php 扫描url死链接

Posted 2020-12-04 mingzhanghui

* 从Packagist上搜索需要的包

  https://packagist.org/

 

* 通过composer下载依赖包

composer require guzzlehttp/guzzle
composer require league/csv

　　

* 使用composer自动加载器, 编写scan.php

<?php

// 1. 使用composer自动加载器
require \'vendor/autoload.php\';

use GuzzleHttp\\RequestOptions;

// 2. 实例Guzzle HTTP客户端
$client = new \\GuzzleHttp\\Client();

$options = [
    RequestOptions::TIMEOUT => 3,
    RequestOptions::DECODE_CONTENT => false,
    RequestOptions::HEADERS => [
        \'User-Agent\' => \'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/67.0.3396.99 Safari/537.36\',
    ]
];

// 3. 打开迭代处理csv
// 或者传用户自定义命令行参数指定输入文件 $argv[1]
// $file = new SplFileObject(\'../data/t_video.csv\'); /* $csvRow[4], $csvRow[5] */
$file = new SplFileObject(\'../data/urls.csv\');
$csv = \\League\\Csv\\Reader::createFromFileObject($file);
foreach ($csv as $csvRow) {
    $url = $csvRow[0];
    echo \'scanning \',$url,\'... \';
    try {
        // 4. 发送http options请求
        $httpResponse = $client->request(\'GET\', $url, $options);

        // 5. 检查http相应的状态码
        $code = $httpResponse->getStatusCode();
        if ($code === 200) {
            echo "\\033[32m[OK]\\033[0m",PHP_EOL;
        } else {
            throw new \\Exception();
        }

    } catch (\\Exception $e) {
        // 6. 把死链发给标准输出
        // echo $url.PHP_EOL;
        echo "\\033[31m[ERROR]\\033[0m ".$e->getMessage().PHP_EOL;
    }
}

　　

* input csv:

../data/urls.csv

https://www.baidu.com
https://mail.qq.com/cgi-bin/frame_html?sid=CYcBjsDbOqznWhVO&r=375cccc57697ed7d00ae5d751663a71c
https://pan.baidu.com/disk/home?errno=0&errmsg=Auth%20Login%20Sucess&&bduss=&ssnerror=0&traceid=#/all?vmode=list&path=%2F05.php%2F25K%20PHP%E9%9D%A2%E8%AF%95%E8%A7%86%E9%A2%91%E6%95%99%E7%A8%8B
http://dict.youdao.com/w/eng/components/#keyfrom=dict2.index
http://php.net/manual/en/splfileobject.fwrite.php
https://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=1&rsv_idx=2&tn=baiduhome_pg&wd=ansi%20%E7%BB%88%E7%AB%AF%E9%A2%9C%E8%89%B2%20%5B%5C33&rsv_spt=1&oq=ansi%2520%25E7%25BB%2588%25E7%25AB%25AF%25E9%25A2%259C%25E8%2589%25B2&rsv_pq=8b17bd6e0027882b&rsv_t=fcf6oR2SbHi9Cpu2eThdv3AQvGwSDf7ecjv7QBvjXoZ3SMpBem3pdNzlNRNmuOW%2BEowe&rqlang=cn&rsv_enter=1&inputT=2640&rsv_sug3=68&rsv_sug2=0&rsv_sug4=3243
https://blog.csdn.net/SLASH_24/article/details/54846392
https://www.jb51.net/article/42358.htm
https://www.cnblogs.com/xudong-bupt/p/3721210.html
http://www.cnblogs.com/mingzhanghui/p/9314906.html
https://packagist.org/packages/maatwebsite/excel
https://www.phptherightway.com/#use_the_current_stable_version
https://doc.phpspider.org/methods.html
http://nosuchurl
http://deadurl

　　

output:

 

* 在Linux终端输出带颜色的文字的方法

  注意 echo "" 要用双引号, 单引号会原样输出 \\033[32mxxx\\033[0m

一、shell下的实现方法

只要设置输出属性，就可输出带颜色的文字 ，shell中的部分属性：

      \\033[0m 关闭所有属性
      \\033[1m 设置高亮度
      \\033[4m 下划线
      \\033[5m 闪烁
      \\033[7m 反显
      \\033[8m 消隐
      \\033[30m 至 \\33[37m 设置前景色
      \\033[40m 至 \\33[47m 设置背景色
      \\033[nA 光标上移n行 
      \\033[nB 光标下移n行
      \\033[nC 光标右移n行
      \\033[nD 光标左移n行
      \\033[y;xH设置光标位置
      \\033[2J 清屏
      \\033[K 清除从光标到行尾的内容
      \\033[s 保存光标位置 
      \\033[u 恢复光标位置
      \\033[?25l 隐藏光标
      \\033[?25h 显示光标

 

--------------------------------------------------------------------------
      各数字所代表的颜色如下：
      字背景颜色范围:40----49
      40:黑
      41:深红
      42:绿
      43:黄色
      44:蓝色
      45:紫色
      46:深绿
      47:白色

      字颜色:30----39
      30:黑
      31:红
      32:绿
      33:黄
      34:蓝色
      35:紫色
      36:深绿 
      37:白色

 

      使用，如：echo -e "\\033[34mHello, world!" (-e作用是引导设置输出属性)，

      恢复属性为默认值：echo -e  "\\033[0m"，

      同类的多种设置项可以组合在一起，中间用分号（;）隔开。如下：

      echo -e "\\033[20;1H\\033[1;4;34mHello,world\\033[0m"

 

===================================================================================

php 命令行脚本

http://php.net/manual/en/wrappers.php.php

http://php.net/manual/en/reserved.variables.argv.php

http://php.net/manual/en/reserved.variables.argc.php

 

====================================================================================

scanner.php 

不在终端打印 返回数组

 1 <?php
 2 /**
 3  * Created by PhpStorm.
 4  * User: Mch
 5  * Date: 7/17/18
 6  * Time: 21:34
 7  */
 8 namespace Tsinghuadtv\\ModernPHP\\Url;
 9 
10 // composer require guzzlehttp/guzzle
11 require \'vendor/autoload.php\';
12 
13 use GuzzleHttp\\RequestOptions;
14 
15 class Sanner {
16     protected $urls;
17 
18     protected $httpClient;
19 
20     protected $options = [
21         RequestOptions::VERSION => 1.1,
22         RequestOptions::TIMEOUT => 3,
23         RequestOptions::DECODE_CONTENT => false,
24         RequestOptions::HEADERS => [
25             \'User-Agent\' => \'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36\'
26         ]
27     ];
28 
29     public function __construct(array $urls) {
30         $this->urls = $urls;
31         $this->httpClient = new \\GuzzleHttp\\Client();
32     }
33 
34     public function getInvalidUrls() {
35         $invalidUrls = [];
36         foreach ($this->urls as $url) {
37             try {
38                 $statusCode = $this->getStatusCodeForUrl($url);
39             } catch (\\Exception $e) {
40                 $statusCode = 500;
41             }
42             if ($statusCode >= 400) {
43                 array_push($invalidUrls, [
44                     \'url\' => $url,
45                     \'status\' => $statusCode
46                 ]);
47             }
48         }
49         return $invalidUrls;
50     }
51 
52     protected function getStatusCodeForUrl($url) {
53         $httpResponse = $this->httpClient->request(\'get\', $url, $this->options);
54         return $httpResponse->getStatusCode();
55     }
56 
57 }

scanner.php

调用scanner.php测试

假设这个包提交到 modernphp/scanner  https://packagist.org

composer require modernphp/scanner

 1 <?php
 2 /**
 3  * Created by PhpStorm.
 4  * User: Mch
 5  * Date: 7/17/18
 6  * Time: 21:41
 7  */
 8 // require \'vendor/autoload.php\';
 9 include \'scanner.php\';
10 
11 $urls = [
12     \'http://www.apple.com\',
13     \'http://nosuchurl\',
14     \'https://www.cnblogs.com/mingzhanghui/p/9317179.html\',
15     \'https://www.baidu.com\',
16     \'http://jp2.php.net\',
17     \'http://sdfssdwerw.org\'
18 ];
19 
20 $scanner = new \\Tsinghuadtv\\ModernPHP\\Url\\Sanner($urls);
21 print_r($scanner->getInvalidUrls());

index.php

output:

Array (

    [0] => Array ([url] => http://nosuchurl   [status] => 500 )

    [1] => Array([url] => http://sdfssdwerw.org  [status] => 500 )

)