slake-school-service/database/seeders/CrawlSourcesSeeder.php

<?php

namespace Database\Seeders;

use App\Models\CrawlSource;
use Illuminate\Database\Seeder;

class CrawlSourcesSeeder extends Seeder
{
    public function run(): void
    {
        $paperSchema = [
            'fields' => [
                [
                    'key' => 'keyword',
                    'type' => 'textarea',
                    'label' => '搜索关键词（选填）',
                    'required' => false,
                    'placeholder' => '多个关键词用逗号或换行分隔，如：graph neural, AI',
                ],
                [
                    'key' => 'max_results',
                    'type' => 'number',
                    'label' => '条数上限',
                    'default' => 20,
                    'min' => 1,
                    'max' => 50,
                ],
            ],
        ];

        CrawlSource::query()->updateOrCreate(
            ['adapter_code' => 'arxiv_api', 'target_type' => 'paper'],
            [
                'name' => 'arXiv',
                'entry_url' => 'https://arxiv.org/',
                'match_domains' => ['arxiv.org', 'export.arxiv.org'],
                'config' => ['api_base' => 'https://export.arxiv.org/api/query'],
                'param_schema' => $paperSchema,
                'status' => 1,
                'sort' => 10,
            ]
        );

        $newsSchema = [
            'fields' => [
                [
                    'key' => 'keyword',
                    'type' => 'textarea',
                    'label' => '搜索关键词（选填）',
                    'required' => false,
                    'placeholder' => '多个关键词用空格、逗号或换行分隔，如：融资 科创板 AI',
                ],
                [
                    'key' => 'max_pages',
                    'type' => 'number',
                    'label' => '抓取页数',
                    'default' => 5,
                    'min' => 1,
                    'max' => 50,
                    'placeholder' => '列表分页时连续抓取多页',
                ],
                [
                    'key' => 'max_results',
                    'type' => 'number',
                    'label' => '条数上限',
                    'default' => 30,
                    'min' => 1,
                    'max' => 50,
                ],
            ],
        ];

        CrawlSource::query()->updateOrCreate(
            ['adapter_code' => 'pedaily_html', 'target_type' => 'industry_news'],
            [
                'name' => '投资界',
                'entry_url' => 'https://www.pedaily.cn/all/',
                'match_domains' => ['pedaily.cn', 'www.pedaily.cn', '*.pedaily.cn'],
                'config' => [],
                'param_schema' => $newsSchema,
                'status' => 1,
                'sort' => 20,
            ]
        );

        CrawlSource::query()->updateOrCreate(
            ['adapter_code' => 'generic_news_html', 'target_type' => 'industry_news'],
            [
                'name' => '通用资讯 HTML',
                'entry_url' => 'https://',
                'match_domains' => ['*'],
                'config' => [],
                'param_schema' => $newsSchema,
                'status' => 1,
                'sort' => 100,
            ]
        );

        CrawlSource::query()->updateOrCreate(
            ['adapter_code' => 'generic_paper_html', 'target_type' => 'paper'],
            [
                'name' => '通用论文 HTML',
                'entry_url' => 'https://',
                'match_domains' => ['*'],
                'config' => [],
                'param_schema' => $paperSchema,
                'status' => 1,
                'sort' => 100,
            ]
        );

        $teacherSchema = [
            'fields' => [
                [
                    'key' => 'keyword',
                    'type' => 'textarea',
                    'label' => '搜索关键词（选填）',
                    'required' => false,
                    'placeholder' => '多个关键词用空格、逗号或换行分隔',
                ],
                [
                    'key' => 'max_pages',
                    'type' => 'number',
                    'label' => '抓取页数',
                    'default' => 5,
                    'min' => 1,
                    'max' => 50,
                    'placeholder' => '列表分页时连续抓取多页',
                ],
                [
                    'key' => 'max_results',
                    'type' => 'number',
                    'label' => '条数上限',
                    'default' => 200,
                    'min' => 1,
                    'max' => 500,
                ],
            ],
        ];

        CrawlSource::query()->updateOrCreate(
            ['adapter_code' => 'faculty_list_html', 'target_type' => 'teacher'],
            [
                'name' => '师资列表页（通用 HTML）',
                'entry_url' => 'https://',
                'match_domains' => ['*'],
                'config' => [],
                'param_schema' => $teacherSchema,
                'status' => 1,
                'sort' => 30,
            ]
        );

        $this->command?->info('采集源 arXiv / 投资界 / 通用 HTML / 师资列表 已写入。');
    }
}