/*
百度知道爬虫!
经过我们分析,百度知道是由静态网页组成。网址格式主要为http://zhidao.baidu.com/question/(编号).html,其中编号便是该问题的编号(PID),按照时间逐个编号的,由于某些问题的删除或者某种原因,可能编号不连续。当我们发现该问题删除时,可以跳过该问题继续。
*/
class spider
{
private $content ;
private $contentlen ;
private $BestAnswer ;
private $CurPosition ;
function GetStart( $iStart )
{
return strpos( $this->content , '>' , $iStart )+1 ;
}
function GetContent ( $url )
{
$this->content = file_get_contents($url);
$this->contentlen = strlen( $this->content ) ;
$start = strpos( $this->content , '
$start = $this->GetStart( $start ) ;
$end = strpos( $this->content , '
$title = substr( $this->content , $start , $this->$end-$start ) ;
if ( strpos( $title , '_百度知道' , 1 ) {
return false;
}
return ture ;
}
function GetTitle()
{
$start = strpos( $this->content , '
if ( $start > 0 )
{
$start = $this->GetStart( $start ) ;
$end = strpos( $this->content , '
$this->CurPosition = $end ;
return substr( $this->content , $start , $end-$start ) ;
}
return NULL ;
}
function GetQTitle()
{
$start = strpos( $this->content , 'span class="question-title"' , $this->CurPosition ) ;
if ( $start > 0 )
{
$start = $this->GetStart( $start ) ;
$end = strpos( $this->content , '' , $start ) ;
$this->CurPosition = $end ;
return substr( $this->content , $start , $end-$start ) ;
}
return NULL ;
}
function GetClassFly()
{
;
}
function GetQContent()
{
$start = strpos( $this->content , 'pre id="question-content"' , $this->CurPosition ) ;
if ( $start > 0 )
{
$start = $this->GetStart( $start ) ;
$end = strpos( $this->content , '' , $start ) ;
$this->CurPosition = $end ;
return substr( $this->content , $start , $end-$start ) ;
}
return NULL ;
}
function GetQsuply()
{
$start = strpos( $this->content , 'id="question-suply"' , $this->CurPosition ) ;
if ( $start > 0 )
{
$start = $this->GetStart( $start ) ;
$end = strpos( $this->content , '' , $start ) ;
$this->CurPosition = $end ;
return substr( $this->content , $start , $end-$start ) ;
}
return NULL ;
}
function GetAnswer()
{
$start = strpos( $this->content , 'class="reply-text mb10"' , $this->CurPosition ) ;
if ( $start > 0 )
{
$start = $this->GetStart( $start ) ;
$end = strpos( $this->content , '' , $start ) ;
$this->CurPosition = $end ;
return substr( $this->content , $start , $end-$start ) ;
}
return NULL ;
}
}
ini_set('max_execution_time', '0');
$TestSpider = new spider() ;
$Startqid = 1000001 ;
$sndqid = 1000051 ;
$standurl = 'http://zhidao.baidu.com/question/' ;
$html = '.html' ;
$url ;
$NoUse = 0 ;
function microtime_float()
{
list($usec, $sec) = explode(" ", microtime());
return ((float)$usec + (float)$sec);
}
$time_start = microtime_float();
$answer ;
for ($i = $Startqid ; $i {
$url = $standurl.$i.$html ;
if ( $TestSpider->GetContent ( $url ) )
{
echo '
正在爬取编号为'.$i.'的网页
' ;
$TestSpider->GetTitle() ; //得到网页标题,不用显示了
echo '问题: '.$TestSpider->GetQTitle().'
' ; //得到问题题目
echo '问题具体内容:'.$TestSpider->GetQContent().'
' ; //得到问题内容,有可能不存在
echo '问题补充说明:'.$TestSpider->GetQsuply().'
' ; //问题补充说明,有可能不存在
while ( ($answer = $TestSpider->GetAnswer()) != NULL )
{
echo '问题答案:'.$answer.'
' ; //得到答案。有可能没有答案!
}
ob_flush() ;
flush() ;
}
else
{
echo '
错误了'.$url.'
' ;$NoUse++ ;
}
}
$time_end = microtime_float();
$time = $time_end - $time_start;
$i = $i-$Startqid ;
echo '
爬取'.$i.'个网页用时'.$time.'秒
其中跳过'.$NoUse.'个无效网页!' ;?>

Hot AI Tools

Undresser.AI Undress
AI-powered app for creating realistic nude photos

AI Clothes Remover
Online AI tool for removing clothes from photos.

Undress AI Tool
Undress images for free

Clothoff.io
AI clothes remover

Video Face Swap
Swap faces in any video effortlessly with our completely free AI face swap tool!

Hot Article

Hot Tools

SublimeText3 Mac version
God-level code editing software (SublimeText3)

MinGW - Minimalist GNU for Windows
This project is in the process of being migrated to osdn.net/projects/mingw, you can continue to follow us there. MinGW: A native Windows port of the GNU Compiler Collection (GCC), freely distributable import libraries and header files for building native Windows applications; includes extensions to the MSVC runtime to support C99 functionality. All MinGW software can run on 64-bit Windows platforms.

PhpStorm Mac version
The latest (2018.2.1) professional PHP integrated development tool

SublimeText3 Chinese version
Chinese version, very easy to use

Notepad++7.3.1
Easy-to-use and free code editor
