登录  /  注册
首页 > php教程 > PHP源码 > 正文

php爬美女照

PHP中文网
发布: 2016-05-26 08:21:15
原创
1303人浏览过

之前看到有人用go来写了爬虫爬hd美女照,拿来用发现用不了,里面有api接口,于是拿来写了个php版本的。php只要安装了curl扩展都没问题。我拿来爬了一下,九百多张。

<?php

/**
 * curl多线程下载类
*/
class MultiHttpRequest
{
public $urls = array ();
private $res = array ();
private $curlopt_header = 0;
private $method ="GET";
private $curlopt = array ();

public function __construct($urls = false, $curlopt = array ())
{
$this->urls = $urls;
if ( !empty($curlopt) ) {
$this->curlopt = $curlopt;
}
}

public function set_urls($urls)
{
$this->urls = $urls;
return $this;
}

public function set_curlopt($name, $vale)
{
$this->curlopt[$name] = $vale;
}

public function is_return_header($b)
{
$this->curlopt_header = $b;
return $this;
}

public function get_curlopt()
{
return $this->curlopt;
}

public function set_method($m)
{
$this->medthod = strtoupper($m);
return $this;
}

public function set_curlopts($arr)
{
$this->curlopt = $arr;
}

public function start()
{
if ( !is_array($this->urls) || count($this->urls) == 0 ) {
return false;
}

$handle = curl_multi_init();
foreach ( $this->urls as $k => $v ) {
$curl[$k] = $this->add_handle($handle, $v);
}

$this->exec_handle($handle);
foreach ( $this->urls as $k => $v ) {
$this->res[$k] = curl_multi_getcontent($curl[$k]);
curl_multi_remove_handle($handle, $curl[$k]);
}
curl_multi_close($handle);
}

private function add_handle($handle, $url)
{
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
foreach ( $this->curlopt as $k => $v ) {
curl_setopt($curl, $k, $v);
}
curl_multi_add_handle($handle, $curl);
return $curl;
}

private function exec_handle($handle)
{
$flag = null;
do {
curl_multi_exec($handle, $flag);
} while ( $flag > 0 );
}

public function getRes()
{
return $this->res;
}

}

class HDbutifulyGril
{
private $url = &#39;&#39;;
private $savepath = &#39;&#39;;
private $imagessavepath = array();

public function __construct($url,$savepath=&#39;&#39;)
{
$this->url = $url;
if( !empty($savepath) && !is_dir($savepath)){
mkdir($savepath,0777,true);
}
$this->savepath = $savepath;
}

/**
 * 得到所有大图的url地址
 * @param type $id
 * @return array();
*/
private function getimagesurl($id = &#39;&#39;)
{
$url = $this->url . $id;
$str = file_get_contents($url);
$arr = json_decode($str, true);
$images = array ();
$savepath = array();
if ( is_array($arr) && !empty($arr) ) {
foreach ( $arr[&#39;data&#39;] as $v ) {
$url = $v[&#39;image&#39;][&#39;original&#39;];
$filename = $this->getFilenameBy($url);
if( !file_exists($filename)){ // 如果图片已经采集了就不要再采了
$images[] = $url;
$savepath[] = $filename;
}
}
}
$this->imagessavepath = $savepath;
return $images;
}

/**
 * 通过url确定图片的保存地址
 * @param string $url
 * @return string 
*/
private function getFilenameBy($url)
{
$tmp = explode(&#39;/&#39;, $url);
return $this->savepath . str_replace(&#39;,&#39;, &#39;_&#39;, array_pop($tmp));
}

/**
 * 开始下载
 * @param int $id pid
*/
public function start($id = &#39;&#39;)
{
$imgurl = $this->getimagesurl($id);
$imgs = $this->MultiDownByUrls($imgurl);
foreach ( $imgs as $k => $v ) {
if ( !empty($v) ) {
file_put_contents($this->imagessavepath[$k], $v);
}
}
}

/**
 * 通过urls多线程下载图片
 * @param array $urls
 * @return array
*/
private function MultiDownByUrls($urls)
{
$opts = array (
CURLOPT_RETURNTRANSFER => 1,
CURLOPT_AUTOREFERER => 1,
CURLOPT_HEADER => 0,
CURLOPT_FOLLOWLOCATION => 1,
CURLOPT_USERAGENT => &#39;Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.154 Safari/537.36&#39;
);
$mutil = new MultiHttpRequest($urls, $opts);
$mutil->start();
return $mutil->getRes();
}

}

$url = &#39;http://api.lovebizhi.com/macos_v4.php?a=category&spdy=1&tid=3&order=hot&color_id=3&device=105&uuid=436e4ddc389027ba3aef863a27f6e6f9&mode=0&retina=0&client_id=1008&device_id=31547324&model_id=105&size_id=0&channel_id=70001&screen_width=1920&screen_height=1200&bizhi_width=1920&bizhi_height=1200&version_code=19&language=zh-Hans&jailbreak=0&mac=&p=&#39;;
$savepath = __DIR__.DIRECTORY_SEPARATOR.&#39;images&#39; . DIRECTORY_SEPARATOR;
$hd = new HDbutifulyGril($url,$savepath);
for ( $i = 1; $i < 100; $i++ ) {
$hd->start($i);
}
登录后复制
智能AI问答
PHP中文网智能助手能迅速回答你的编程问题,提供实时的代码和解决方案,帮助你解决各种难题。不仅如此,它还能提供编程资源和学习指导,帮助你快速提升编程技能。无论你是初学者还是专业人士,AI智能助手都能成为你的可靠助手,助力你在编程领域取得更大的成就。
来源:php中文网
本文内容由网友自发贡献,版权归原作者所有,本站不承担相应法律责任。如您发现有涉嫌抄袭侵权的内容,请联系admin@php.cn
作者最新文章
最新问题
热门教程
更多>
最新下载
更多>
网站特效
网站源码
网站素材
前端模板
关于我们 免责申明 意见反馈 讲师合作 广告合作 最新更新
php中文网:公益在线php培训,帮助PHP学习者快速成长!
关注服务号 技术交流群
PHP中文网订阅号
每天精选资源文章推送
PHP中文网APP
随时随地碎片化学习
PHP中文网抖音号
发现有趣的

Copyright 2014-2024 https://www.php.cn/ All Rights Reserved | php.cn | 湘ICP备2023035733号