<?php


namespace App\Services;


use App\ImageRecord;
use Exception;
use ErrorException;
use Log;
use QL\QueryList;

class XiurenjiService
{
    private $name_dir = [
        "xiuren" => [
            "path" => "XiuRen/",
            "dir" => "xiuren/"
        ],
        "xiaoyu" => [
            "path" => "XiaoYu/",
            "dir" => "xiaoyu/"
        ],
        "youwu" => [
            "path" => "YouWu/",
            "dir" => "youwu/"
        ],
        "mygirl" => [
            "path" => "MyGirl/",
            "dir" => "mygirl/"
        ],
        "huayang" => [
            "path" => "HuaYang/",
            "dir" => "huayang/"
        ],
        "mfstar" => [
            "path" => "MFStar/",
            "dir" => "mfstar/"
        ],
        "imiss" => [
            "path" => "IMiss/",
            "dir" => "imiss/"
        ]

    ];
    public $domainUrl = "https://www.xiurenb.net/";
    public $xiurenRootUrl = "https://www.xiurenb.net/XiuRen/";
    //    public $rootDir = "/Users/shixuesen/Documents/tmp/xiuren/";
    //    public $rootDir = "/Volumes/Backup/images/xiuren/";
    public $rootDir = "/Volumes/Crucial X6/Image/xr/";
    public $queryInstance;
    public $queryNew;

    public function __construct()
    {
        $this->queryInstance = QueryList::getInstance();
        $this->queryNew = new QueryList();
    }

    public function scrapeAll()
    {
        foreach ($this->name_dir as $key => $value) {
            # code...
            dump("current site: " . $key);
            $this->scrapeAlbum($key, 20);
        }
        // $this->scrapeAlbum("xiuren", 20);
        // $this->scrapeAlbum("xiaoyu", 20);
        // $this->scrapeAlbum("youwu", 20);
        // $this->scrapeAlbum("mygirl", 20);
        // $this->scrapeAlbum("huayang", 20);
        // $this->scrapeAlbum("mfstar", 20);
        // $this->scrapeAlbum("imiss", 20);
    }

    public function scrapeAlbum($path, $num = 20, $startPage = 0)
    {
        $pageSize = 20;
        $urlPath = $this->name_dir[$path]["path"];
        $rootDir = $this->rootDir;
        $this->rootDir = $this->rootDir . $this->name_dir[$path]["dir"];
        $pageCount = $this->getEncodeHtmlContent("https://www.xiurenb.net/$urlPath/index.html")->find(".page span strong")->htmls()->get(0);
        dump("current site item count: " . $pageCount);
        if ((int)$pageCount > 0) {
            $pageCount = min($pageCount, $num);
            for ($i = $startPage; $i <= ceil($pageCount / $pageSize); $i++) {
                $urlSuffix = "";
                if ($i == 0) {
                    $urlSuffix = "index.html";
                } else {
                    $urlSuffix = "index" . $i . ".html";
                }
                $this->scrapePageAlbum($this->domainUrl . $urlPath . $urlSuffix);
            }
        }
        $this->rootDir = $rootDir;
    }

    public function scrapePageAlbum($url)
    {

        $pageContent = $this->getEncodeHtmlContent($url);
        $items = $pageContent->find(".i_list a")->getElements();
        $i = 0;
        foreach ($items as $item) {
            // $i++;
            // if ($i < 18) {
            //     continue;
            //     # code...
            // }
            dump($item->getAttribute("href"));
            $this->scrapeSingleAlbum($this->domainUrl . $item->getAttribute("href"));
        }
    }

    public function scrapeSingleAlbum($url)
    {
        Log::info("scrapeSingleAlbum $url");
        $pageContent = $this->getEncodeHtmlContent($url);
        $albumName = $pageContent->find(".item_title h1")->htmls()->get(0);
        $pageItems = $pageContent->find(".content:eq(0) .page a")->attrs("href")->all();
        if ($this->checkAlbumHasDownload($albumName)) {
            Log::info("已经下载过了，相册名：" . $albumName);
            return;
        }
        dump("当前相册名: " . $albumName);
        $imageNo = 1;
        $description = null;
        $this->parseContent($this->rootDir . $albumName, $pageContent, $imageNo, $description);
        $pageItems = array_slice($pageItems, 2, count($pageItems) - 3);
        foreach ($pageItems as $item) {
            $pageContent = $this->getEncodeHtmlContent($this->domainUrl . $item);
            $this->parseContent($this->rootDir . $albumName, $pageContent, $imageNo, $description);
        }
    }

    public function parseContent($dir, $pageContent, &$imageNo, &$description)
    {
        if (!is_dir($dir)) {
            try {
                mkdir($dir);
            } catch (Exception $e) {
                Log::error($e->getMessage());
                return;
            }
        }
        $images = $pageContent->find(".content p img")->getElements();
        $user = $pageContent->find(".item_info div a:eq(-1) span")->htmls()->get(0);
        if ($description == null) {
            $metas = $pageContent->find("meta")->getElements();
            foreach ($metas as $meta) {
                $name = $meta->getAttribute("name");
                if (trim($name) == "description") {
                    $description = $meta->getAttribute("content");
                    break;
                }
            }
            dump("description: " . $description);
        }

        if ($imageNo == 1) {
            // 只在每个相册第一次输出名字
            dump("user is " . $user);
        }

        foreach ($images as $image) {
            usleep(random_int(10, 100) * 100);
            $imageUrl = $image->getAttribute("src");
            $trueImageUrl = "https://www.xiurenb.net" . $imageUrl;
            $fileInfo = pathinfo($trueImageUrl);
            if (file_exists($dir . DIRECTORY_SEPARATOR . $fileInfo["filename"] . ".jpg")) {
                rename($dir . DIRECTORY_SEPARATOR . $fileInfo["filename"] . ".jpg", $dir . DIRECTORY_SEPARATOR . $imageNo . "-" . $fileInfo["filename"] . ".jpg");
                $imageNo++;
                continue;
            }
            if (file_exists($dir . DIRECTORY_SEPARATOR . $fileInfo["filename"] . ".webp")) {
                rename($dir . DIRECTORY_SEPARATOR . $fileInfo["filename"] . ".webp", $dir . DIRECTORY_SEPARATOR . $imageNo . "-" . $fileInfo["filename"] . ".webp");
                $imageNo++;
                continue;
            }

            // 情况 2 缺少 user
            if (file_exists($dir . DIRECTORY_SEPARATOR . $imageNo . "-" . $fileInfo["filename"] . ".jpg")) {
                rename($dir . DIRECTORY_SEPARATOR . $imageNo . "-" . $fileInfo["filename"] . ".jpg", $dir . DIRECTORY_SEPARATOR . trim($user) . "-" . $imageNo . "-" . $fileInfo["filename"] . ".jpg");
                $imageNo++;
                continue;
            }
            if (file_exists($dir . DIRECTORY_SEPARATOR . $imageNo . "-" . $fileInfo["filename"] . ".webp")) {
                rename($dir . DIRECTORY_SEPARATOR . $imageNo . "-" . $fileInfo["filename"] . ".webp", $dir . DIRECTORY_SEPARATOR . trim($user) . "-" . $imageNo . "-" . $fileInfo["filename"] . ".webp");
                $imageNo++;
                continue;
            }

            // 情况 3 缺少描述
            if (file_exists($dir . DIRECTORY_SEPARATOR . trim($user) . "-" . $imageNo . "-" . $fileInfo["filename"] . ".jpg")) {
                if ($description != null) {
                    rename($dir . DIRECTORY_SEPARATOR . trim($user) . "-" . $imageNo . "-" . $fileInfo["filename"] . ".jpg", $dir . DIRECTORY_SEPARATOR . trim($user) . "-" . $description . "-" . $imageNo . "-" . $fileInfo["filename"] . ".jpg");
                }
                $imageNo++;
                continue;
            }
            if (file_exists($dir . DIRECTORY_SEPARATOR . trim($user) . "-" . $imageNo . "-" . $fileInfo["filename"] . ".webp")) {
                if ($description != null) {
                    rename($dir . DIRECTORY_SEPARATOR . trim($user) . "-" . $imageNo . "-" . $fileInfo["filename"] . ".webp", $dir . DIRECTORY_SEPARATOR . trim($user) . "-" . $description . "-" . $imageNo . "-" . $fileInfo["filename"] . ".webp");
                }
                $imageNo++;
                continue;
            }

            // 情况 4 已存在则返回
            if (file_exists($dir . DIRECTORY_SEPARATOR . trim($user) . "-" . $description . "-" . $imageNo . "-" . $fileInfo["filename"] . ".jpg")) {
                # code...
                $imageNo++;
                continue;
            }
            if (file_exists($dir . DIRECTORY_SEPARATOR . trim($user) . "-" . $description . "-" . $imageNo . "-" . $fileInfo["basename"])) {
                # code...
                $imageNo++;
                continue;
            }

            // 情况 5 user 为空
            if (file_exists($dir . DIRECTORY_SEPARATOR . "-" . $description . "-" . $imageNo . "-" . $fileInfo["filename"] . ".jpg")) {
                rename($dir . DIRECTORY_SEPARATOR . "-" . $description . "-" . $imageNo . "-" . $fileInfo["filename"] . ".jpg", $dir . DIRECTORY_SEPARATOR . trim($user) . "-" . $description . "-" . $imageNo . "-" . $fileInfo["filename"] . ".jpg");
                $imageNo++;
                continue;
            }
            if (file_exists($dir . DIRECTORY_SEPARATOR . "-" . $description . "-" . $imageNo . "-" . $fileInfo["basename"])) {
                rename($dir . DIRECTORY_SEPARATOR . "-" . $description . "-" . $imageNo . "-" . $fileInfo["basename"], $dir . DIRECTORY_SEPARATOR . trim($user) . "-" . $description . "-" . $imageNo . "-" . $fileInfo["basename"]);
                $imageNo++;
                continue;
            }
            // dump($fileInfo);
            $attempts = 0;
            $content = "";
            do {
                try {
                    $curl_handle = curl_init();


                    curl_setopt_array($curl_handle, array(
                        CURLOPT_URL => $trueImageUrl,
                        CURLOPT_RETURNTRANSFER => true,
                        CURLOPT_ENCODING => '',
                        CURLOPT_MAXREDIRS => 10,
                        CURLOPT_TIMEOUT => 0,
                        CURLOPT_FOLLOWLOCATION => true,
                        CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
                        CURLOPT_CUSTOMREQUEST => 'GET',
                        CURLOPT_HTTPHEADER => array(
                            'Connection: keep-alive',
                            'sec-ch-ua: " Not A;Brand";v="99", "Chromium";v="98", "Google Chrome";v="98"',
                            'sec-ch-ua-mobile: ?0',
                            'User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.109 Safari/537.36',
                            'sec-ch-ua-platform: "macOS"',
                            'Accept: image/avif,image/webp,image/apng,image/svg+xml,image/*,*/*;q=0.8',
                            'Sec-Fetch-Site: same-origin',
                            'Sec-Fetch-Mode: no-cors',
                            'Sec-Fetch-Dest: image',
                            'Accept-Language: zh-CN,zh;q=0.9',
                            'Cookie: UM_distinctid=17e8fc4c12917-0742b5d542c2af-133a6253-13c680-17e8fc4c12a924; ASPSESSIONIDCWCCSCAC=EODDLCJCADBNDFDGCMALGMKO; CNZZDATA1278618868=1237248404-1643081659-%7C1646134190; ASPSESSIONIDCWCDTDAD=HAJGDPOCNBIKMMMNLCENPLAM'
                        ),
                    ));


                    $content = curl_exec($curl_handle);
                    if ($content === false) {
                        $le = new Exception("get image has error: " . curl_error($curl_handle));
                        curl_close($curl_handle);
                        throw $le;
                    }
                    curl_close($curl_handle);
                    //                    $content = file_get_contents($trueImageUrl);
                } catch (ErrorException | Exception $e) {
                    echo $e->getTraceAsString() . "\n";
                    $sleepTime = 10000 * random_int(100, 1000);
                    echo "wait for $trueImageUrl sleep {$sleepTime} nano second \n";
                    usleep($sleepTime);
                    $attempts++;
                    continue;
                }
                break;
            } while ($attempts < 100);
            if ($content != "") {
                dump("new file is " .$dir . DIRECTORY_SEPARATOR . trim($user) . "-" . $description . "-" . $imageNo . "-" . $fileInfo["basename"]);
                file_put_contents($dir . DIRECTORY_SEPARATOR . trim($user) . "-" . $description . "-" . $imageNo . "-" . $fileInfo["basename"], $content);
            } else {
                Log::error("image content is empty " . $trueImageUrl);
            }
            $imageNo++;
            //            dump("current imageNo: " . $imageNo);
        }
    }

    public function getEncodeHtmlContent($url)
    {
        $attempts = 0;
        $html = "";
        $arrContextOptions = array(
            "ssl" => array(
                "allow_self_signed" => true,
                "verify_peer" => false,
                "verify_peer_name" => false,
            ),
        );
        do {
            try {
                $curl = curl_init();

                curl_setopt_array($curl, array(
                    CURLOPT_URL => $url,
                    CURLOPT_RETURNTRANSFER => true,
                    CURLOPT_ENCODING => 'UTF-8',
                    CURLOPT_MAXREDIRS => 10,
                    CURLOPT_TIMEOUT => 0,
                    CURLOPT_FOLLOWLOCATION => true,
                    CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
                    CURLOPT_CUSTOMREQUEST => 'GET',
                    CURLOPT_SSL_VERIFYPEER => false,
                    CURLOPT_SSL_VERIFYHOST => false,

                    CURLOPT_HTTPHEADER => array(
                        'authority: www.xiurenji.net',
                        'pragma: no-cache',
                        'cache-control: no-cache',
                        'sec-ch-ua: " Not;A Brand";v="99", "Google Chrome";v="91", "Chromium";v="91"',
                        'sec-ch-ua-mobile: ?0',
                        'upgrade-insecure-requests: 1',
                        'user-agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36',
                        'accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
                        'sec-fetch-site: same-origin',
                        'sec-fetch-mode: navigate',
                        'sec-fetch-user: ?1',
                        'sec-fetch-dest: document',
                        'referer: https://www.xiurenji.net/XiuRen/',
                        'accept-language: zh-CN,zh;q=0.9',
                        'cookie: UM_distinctid=177fd93a0ca93c-06b94658d5d337-121a4759-13c680-177fd93a0cbcaf; ASPSESSIONIDCATDQACD=FDPMPCLAMHNCPJFCBLKFLCKH; CNZZDATA1278618868=367774893-1614867004-%7C1625926983; __51cke__=; __tins__20641871=%7B%22sid%22%3A%201625931982756%2C%20%22vd%22%3A%203%2C%20%22expires%22%3A%201625933829110%7D; __51laig__=7'
                    ),
                ));

                $response = curl_exec($curl);
                $error = curl_error($curl);
                echo $error;
                curl_close($curl);

                //                echo $response;
                //                $html = iconv('gb2312','UTF-8//IGNORE', $response);
                $html = iconv_gbk_to_uft8($response);
                $this->queryNew->setHtml($response);
                //                $html = $response;
            } catch (Exception $e) {
                echo $e->getMessage() . "\n";
                echo $e->getTraceAsString() . "\n";
                $sleepTime = 10000 * random_int(100, 1000);
                echo "sleep {$sleepTime} nano second \n";
                usleep($sleepTime);
                $attempts++;
                continue;
            }
            break;
        } while ($attempts < 100);
        // dump("current url: " . $url);
        return $this->queryInstance->setHtml($html);
    }


    private function checkAlbumHasDownload($albumName)
    {
        $record = ImageRecord::where("name", $albumName)->first();
        if ($record != null) {
            return true;
        }
    }
}