useds/app/command/EmailParseCommand.php

<?php
namespace app\command;

use support\Db;
use Symfony\Component\Console\Command\Command;
use Symfony\Component\Console\Input\InputInterface;
use Symfony\Component\Console\Output\OutputInterface;

/**
 * 将拉取邮箱的详情进行清洗，找出询盘的邮件入库（根据emai_detail）
 */
class EmailParseCommand extends Command
{
    protected static $defaultName        = 'email-parse';
    protected static $defaultDescription = '邮件清洗';

    protected function configure()
    {
        // 不再接收参数，固定每次 100 条
    }

    protected function execute(InputInterface $input, OutputInterface $output): int
    {
        $batchSize = 100;   // 每次处理 100 条
        $page      = 0;

        // 明确定义 parsed_contacts 表里要插入的所有列（顺序无所谓，但要全部包含）
        $fields = [
            'email_id',
            'date',
            'email',
            'name',
            'tel',
            'company',
            'country',
            'form_url',
            'message',
            'ip',
            'iplocation',
            'ilang',
            'mailto',
            'navigator_language',
            'navigator_platform',
            'screen_width',
            'screen_height',
            'ucountry',
        ];

        while (true) {
            $rows = Db::table('emails')
                ->orderBy('id', 'asc')
                ->limit($batchSize)
                ->offset($page * $batchSize)
                ->get();

            if ($rows->isEmpty()) {
                break;
            }

            $toInsert = [];
            foreach ($rows as $row) {
                $parsed = $this->parseHtml($row->body);
                if ($parsed === null) {
                    $output->writeln("  ↳ [{$row->id}] skip: not a contact-form HTML");
                    continue;
                }

                // 严格按 $fields 顺序填充每条记录，缺失的字段补 null
                $record = [];
                foreach ($fields as $col) {
                    if ($col === 'email_id') {
                        $record[$col] = $row->id;
                    } else {
                        $record[$col] = $parsed[$col] ?? null;
                    }
                }

                $toInsert[] = $record;
            }

            if (!empty($toInsert)) {
                Db::table('email_parsed_result')->insert($toInsert);
                $output->writeln("Inserted batch #" . ($page + 1) . ", count: " . count($toInsert));
            }

            $page++;
        }

        $output->writeln("✔ All done.");
        return Command::SUCCESS;
    }

    /**
     * 解析 HTML，找不到 <h2>Preview</h2> 则返回 null，
     * 否则提取所有 <span>Key:</span> Value 为小写蛇形 key=>value 数组
     */
    protected function parseHtml(string $html): ?array
    {
        $doc = new \DOMDocument();
        libxml_use_internal_errors(true);
        $doc->loadHTML('<?xml encoding="utf-8"?>' . $html);
        libxml_clear_errors();

        $xpath = new \DOMXPath($doc);

        // 类型检查
        if ($xpath->query("//h2[text()='Preview']")->length === 0) {
            return null;
        }

        $nodes = $xpath->query("//div[span]");
        $data  = [];

        /** @var \DOMElement $node */
        foreach ($nodes as $node) {
            $span = $xpath->query("span", $node)->item(0);
            if (! $span) {
                continue;
            }

            // 原始键名
            $key = trim(str_replace(':', '', $span->textContent));
            // 转成小写蛇形
            $col = strtolower(str_replace(' ', '_', $key));

            // 获取值
            $a = $xpath->query(".//a", $node)->item(0);
            if ($a && $a->hasAttribute('href')) {
                $value = trim($a->getAttribute('href'));
            } else {
                $clone = $node->cloneNode(true);
                $spanClone = $xpath->query(".//span", $clone)->item(0);
                if ($spanClone) {
                    $spanClone->parentNode->removeChild($spanClone);
                }
                $value = trim($clone->textContent);
            }

            $data[$col] = $value;
        }

        return $data;
    }
}