price and price on the line .........

 

To close the job, use the stupid method first,

Appendstringtoatextfile. append (new file ("D: // list.txt"), "Test 1 ");

Store all the information in D:/list.txt, and then use the stupid method to replace all the symbols in batches. Save a decent "D:/list .txt ".

 

In addition, I also need to capture the image, and then display the local link of the image in the list ....

 

 

Package newfolder;

 

 

Import java. Io. bufferedreader;

Import java. Io. inputstreamreader;

Import java.net. httpurlconnection;

Import java.net. url;

 

Public class catchillfinalv1 {

 

Public static string gethtml (string urlstring ){

Try {

Stringbuffer html = new stringbuffer ();

URL url = new URL (urlstring );

Httpurlconnection conn = (httpurlconnection) URL. openconnection ();

Inputstreamreader ISR = new inputstreamreader (conn. getinputstream ());

Bufferedreader BR = new bufferedreader (ISR );

String temp;

 

While (temp = Br. Readline ())! = NULL ){

Html. append (temp). append ("/N ");

}

BR. Close ();

ISR. Close ();

String test = html. tostring ();

String [] testarray = test. Split ("/"");

System. Out. println (test. Split ("href"). Length );

 

Return test;

} Catch (exception e ){

E. printstacktrace ();

Return NULL;

}

}

 

Public static void main (string [] ARGs ){

String url = "http://s.vancl.com/search.aspx ";

Int I = 0;

String nextpageurl = "";

Try {

Do {// A dowhile should be used to determine whether the URL on the next page exists

 

String test = catchillfinalv1.gethtml (URL );

String [] stringarray = test. Split ("Li class =/" sclistarea ");

 

For (Int J = 1; j <40; j ++) {// circular control, 40 items, 41 paragraphs divided, []

String [] Output = stringarray [J]. Split ("/"");

System. Out. println ("th" + (40 * I + J) + "commodity ");

System. Out. println ("item link:" + output [output. Length-10]);

System. Out. println ("item name:" + output [output. Length-8]);

// System. Out. println ("Market Price:" + output [output. Length-3]);

System. Out. println ("Market Price:" + output [output. Length-3]. replaceall ("span ",""));

// System. Out. println ("Market Price:" + output [output. Length-3]. replaceall ("<. *> ",""));

System. Out. println ("Price:" + output [output. Length-1]);

}

 

// 40th, connected to the back, cannot use length-10 or the like

String [] Output = stringarray [40]. Split ("/"");

System. Out. println ("the current number is" + (40 * (I + 1) + "item ");

System. Out. println ("item link:" + output [62]);

System. Out. println ("item name:" + output [64]);

System. Out. println ("Market Price:" + output [69]);

// System. Out. println ("Market Price:" + output [output. Length-3]. replaceall ("<. *> ",""));

System. Out. println ("Price:" + output [71]);

 

 

// Get the jump Link

String [] Page = test. Split ("next page ");

String [] Count = page [1]. Split ("/"");

Nextpageurl = count [count. Length-2];

System. Out. println ("Next Page Link:" + nextpageurl );

 

 

Url = "http://s.vancl.com ";

URL + = nextpageurl; // directly use/search. aspx? S = 1 & D = 0 & B = 0 & P = 4 & R = 40 No, need to add http://s.vancl.com/search.aspx in front

 

I ++;

 

} While (nextpageurl! = "");

} Catch (exception e) {// The last page contains a java. Lang. arrayindexoutofboundsexception exception.

E. printstacktrace ();

 

}

 

 

 

 

 

// System. Out. println (stringarray [1]. Split ("/" "). Length );

// System. Out. println (test. Split ("Li") [1]);

// System. Out. println (test. Split ("href") [11]);

// System. Out. println (test. Split ("href") [111]);

// System. Out. println (catchurl. gethtml ("http://s.vancl.com/search.aspx "));

}

}