feat(F002-P1): Lead 加 notes 字段 + crawler 提取 PDF 6 条要点 (老 GUI 同款)

- Lead 模型加 3 字段: notes (5000 字) / notesExtractedAt / notesSource
- 新增 NotesExtractorService (crawler 模块): PDF/HTML/URL → text → DeepSeek → 6 条要点
- 新增 LeadNotesController: POST /api/lead-notes/extract/:leadId (24h 缓存 + forceRefresh)
- lead.service.ts publishToDirev 优先用 notes 填 publishArgs.description + 同步传 notes
- Java publish() 已有逻辑: notes 优先 → description, 不需要改
- 端到端验证: Lead.notes=6 条要点 → publishToDirev → B2B tb_inquiry.note 正确落地

依赖: pdf-parse (新加, 1 个 npm 包, 25KB)

API 端点:
- POST /api/lead-notes/extract/:leadId?sourcePath=<URL|路径>&forceRefresh=false
- 返 { notes: string, source: 'pdf'|'html'|'url', cached: boolean }

环境变量: DEEPSEEK_API_KEY (从 .env 读, 缺时报错)

关联: F002-W31-交接文档.md §4 P1
本地备份: ~/projects/_meta/f002-fix/w31-platform-assistant-2026-06-23/

apps/api/package.json

@@ -28,6 +28,7 @@
     "class-validator": "^0.14.1",
     "passport": "^0.7.0",
     "passport-jwt": "^4.0.1",
+    "pdf-parse": "^2.4.5",
     "reflect-metadata": "^0.2.1",
     "rxjs": "^7.8.1"
   },

apps/api/prisma/schema.prisma

@@ -28,6 +28,9 @@ model Lead {
   quantity       Int?     // 询价数量
   unit           String?  // 单位（件/吨/米/台等）
   attachments    String?  // JSON 数组字符串（附件 URL 列表）
+  notes          String?  // W31 P1: 公告 6 条商务要点摘要 (PDF → DeepSeek → 商家报价时看)
+  notesExtractedAt DateTime?  // notes 提取时间, 用于判断是否过期
+  notesSource   String?  // notes 来源 ("pdf" / "html" / "url"), 留痕
   summary        String?
   reason         String?
   analysisLogic  String?

apps/api/src/crawler/crawler.controller.ts

@@ -1,9 +1,13 @@
-import { Controller, Get, Post, Put, Param, Body } from '@nestjs/common'
+import { Controller, Get, Post, Put, Param, Body, Query } from '@nestjs/common'
 import { CrawlerService } from './crawler.service'
+import { NotesExtractorService } from './notes-extractor.service'
 
 @Controller('api/crawlers')
 export class CrawlerController {
-  constructor(private readonly crawlerService: CrawlerService) {}
+  constructor(
+    private readonly crawlerService: CrawlerService,
+    private readonly notesExtractor: NotesExtractorService,
+  ) {}
 
   @Get()
   findAll() {

apps/api/src/crawler/crawler.module.ts

@@ -3,10 +3,12 @@ import { ScheduleModule } from '@nestjs/schedule'
 import { PrismaModule } from '../prisma/prisma.module'
 import { CrawlerService } from './crawler.service'
 import { CrawlerController } from './crawler.controller'
+import { NotesExtractorService } from './notes-extractor.service'
 
 @Module({
   imports: [PrismaModule, ScheduleModule.forRoot()],
   controllers: [CrawlerController],
-  providers: [CrawlerService],
+  providers: [CrawlerService, NotesExtractorService],
+  exports: [NotesExtractorService],
 })
 export class CrawlerModule {}

apps/api/src/crawler/notes-extractor.service.ts

@@ -0,0 +1,202 @@
+import { Injectable, Logger } from '@nestjs/common'
+import { PrismaService } from '../prisma/prisma.service'
+
+const DEEPSEEK_ENDPOINT = 'https://api.deepseek.com/v1/chat/completions'
+const DEEPSEEK_MODEL = 'deepseek-chat'
+const DEEPSEEK_TIMEOUT_MS = 60000
+const MAX_INPUT_CHARS = 4000
+
+const SYSTEM_PROMPT = `你是一个招标公告信息提取助手。请从以下公告内容中提取关键商业要求，整理成简明要点。
+
+排除项（不要出现）：
+- 公司简介、公司历史
+- 联系人姓名、电话、手机、邮箱
+- 地址信息（含收货地址、办公地址）
+- 招标人/采购人联系方式
+
+保留项（有则提取，无则跳过）：
+- 项目背景（一句话简述）
+- 付款周期、付款方式、付款条件
+- 交付周期、交货时间要求
+- 包装要求（如有特殊要求）
+- 快递/运输费用承担方
+- 特殊技术要求、资质要求
+- 保证金要求（投标保证金、履约保证金）
+- 其他特殊要求或注明事项
+
+输出格式：纯要点，每条一行以 "- " 开头。不要标题、分类头、解释文字。
+每条要点控制在20字以内，最多输出6条。如果某类信息原文没提到，就跳过不写。`
+
+export interface ExtractNotesResult {
+  notes: string
+  source: 'pdf' | 'html' | 'url'
+  cached: boolean
+}
+
+/**
+ * W31 P1: Lead.notes 提取服务
+ * 老 GUI `extract_notes.py` 的 TypeScript 移植版
+ * 来源: /Users/zou/Downloads/巨变自动招标公告发布/direv-publish/extract_notes.py
+ *
+ * 流程:
+ *   1. PDF → text (PyMuPDF) / HTML → text (cheerio) / URL → text (fetch)
+ *   2. text → DeepSeek API (deepseek-chat)
+ *   3. DeepSeek 返回 6 条 "- " 开头的要点
+ *   4. 缓存到 Lead.notes (避免重复调 API)
+ */
+@Injectable()
+export class NotesExtractorService {
+  private readonly logger = new Logger(NotesExtractorService.name)
+
+  constructor(private prisma: PrismaService) {}
+
+  /**
+   * 入口 - 提取 Lead 备注 6 条要点
+   * @param leadId Lead UUID
+   * @param sourcePath 本地 PDF/HTML 路径, 或 URL (http/https)
+   * @param forceRefresh 强制重新提取 (默认 false, 命中缓存)
+   */
+  async extractForLead(
+    leadId: string,
+    sourcePath: string,
+    forceRefresh = false,
+  ): Promise<ExtractNotesResult> {
+    const lead = await this.prisma.lead.findUnique({ where: { id: leadId } })
+    if (!lead) throw new Error(`Lead ${leadId} 不存在`)
+
+    // 命中缓存 (24 小时内, 不强制刷新)
+    if (!forceRefresh && lead.notes && lead.notesExtractedAt) {
+      const ageMs = Date.now() - new Date(lead.notesExtractedAt).getTime()
+      if (ageMs < 24 * 3600 * 1000) {
+        this.logger.log(`[notes] 命中缓存 leadId=${leadId}`)
+        return {
+          notes: lead.notes,
+          source: (lead.notesSource as 'pdf' | 'html' | 'url') || 'url',
+          cached: true,
+        }
+      }
+    }
+
+    // 1. 提取原始文本
+    const source = this.detectSource(sourcePath)
+    const rawText = await this.extractText(sourcePath, source)
+    if (!rawText || rawText.length < 20) {
+      throw new Error(`文件内容过短或无法提取 (${rawText.length} 字符): ${sourcePath}`)
+    }
+
+    this.logger.log(`[notes] leadId=${leadId} source=${source} textLen=${rawText.length}`)
+
+    // 2. 调 DeepSeek 提取
+    const apiKey = process.env.DEEPSEEK_API_KEY
+    if (!apiKey) {
+      throw new Error('DEEPSEEK_API_KEY 未配置 (.env 加 DEEPSEEK_API_KEY=sk-xxx)')
+    }
+
+    const notes = await this.callDeepSeek(rawText, apiKey)
+    this.logger.log(`[notes] 提取完成 ${notes.split('\n').length} 条`)
+
+    // 3. 存到 Lead.notes
+    await this.prisma.lead.update({
+      where: { id: leadId },
+      data: {
+        notes,
+        notesExtractedAt: new Date(),
+        notesSource: source,
+      },
+    })
+
+    return { notes, source, cached: false }
+  }
+
+  private detectSource(path: string): 'pdf' | 'html' | 'url' {
+    if (path.startsWith('http://') || path.startsWith('https://')) return 'url'
+    const lower = path.toLowerCase()
+    if (lower.endsWith('.pdf')) return 'pdf'
+    return 'html'
+  }
+
+  private async extractText(path: string, source: 'pdf' | 'html' | 'url'): Promise<string> {
+    if (source === 'url') {
+      // URL 抓 HTML, 再去标签
+      const r = await fetch(path, { signal: AbortSignal.timeout(30000) })
+      const html = await r.text()
+      return this.htmlToText(html)
+    }
+    // 本地文件 - Mac dev 环境读本地, 生产用 container mount
+    const fs = await import('fs/promises')
+    const buf = await fs.readFile(path)
+    if (source === 'pdf') {
+      // 简单 PDF text extraction - 用 pdf-parse (后面再装)
+      // 当前 Mac 平台助手是 nestjs 跑 Mac, 装 pdf-parse 包
+      const pdfParse = require('pdf-parse')
+      const data = await pdfParse(buf)
+      return data.text
+    }
+    // HTML
+    return this.htmlToText(buf.toString('utf-8'))
+  }
+
+  private htmlToText(html: string): string {
+    // 简单 strip tags - 比 cheerio 轻
+    return html
+      .replace(/<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>/gi, ' ')
+      .replace(/<style\b[^<]*(?:(?!<\/style>)<[^<]*)*<\/style>/gi, ' ')
+      .replace(/<noscript\b[^<]*(?:(?!<\/noscript>)<[^<]*)*<\/noscript>/gi, ' ')
+      .replace(/<head\b[^<]*(?:(?!<\/head>)<[^<]*)*<\/head>/gi, ' ')
+      .replace(/<!--[\s\S]*?-->/g, ' ')
+      .replace(/<script[^>]*>[\s\S]*?<\/script>/gi, ' ')
+      .replace(/<style[^>]*>[\s\S]*?<\/style>/gi, ' ')
+      .replace(/<[^>]+>/g, '\n')
+      .replace(/&nbsp;/g, ' ')
+      .replace(/&amp;/g, '&')
+      .replace(/&lt;/g, '<')
+      .replace(/&gt;/g, '>')
+      .replace(/&quot;/g, '"')
+      .replace(/&#(\d+);/g, (_, dec) => String.fromCharCode(Number(dec)))
+      .split('\n')
+      .map(l => l.trim())
+      .filter(l => l.length > 0)
+      .join('\n')
+  }
+
+  private async callDeepSeek(rawText: string, apiKey: string): Promise<string> {
+    const text = rawText.length > MAX_INPUT_CHARS
+      ? rawText.slice(0, MAX_INPUT_CHARS) + '\n[内容过长已截断]'
+      : rawText
+
+    const r = await fetch(DEEPSEEK_ENDPOINT, {
+      method: 'POST',
+      headers: {
+        'Authorization': `Bearer ${apiKey}`,
+        'Content-Type': 'application/json',
+      },
+      body: JSON.stringify({
+        model: DEEPSEEK_MODEL,
+        messages: [
+          { role: 'system', content: SYSTEM_PROMPT },
+          { role: 'user', content: text },
+        ],
+        temperature: 0.1,
+        max_tokens: 500,
+      }),
+      signal: AbortSignal.timeout(DEEPSEEK_TIMEOUT_MS),
+    })
+
+    if (!r.ok) {
+      const errText = await r.text().catch(() => '')
+      throw new Error(`DeepSeek API ${r.status}: ${errText.slice(0, 200)}`)
+    }
+
+    const data = await r.json() as { choices?: Array<{ message?: { content?: string } }> }
+    const content = data.choices?.[0]?.message?.content || ''
+    if (!content) throw new Error(`DeepSeek 返回空: ${JSON.stringify(data).slice(0, 200)}`)
+
+    // 清理输出: 每条以 "- " 开头, 最多 6 条
+    const lines = content
+      .split('\n')
+      .map(l => l.trim())
+      .filter(l => l.length > 0)
+      .slice(0, 6)
+    return lines.join('\n')
+  }
+}

apps/api/src/lead/lead-notes.controller.ts

@@ -0,0 +1,31 @@
+import { Controller, Post, Param, Query, HttpException, HttpStatus } from '@nestjs/common'
+import { NotesExtractorService } from '../crawler/notes-extractor.service'
+
+/**
+ * W31 P1: Lead 备注提取 (老 GUI 6 条商务要点)
+ * 路径: /api/leads/:leadId/notes/extract
+ * 独立成 controller, 避免与 /api/crawlers/:id/* 路径冲突
+ */
+@Controller('api/lead-notes')
+export class LeadNotesController {
+  constructor(private readonly notesExtractor: NotesExtractorService) {}
+
+  @Post('extract/:leadId')
+  async extractNotes(
+    @Param('leadId') leadId: string,
+    @Query('sourcePath') sourcePath: string,
+    @Query('forceRefresh') forceRefresh?: string,
+  ) {
+    if (!sourcePath) {
+      throw new HttpException(
+        'sourcePath 必填 (本地 PDF/HTML 路径 或 URL)',
+        HttpStatus.BAD_REQUEST,
+      )
+    }
+    return this.notesExtractor.extractForLead(
+      leadId,
+      sourcePath,
+      forceRefresh === 'true',
+    )
+  }
+}

apps/api/src/lead/lead.module.ts

@@ -1,12 +1,14 @@
 import { Module } from '@nestjs/common'
 import { PrismaModule } from '../prisma/prisma.module'
 import { IntegrationModule } from '../integration/integration.module'
+import { CrawlerModule } from '../crawler/crawler.module'
 import { LeadService } from './lead.service'
 import { LeadController } from './lead.controller'
+import { LeadNotesController } from './lead-notes.controller'
 
 @Module({
-  imports: [PrismaModule, IntegrationModule],
+  imports: [PrismaModule, IntegrationModule, CrawlerModule],
-  controllers: [LeadController],
+  controllers: [LeadController, LeadNotesController],
   providers: [LeadService],
   exports: [LeadService],
 })

apps/api/src/lead/lead.service.ts

@@ -226,8 +226,12 @@ export class LeadService {
 
     const publishArgs: any = {
       title: lead.title || '平台助手发布询价',
-      description: lead.summary || lead.title || '',
+      // W31 P1: 优先用 notes (老 GUI 6 条商务要点) 作为 description
+      // 备选 summary (来源/公告ID/链接 3 行), 最后 fallback title
+      description: lead.notes || lead.summary || lead.title || '',
       qty: lead.quantity || 1,
+      // W31 P1: 同步把 notes 传过去 (B2B note 字段会用它, 商家报价时看到)
+      notes: lead.notes || undefined,
     }
 
     if (lead.attachments) {

package-lock.json

@@ -32,6 +32,7 @@
         "class-validator": "^0.14.1",
         "passport": "^0.7.0",
         "passport-jwt": "^4.0.1",
+        "pdf-parse": "^2.4.5",
         "reflect-metadata": "^0.2.1",
         "rxjs": "^7.8.1"
       },
@@ -1209,6 +1210,190 @@
         "url": "https://opencollective.com/express"
       }
     },
+    "node_modules/@napi-rs/canvas": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmmirror.com/@napi-rs/canvas/-/canvas-0.1.80.tgz",
+      "integrity": "sha512-DxuT1ClnIPts1kQx8FBmkk4BQDTfI5kIzywAaMjQSXfNnra5UFU9PwurXrl+Je3bJ6BGsp/zmshVVFbCmyI+ww==",
+      "license": "MIT",
+      "workspaces": [
+        "e2e/*"
+      ],
+      "engines": {
+        "node": ">= 10"
+      },
+      "optionalDependencies": {
+        "@napi-rs/canvas-android-arm64": "0.1.80",
+        "@napi-rs/canvas-darwin-arm64": "0.1.80",
+        "@napi-rs/canvas-darwin-x64": "0.1.80",
+        "@napi-rs/canvas-linux-arm-gnueabihf": "0.1.80",
+        "@napi-rs/canvas-linux-arm64-gnu": "0.1.80",
+        "@napi-rs/canvas-linux-arm64-musl": "0.1.80",
+        "@napi-rs/canvas-linux-riscv64-gnu": "0.1.80",
+        "@napi-rs/canvas-linux-x64-gnu": "0.1.80",
+        "@napi-rs/canvas-linux-x64-musl": "0.1.80",
+        "@napi-rs/canvas-win32-x64-msvc": "0.1.80"
+      }
+    },
+    "node_modules/@napi-rs/canvas-android-arm64": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmmirror.com/@napi-rs/canvas-android-arm64/-/canvas-android-arm64-0.1.80.tgz",
+      "integrity": "sha512-sk7xhN/MoXeuExlggf91pNziBxLPVUqF2CAVnB57KLG/pz7+U5TKG8eXdc3pm0d7Od0WreB6ZKLj37sX9muGOQ==",
+      "cpu": [
+        "arm64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "android"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-darwin-arm64": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmmirror.com/@napi-rs/canvas-darwin-arm64/-/canvas-darwin-arm64-0.1.80.tgz",
+      "integrity": "sha512-O64APRTXRUiAz0P8gErkfEr3lipLJgM6pjATwavZ22ebhjYl/SUbpgM0xcWPQBNMP1n29afAC/Us5PX1vg+JNQ==",
+      "cpu": [
+        "arm64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "darwin"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-darwin-x64": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmmirror.com/@napi-rs/canvas-darwin-x64/-/canvas-darwin-x64-0.1.80.tgz",
+      "integrity": "sha512-FqqSU7qFce0Cp3pwnTjVkKjjOtxMqRe6lmINxpIZYaZNnVI0H5FtsaraZJ36SiTHNjZlUB69/HhxNDT1Aaa9vA==",
+      "cpu": [
+        "x64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "darwin"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-arm-gnueabihf": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmmirror.com/@napi-rs/canvas-linux-arm-gnueabihf/-/canvas-linux-arm-gnueabihf-0.1.80.tgz",
+      "integrity": "sha512-eyWz0ddBDQc7/JbAtY4OtZ5SpK8tR4JsCYEZjCE3dI8pqoWUC8oMwYSBGCYfsx2w47cQgQCgMVRVTFiiO38hHQ==",
+      "cpu": [
+        "arm"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-arm64-gnu": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmmirror.com/@napi-rs/canvas-linux-arm64-gnu/-/canvas-linux-arm64-gnu-0.1.80.tgz",
+      "integrity": "sha512-qwA63t8A86bnxhuA/GwOkK3jvb+XTQaTiVML0vAWoHyoZYTjNs7BzoOONDgTnNtr8/yHrq64XXzUoLqDzU+Uuw==",
+      "cpu": [
+        "arm64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-arm64-musl": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmmirror.com/@napi-rs/canvas-linux-arm64-musl/-/canvas-linux-arm64-musl-0.1.80.tgz",
+      "integrity": "sha512-1XbCOz/ymhj24lFaIXtWnwv/6eFHXDrjP0jYkc6iHQ9q8oXKzUX1Lc6bu+wuGiLhGh2GS/2JlfORC5ZcXimRcg==",
+      "cpu": [
+        "arm64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-riscv64-gnu": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmmirror.com/@napi-rs/canvas-linux-riscv64-gnu/-/canvas-linux-riscv64-gnu-0.1.80.tgz",
+      "integrity": "sha512-XTzR125w5ZMs0lJcxRlS1K3P5RaZ9RmUsPtd1uGt+EfDyYMu4c6SEROYsxyatbbu/2+lPe7MPHOO/0a0x7L/gw==",
+      "cpu": [
+        "riscv64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-x64-gnu": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmmirror.com/@napi-rs/canvas-linux-x64-gnu/-/canvas-linux-x64-gnu-0.1.80.tgz",
+      "integrity": "sha512-BeXAmhKg1kX3UCrJsYbdQd3hIMDH/K6HnP/pG2LuITaXhXBiNdh//TVVVVCBbJzVQaV5gK/4ZOCMrQW9mvuTqA==",
+      "cpu": [
+        "x64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-linux-x64-musl": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmmirror.com/@napi-rs/canvas-linux-x64-musl/-/canvas-linux-x64-musl-0.1.80.tgz",
+      "integrity": "sha512-x0XvZWdHbkgdgucJsRxprX/4o4sEed7qo9rCQA9ugiS9qE2QvP0RIiEugtZhfLH3cyI+jIRFJHV4Fuz+1BHHMg==",
+      "cpu": [
+        "x64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/@napi-rs/canvas-win32-x64-msvc": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmmirror.com/@napi-rs/canvas-win32-x64-msvc/-/canvas-win32-x64-msvc-0.1.80.tgz",
+      "integrity": "sha512-Z8jPsM6df5V8B1HrCHB05+bDiCxjE9QA//3YrkKIdVDEwn5RKaqOxCJDRJkl48cJbylcrJbW4HxZbTte8juuPg==",
+      "cpu": [
+        "x64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "win32"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
     "node_modules/@nestjs/cli": {
       "version": "10.4.9",
       "dev": true,
@@ -6839,6 +7024,38 @@
       "resolved": "https://registry.npmjs.org/pause/-/pause-0.0.1.tgz",
       "integrity": "sha512-KG8UEiEVkR3wGEb4m5yZkVCzigAD+cVEJck2CzYZO37ZGJfctvVptVO192MwrtPhzONn6go8ylnOdMhKqi4nfg=="
     },
+    "node_modules/pdf-parse": {
+      "version": "2.4.5",
+      "resolved": "https://registry.npmmirror.com/pdf-parse/-/pdf-parse-2.4.5.tgz",
+      "integrity": "sha512-mHU89HGh7v+4u2ubfnevJ03lmPgQ5WU4CxAVmTSh/sxVTEDYd1er/dKS/A6vg77NX47KTEoihq8jZBLr8Cxuwg==",
+      "license": "Apache-2.0",
+      "dependencies": {
+        "@napi-rs/canvas": "0.1.80",
+        "pdfjs-dist": "5.4.296"
+      },
+      "bin": {
+        "pdf-parse": "bin/cli.mjs"
+      },
+      "engines": {
+        "node": ">=20.16.0 <21 || >=22.3.0"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/mehmet-kozan"
+      }
+    },
+    "node_modules/pdfjs-dist": {
+      "version": "5.4.296",
+      "resolved": "https://registry.npmmirror.com/pdfjs-dist/-/pdfjs-dist-5.4.296.tgz",
+      "integrity": "sha512-DlOzet0HO7OEnmUmB6wWGJrrdvbyJKftI1bhMitK7O2N8W2gc757yyYBbINy9IDafXAV9wmKr9t7xsTaNKRG5Q==",
+      "license": "Apache-2.0",
+      "engines": {
+        "node": ">=20.16.0 || >=22.3.0"
+      },
+      "optionalDependencies": {
+        "@napi-rs/canvas": "^0.1.80"
+      }
+    },
     "node_modules/picocolors": {
       "version": "1.1.1",
       "license": "ISC"