升值英文(完整word版)网络爬虫试验报告

为相对

URL

，

bas e

为这个

URL

上的页面，这种形式的

U

RL

类构造函数可构造一个绝对

URL

。在

URL

变为正确的绝对形式之后，通过检查它是否

在等待区，

来确认此

URL

是否已经被处理过。

如果此

URL

没有被处理过，

它会添加到等待

区，之后，它会像其他

URL

一样被处理。

相关的代码如下所示：

import

.*;

import

.*;

import

.*;

import

.*;

public

class

CheckLinks

extends

implements

Runnable,ISpiderReportable

{

/**

*

The

constructor.

Perform

setup

here.

*/

public

CheckLinks()

{

//{{INIT_CONTROLS

setTitle(

Broken

Links

getContentPane().setLayout(null);

setSize(405,288);

setVisible(true);

t(

a

URL:

getContentPane().add(label1);

nds(12,12,84,12);

t(

ionCommand(

getContentPane().add(begin);

nds(12,36,84,24);

getContentPane().add(url);

nds(108,36,288,24);

oscrolls(true);

izontalScrollBarPolicy(.

NTAL_SCROLLBAR_ALWAYS);

ticalScrollBarPolicy(.

AL_SCROLLBAR_ALWAYS);

que(true);

getContentPane().add(errorScroll);

nds(12,120,384,156);

table(false);

wport().add(errors);

nds(0,0,366,138);

t(

Processing:

getContentPane().add(current);

nds(12,72,384,12);

t(

Links:

0

getContentPane().add(goodLinksLabel);

nds(12,96,192,12);

t(

Links:

0

getContentPane().add(badLinksLabel);

nds(216,96,96,12);

//}}

//{{INIT_MENUS

//}}

//{{REGISTER_LISTENERS

SymAction

lSymAction

=

new

SymAction();

ionListener(lSymAction);

//}}

}

/**

*

Main

method

for

the

application

*

*

@param

args

Not

used

*/

static

public

void

main(String

args[])

{

(new

CheckLinks()).setVisible(true);

}

/**

*

Add

notifications.

*/

public

void

addNotify()

{

//

Record

the

size

of

the

window

prior

to

calling

parent's

//

addNotify.

Dimension

size

=

getSize();

ify();

if

(

frameSizeAdjusted

)

return;

frameSizeAdjusted

=

true;

//

Adjust

size

of

frame

according

to

the

insets

and

menu

bar

Insets

insets

=

getInsets();

ar

menuBar

=

getRootPane().getJMenuBar();

int

menuBarHeight

=

0;

if

(

menuBar

!=

null

)

menuBarHeight

=

ferredSize().height;

setSize(

+

+

,

+

+

+

menuBarHeight);

}

//

Used

by

addNotify

boolean

frameSizeAdjusted

=

false;

//{{DECLARE_CONTROLS

label1

=

new

();

/**

*

The

begin

or

cancel

button

*/

n

begin

=

new

n();

/**

*

The

URL

being

processed

*/

ield

url

=

new

ield();

/**

*

Scroll

the

errors.

*/

lPane

errorScroll

=

new

lPane();

/**

*

A

place

to

store

the

errors

created

*/

rea

errors

=

new

rea();

current

=

new

();

goodLinksLabel

=

new

();

badLinksLabel

=

new

();

//}}

//{{DECLARE_MENUS

//}}

/**

*

The

background

spider

thread

*/

protected

Thread

backgroundThread;

/**

*

The

spider

object

being

used

*/

protected

Spider

spider;

/**

*

The

URL

that

the

spider

began

with

*/

protected

URL

base;

/**

*

How

many

bad

links

have

been

found

*/

protected

int

badLinksCount

=

0;

/**

*

How

many

good

links

have

been

found

*/

protected

int

goodLinksCount

=

0;

/**

*

Internal

class

used

to

dispatch

events

*

*

@author wuhailin

*

@version

1.0

*/

class

SymAction

implements

Listener

{

public

void

actionPerformed(Event

event)

{

Object

object

=

rce();

if

(

object

==

begin

)

begin_actionPerformed(event);

}

}

/**

*

Called

when

the

begin

or

cancel

buttons

are

clicked

*

*

@param

event

The

event

associated

with

the

button.

*/

void

begin_actionPerformed(Event

event)

{

if

(

backgroundThread==null

)

{

el(

backgroundThread

=

new

Thread(this);

();

goodLinksCount=0;

badLinksCount=0;

}

else

{

();

}

}

/**

*

Perform

the

background

thread

operation.

This

method

*

actually

starts

the

background

thread.

*/

public

void

run()

{

try

{

t(