解析

POST /parse

上传并解析文件

cURL

curl --request POST \
  --url https://api.firecrawl.dev/v2/parse \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file' \
  --form 'options={
  "blockAds": true,
  "excludeTags": [
    "<string>"
  ],
  "formats": [
    "markdown"
  ],
  "headers": {},
  "includeTags": [
    "<string>"
  ],
  "integration": "<string>",
  "onlyMainContent": true,
  "origin": "api",
  "parsers": [
    "pdf"
  ],
  "removeBase64Images": true,
  "skipTlsVerification": true,
  "timeout": 30000,
  "zeroDataRetention": false
}'

200

{
  "data": {
    "actions": {
      "javascriptReturns": [
        {
          "type": "<string>",
          "value": "<unknown>"
        }
      ],
      "pdfs": [
        "<string>"
      ],
      "scrapes": [
        {
          "html": "<string>",
          "url": "<string>"
        }
      ],
      "screenshots": [
        "<string>"
      ]
    },
    "answer": "<string>",
    "audio": "<string>",
    "branding": {
      "animations": {},
      "colors": {
        "accent": "<string>",
        "background": "<string>",
        "error": "<string>",
        "link": "<string>",
        "primary": "<string>",
        "secondary": "<string>",
        "success": "<string>",
        "textPrimary": "<string>",
        "textSecondary": "<string>",
        "warning": "<string>"
      },
      "components": {
        "buttonPrimary": {
          "background": "<string>",
          "borderRadius": "<string>",
          "textColor": "<string>"
        },
        "buttonSecondary": {
          "background": "<string>",
          "borderColor": "<string>",
          "borderRadius": "<string>",
          "textColor": "<string>"
        },
        "input": {}
      },
      "fonts": [
        {
          "family": "<string>"
        }
      ],
      "icons": {},
      "images": {
        "favicon": "<string>",
        "logo": "<string>",
        "ogImage": "<string>"
      },
      "layout": {},
      "logo": "<string>",
      "personality": {},
      "spacing": {
        "baseUnit": 123,
        "borderRadius": "<string>",
        "margins": {},
        "padding": {}
      },
      "typography": {
        "fontFamilies": {
          "code": "<string>",
          "heading": "<string>",
          "primary": "<string>"
        },
        "fontSizes": {
          "body": "<string>",
          "h1": "<string>",
          "h2": "<string>",
          "h3": "<string>"
        },
        "fontWeights": {
          "bold": 123,
          "light": 123,
          "medium": 123,
          "regular": 123
        },
        "lineHeights": {
          "body": "<string>",
          "heading": "<string>"
        }
      }
    },
    "changeTracking": {
      "diff": "<string>",
      "json": {},
      "previousScrapeAt": "2023-11-07T05:31:56Z"
    },
    "highlights": "<string>",
    "html": "<string>",
    "links": [
      "<string>"
    ],
    "markdown": "<string>",
    "metadata": {
      "<any other metadata> ": "<string>",
      "concurrencyLimited": true,
      "concurrencyQueueDurationMs": 123,
      "contentType": "<string>",
      "description": "<string>",
      "error": "<string>",
      "keywords": "<string>",
      "language": "<string>",
      "ogLocaleAlternate": [
        "<string>"
      ],
      "sourceURL": "<string>",
      "statusCode": 123,
      "title": "<string>",
      "url": "<string>"
    },
    "rawHtml": "<string>",
    "screenshot": "<string>",
    "summary": "<string>",
    "video": "<string>",
    "warning": "<string>"
  },
  "success": true
}

上传本地或非公开文档，并将其转换为整洁、可供 LLM 使用的数据。/parse 通过 multipart/form-data 接收文件二进制内容，并返回 Markdown、JSON、HTML、链接、图像或摘要——同时保留阅读顺序和表格。

• 将 PDF、DOCX、XLSX、HTML 等转换为 Markdown 或结构化 JSON
• 借助基于 Rust 的引擎，解析速度最高可提升 5 倍
• 单次请求最多支持 50 MB 的文件
• 支持零数据保留

​

何时使用 /parse

当源文档是本地文件或无法通过公开 URL 访问时，请使用 /parse。如果你有一个指向文档的公开 URL，建议优先使用 /scrape——它会根据扩展名或内容类型自动识别文件类型，并以相同方式解析。

来源	端点
指向文档的公开 URL (例如 https://example.com/report.pdf)	POST /scrape
本地文件或非公开字节流 (PDF、DOCX、XLSX、HTML 等)	POST /parse (此端点)

授权

Authorization · string · header · 必填

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

请求体

multipart/form-data

file · file · 必填

要解析的文件字节。支持的扩展名：.html、.htm、.pdf、.docx、.doc、.odt、.rtf、.xlsx、.xls。

options · object

可选的解析选项，以 JSON 形式通过 multipart 的 options 字段传递。

Show child attributes

响应

200

application/json

成功响应

data · object

Show child attributes

success · boolean