用 Tensorflow.js 做了一个动漫分类的功能（一）

<?php/** * @Notes: 公众号：ZERO开发 * @Interface getCondition * @Return mixed * @Author: bqs * @Time: 2021/4/19 15:28 */
namespace app\common\command;
use think\console\Command;use think\console\Input;use think\console\Output;use think\console\input\Argument;use think\console\input\Option;use think\Db;use think\facade\Hook;use think\facade\Log;use QL\QueryList;
class QueryListSpiderSingle extends Command{
    protected function configure()    {        $this->setName('querylist:single')            ->setDescription('采集');    }
    protected function execute(Input $input, Output $output)    {        ini_set('memory_limit', '512M');
        $output->writeln("=========date:" . date('Y-m-d H:i:s') . "===============");
        // 北桥苏奥特曼        //$slImgsUrl = "https://zhuanlan.zhihu.com/p/377571373";        $slImgsUrl = "https://zhuanlan.zhihu.com/p/344680014";
        // 原生query_list        $list = QueryList::get($slImgsUrl)->find('.RichText')->find('noscript')->find('img')->attrs('src');
        $path = 'E:\2setsoft\1dev\phpstudy_pro\WWW\4test\tensorflowJs\js-ml-code\t7\动漫分类\train\奥特曼\\';        foreach($list as $key => $value) {            $index = $key + 1 + 42;
            $filename = $index < 10 ? str_pad($index, 2, "0", STR_PAD_LEFT) : $index;            $filend = pathinfo($value, PATHINFO_EXTENSION);            $file = file_get_contents($value);            file_put_contents($path . $filename . "." . $filend, $file);
            $output->writeln($index . "--" . $value . "已保存--");        }
        $output->writeln("============date:" .date("Y-m-d H:i:s") . "采集完成==============");    }    }

<?php/** * @Notes: 文件描述 * @Interface getCondition * @Return mixed * @Author: bqs * @Time: 2021/4/19 15:28 */
namespace app\common\command;
use think\console\Command;use think\console\Input;use think\console\Output;use think\console\input\Argument;use think\console\input\Option;use think\Db;use think\facade\Hook;use think\facade\Log;use QL\QueryList;use QL\Ext\CurlMulti;
class QueryListSpider extends Command{
    protected function configure()    {        $this->setName('query:list')            ->setDescription('采集');    }
    protected function execute(Input $input, Output $output)    {        ini_set('memory_limit', '512M');
        $output->writeln("=========date:" . date('Y-m-d H:i:s') . "===============");
        // 地址与目录映射        $dirMap = [            "假面骑士" => "https://zhuanlan.zhihu.com/p/376119915",            "龙珠" => "https://zhuanlan.zhihu.com/p/340048917",            "火影忍者" => ["https://zhuanlan.zhihu.com/p/352717188", "https://zhuanlan.zhihu.com/p/393213201", "https://zhuanlan.zhihu.com/p/358228745"],            "海贼王" => ["https://zhuanlan.zhihu.com/p/357683518", "https://zhuanlan.zhihu.com/p/338160632"]        ];
        // 采集地址        $multiArr = [];        $multiArr = array_reduce(array_values($dirMap), function ($res, $value) {            $res = array_merge($res, (array)$value);            return $res;        }, []);
        // 采集映射        $multiMap = [];        foreach($dirMap as $key => $value) {            if (!is_array($value)) {                $multiMap[$value] = $key;            } else {                $temp = array_fill_keys($value, $key);                $multiMap = array_merge($multiMap, $temp);            }        }
        // 开始使用多线程采集        $ql = QueryList::use (CurlMulti::class);        $ql->curlMulti($multiArr)        ->success(function (QueryList $ql, CurlMulti $curl, $r) use ($multiMap) {
            $path = 'E:\2setsoft\1dev\phpstudy_pro\WWW\4test\tensorflowJs\js-ml-code\t7\动漫分类\train\\';            $queryUrl = $r['info']['url'];            $className = $multiMap[$queryUrl] ?? "";            $targetDir = $path . $className;            $path = $targetDir . '\\';
            $endFileIndex = 0;            $existFileList = $this->scanFile($targetDir);            if ($existFileList) {                // 取出所有数字文件名最大值                $endFileName = max($existFileList);                $endFileIndex = explode(".", $endFileName)[0];            }
            $data = $ql->find('.RichText')->find('noscript')->find('img')->attrs('src');
            foreach($data as $key => $value) {                $index = $key + 1 + $endFileIndex;
                $filename = $index < 10 ? str_pad($index, 2, "0", STR_PAD_LEFT) : $index;                $filend = pathinfo($value, PATHINFO_EXTENSION);                $file = file_get_contents($value);                file_put_contents($path . $filename . "." . $filend, $file);            }        })        // 每个任务失败回调        ->error(function ($errorInfo, CurlMulti $curl) {            echo "Current url:{$errorInfo['info']['url']} \r\n";            print_r($errorInfo['error']);        })        ->start([            // 最大并发数            'maxThread' => 10,            // 错误重试次数            'maxTry' => 5,        ]);
        $output->writeln("============date:" . date("Y-m-d H:i:s") . "采集完成==============");    }
    // 扫描目录下所有文件    protected function scanFile($path) {        $result = [];        $files = scandir($path);        foreach ($files as $file) {            if ($file != '.' && $file != '..') {                if (is_dir($path . '/' . $file)) {                    $this->scanFile($path . '/' . $file);                } else {                    $result[] = basename($file);                }            }        }        return $result;    }
}