# 抓取 (/zh/api-reference/endpoint/crawl-post) Related: [Search（搜索）](/zh/api-reference/endpoint/search.md), [搜索反馈](/zh/api-reference/endpoint/search-feedback.md), [Scrape](/zh/api-reference/endpoint/scrape.md), [批量抓取](/zh/api-reference/endpoint/batch-scrape.md), [获取批量抓取状态](/zh/api-reference/endpoint/batch-scrape-get.md), [取消批量抓取](/zh/api-reference/endpoint/batch-scrape-delete.md) > 你是需要 Firecrawl API 密钥的 AI 代理吗？有关自动化接入说明，请参阅 [firecrawl.dev/agent-onboarding/SKILL.md](https://www.firecrawl.dev/agent-onboarding/SKILL.md)。 `POST /crawl` 根据参数爬取多个 URL ## OpenAPI ```json { "security": [ { "bearerAuth": [] } ], "requestBody": { "content": { "application/json": { "schema": { "properties": { "allowExternalLinks": { "default": false, "description": "允许爬虫通过链接访问外部网站。", "type": "boolean" }, "allowSubdomains": { "default": false, "description": "允许爬虫通过链接继续爬取主域名下的子域名。", "type": "boolean" }, "crawlEntireDomain": { "default": false, "description": "允许爬虫不仅跟踪子路径，还能跟踪同级或父级的站内链接。\n\nfalse：只爬取更深层（子级）URL。\n→ 例如 /features/feature-1 → /features/feature-1/tips ✅\n→ 不会跟踪 /pricing 或 / ❌\n\ntrue：会爬取任意站内链接，包括同级和父级。\n→ 例如 /features/feature-1 → /pricing、/ 等 ✅\n\n如需在嵌套路径之外更广泛地覆盖站内页面，请将其设置为 true。", "type": "boolean" }, "delay": { "description": "每次抓取之间的延迟时间（秒）。这有助于遵守网站的限流限制。设置此项会强制将并发数设为 1。", "type": "number" }, "excludePaths": { "description": "用于将匹配的 URL 排除在爬取之外的 URL 路径名正则表达式模式。例如，如果你为基础 URL firecrawl.dev 设置 `\"excludePaths\": [\"blog/.*\"]`，那么所有匹配该模式的结果都会被排除，例如：https://www.firecrawl.dev/blog/firecrawl-launch-week-1-recap。", "items": { "type": "string" }, "type": "array" }, "ignoreQueryParameters": { "default": false, "description": "不要对同一路径使用不同（或没有）查询参数重复抓取", "type": "boolean" }, "ignoreRobotsTxt": { "default": false, "description": "忽略网站的 robots.txt 规则。仅限企业版——如需启用，请联系 support@firecrawl.com。", "type": "boolean" }, "includePaths": { "description": "在抓取过程中用于匹配 URL 的 URL 路径正则表达式规则。只有路径满足这些规则的页面才会包含在响应中。注意：起始 URL 也会基于这些规则进行检查——如果起始 URL 不匹配，本次抓取可能返回 0 个页面。例如，如果你在基础 URL firecrawl.dev/blog 下设置 \"includePaths\": [\"blog/.*\"]，那么结果中只会包含 /blog/ 下的页面，比如：https://www.firecrawl.dev/blog/firecrawl-launch-week-1-recap。", "items": { "type": "string" }, "type": "array" }, "limit": { "default": 10000, "description": "最大爬取页数。默认值为 10000。", "type": "integer" }, "maxConcurrency": { "description": "最大并发抓取数量。此参数允许你为本次抓取设置并发上限。如果未指定，则本次抓取将遵循你所在团队的并发限制。", "type": "integer" }, "maxDiscoveryDepth": { "description": "根据页面被发现的顺序设定的最大爬取深度。根站点和 sitemap 中的页面的发现深度为 0。比如，如果你将其设置为 1，并将 `sitemap` 设置为 `'skip'`，则只会爬取你输入的 URL 以及该页面上链接到的所有 URL。", "type": "integer" }, "prompt": { "description": "用于根据自然语言生成爬虫选项（包括下方的所有参数）的提示词。显式指定的参数会覆盖生成的对应参数。", "type": "string" }, "regexOnFullURL": { "default": false, "description": "当设为 true 时，includePaths 和 excludePaths 的正则表达式会匹配完整 URL（包括查询参数），而不仅仅是 URL 的路径部分。适用于需要基于查询字符串过滤 URL 的场景。", "type": "boolean" }, "robotsUserAgent": { "description": "用于评估 robots.txt 的自定义 User-Agent 字符串。设置后，系统会使用该 User-Agent 获取 robots.txt，并依据它而非默认值匹配允许/禁止规则。仅限企业版——如需启用，请联系 support@firecrawl.com。", "type": "string" }, "scrapeOptions": { "properties": { "actions": { "description": "在抓取页面内容之前需要执行的页面 actions", "items": { "oneOf": [ { "oneOf": [ { "additionalProperties": false, "properties": { "milliseconds": { "description": "要等待的毫秒数", "minimum": 1, "type": "integer" }, "type": { "description": "等待指定的毫秒数", "enum": [ "wait" ], "type": "string" } }, "required": [ "type", "milliseconds" ], "title": "Wait by Duration", "type": "object" }, { "additionalProperties": false, "properties": { "selector": { "description": "用于等待的 CSS 选择器", "example": "#my-element", "type": "string" }, "type": { "description": "等待特定元素出现", "enum": [ "wait" ], "type": "string" } }, "required": [ "type", "selector" ], "title": "Wait for Element", "type": "object" } ], "title": "Wait" }, { "properties": { "fullPage": { "default": false, "description": "是否捕获整个页面的截图（忽略 viewport.height），还是仅截取当前视口区域。", "type": "boolean" }, "quality": { "description": "截图质量，取值范围为 1 到 100，100 为最高质量。", "type": "integer" }, "type": { "description": "截取屏幕截图。链接将在响应的 `actions.screenshots` 数组中返回。", "enum": [ "screenshot" ], "type": "string" }, "viewport": { "properties": { "height": { "description": "视口高度（以像素为单位）", "type": "integer" }, "width": { "description": "以像素为单位的视口宽度", "type": "integer" } }, "required": [ "width", "height" ], "type": "object" } }, "required": [ "type" ], "title": "Screenshot", "type": "object" }, { "properties": { "all": { "default": false, "description": "点击所有匹配该选择器的元素，而不仅仅是第一个。即使没有任何元素匹配该选择器，也不会抛出错误。", "type": "boolean" }, "selector": { "description": "用于查找元素的查询选择器", "example": "#load-more-button", "type": "string" }, "type": { "description": "单击一个元素", "enum": [ "click" ], "type": "string" } }, "required": [ "type", "selector" ], "title": "Click", "type": "object" }, { "properties": { "text": { "description": "要键入的文本", "example": "Hello, world!", "type": "string" }, "type": { "description": "向输入框、文本区域或 contenteditable 元素写入文本。注意：在写入之前，你必须先使用「click」操作使该元素获得焦点。文本将以逐字符方式输入，以模拟键盘输入。", "enum": [ "write" ], "type": "string" } }, "required": [ "type", "text" ], "title": "Write text", "type": "object" }, { "description": "请在页面上按下一个按键。按键代码请参见：https://asawicki.info/nosense/doc/devices/keyboard/key_codes.html。", "properties": { "key": { "description": "要按的键", "example": "Enter", "type": "string" }, "type": { "description": "在页面上按下任意键", "enum": [ "press" ], "type": "string" } }, "required": [ "type", "key" ], "title": "Press a key", "type": "object" }, { "properties": { "direction": { "default": "down", "description": "滚动方向", "enum": [ "up", "down" ], "type": "string" }, "selector": { "description": "用于滚动的元素选择器", "example": "#my-element", "type": "string" }, "type": { "description": "滚动整个页面或某个特定元素", "enum": [ "scroll" ], "type": "string" } }, "required": [ "type" ], "title": "Scroll", "type": "object" }, { "properties": { "type": { "description": "抓取当前页面内容，并返回其 URL 和 HTML。", "enum": [ "scrape" ], "type": "string" } }, "required": [ "type" ], "title": "Scrape", "type": "object" }, { "properties": { "script": { "description": "待执行的 JavaScript 代码", "example": "document.querySelector('.button').click();", "type": "string" }, "type": { "description": "在页面上执行 JavaScript 代码", "enum": [ "executeJavascript" ], "type": "string" } }, "required": [ "type", "script" ], "title": "Execute JavaScript", "type": "object" }, { "properties": { "format": { "default": "Letter", "description": "生成的 PDF 的页面大小", "enum": [ "A0", "A1", "A2", "A3", "A4", "A5", "A6", "Letter", "Legal", "Tabloid", "Ledger" ], "type": "string" }, "landscape": { "default": false, "description": "是否以横向方向生成 PDF", "type": "boolean" }, "scale": { "default": 1, "description": "生成 PDF 的缩放比例", "type": "number" }, "type": { "description": "生成当前页面的 PDF 文件。该 PDF 文件会通过响应中的 `actions.pdfs` 数组返回。", "enum": [ "pdf" ], "type": "string" } }, "required": [ "type" ], "title": "Generate PDF", "type": "object" } ] }, "type": "array" }, "auditMetadata": { "additionalProperties": false, "description": "为组织启用 SIEM Logging 后，SIEM 日志事件中会包含用户归属信息。", "properties": { "username": { "description": "与该请求关联的用户名。", "maxLength": 1024, "type": "string" } }, "required": [ "username" ], "type": "object" }, "blockAds": { "default": true, "description": "启用广告拦截和 Cookie 弹窗拦截功能。", "type": "boolean" }, "excludeTags": { "description": "在输出中需要排除的标签。", "items": { "type": "string" }, "type": "array" }, "formats": { "default": [ "markdown" ], "description": "要在响应中包含的输出 formats。你可以指定一个或多个 formats，既可以使用字符串（例如：`'markdown'`），也可以使用带有其他选项的对象（例如：`{ type: 'json', schema: {...} }`）。某些 formats 需要配置特定选项。示例：`['markdown', { type: 'json', schema: {...} }]`。", "items": { "oneOf": [ { "properties": { "type": { "enum": [ "markdown" ], "type": "string" } }, "required": [ "type" ], "title": "Markdown", "type": "object" }, { "properties": { "type": { "enum": [ "summary" ], "type": "string" } }, "required": [ "type" ], "title": "Summary", "type": "object" }, { "properties": { "type": { "enum": [ "html" ], "type": "string" } }, "required": [ "type" ], "title": "HTML", "type": "object" }, { "properties": { "type": { "enum": [ "rawHtml" ], "type": "string" } }, "required": [ "type" ], "title": "Raw HTML", "type": "object" }, { "properties": { "type": { "enum": [ "links" ], "type": "string" } }, "required": [ "type" ], "title": "Links", "type": "object" }, { "properties": { "type": { "enum": [ "images" ], "type": "string" } }, "required": [ "type" ], "title": "Images", "type": "object" }, { "properties": { "fullPage": { "default": false, "description": "是否捕获整个页面的截图（忽略 viewport.height），还是仅截取当前视口区域。", "type": "boolean" }, "quality": { "description": "截图质量，范围为 1 到 100，100 为最高质量。", "type": "integer" }, "type": { "enum": [ "screenshot" ], "type": "string" }, "viewport": { "properties": { "height": { "description": "视口高度（像素）", "type": "integer" }, "width": { "description": "视口宽度（像素）", "type": "integer" } }, "required": [ "width", "height" ], "type": "object" } }, "required": [ "type" ], "title": "Screenshot", "type": "object" }, { "properties": { "prompt": { "description": "用于生成 JSON 输出的提示", "type": "string" }, "schema": { "description": "用于 JSON 输出的 Schema，必须符合 [JSON Schema](https://json-schema.org/) 规范。", "type": "object" }, "type": { "enum": [ "json" ], "type": "string" } }, "required": [ "type" ], "title": "JSON", "type": "object" }, { "properties": { "modes": { "description": "用于变更跟踪的模式。`git-diff` 提供详细的差异对比，而 `json` 则对比提取出的 JSON 数据。", "items": { "enum": [ "git-diff", "json" ], "type": "string" }, "type": "array" }, "prompt": { "description": "在使用 `json` 模式进行变更跟踪时要使用的提示词。如果未提供，将使用默认提示词。", "type": "string" }, "schema": { "description": "在使用「json」模式进行 JSON 提取时所用的 schema。用于定义要提取和对比的数据结构。必须符合 [JSON Schema](https://json-schema.org/) 标准。", "type": "object" }, "tag": { "default": null, "description": "用于变更跟踪的标签。标签可以将变更跟踪历史划分为不同的「分支」，带有特定标签的变更跟踪只会与同一标签下的抓取结果进行比较。如果未提供，则会使用默认标签（null）。", "nullable": true, "type": "string" }, "type": { "enum": [ "changeTracking" ], "type": "string" } }, "required": [ "type" ], "title": "Change Tracking", "type": "object" }, { "properties": { "type": { "enum": [ "branding" ], "type": "string" } }, "required": [ "type" ], "title": "Branding", "type": "object" }, { "properties": { "type": { "enum": [ "product" ], "type": "string" } }, "required": [ "type" ], "title": "Product", "type": "object" }, { "properties": { "type": { "enum": [ "menu" ], "type": "string" } }, "required": [ "type" ], "title": "Menu", "type": "object" }, { "description": "从受支持的视频 URL（如 YouTube）中提取音频（MP3）。返回已签名的 GCS URL。", "properties": { "type": { "enum": [ "audio" ], "type": "string" } }, "required": [ "type" ], "title": "Audio", "type": "object" }, { "description": "从受支持的视频 URL（如 YouTube）中提取最高画质的视频。返回已签名的 GCS URL。", "properties": { "type": { "enum": [ "video" ], "type": "string" } }, "required": [ "type" ], "title": "Video", "type": "object" }, { "description": "针对页面提出自然语言问题。答案会在响应的 `answer` 字段中返回。", "properties": { "question": { "description": "要回答的页面相关问题。最大长度为 10,000 个字符。", "maxLength": 10000, "type": "string" }, "type": { "enum": [ "question" ], "type": "string" } }, "required": [ "type", "question" ], "title": "Question", "type": "object" }, { "description": "从页面中查找相关源文本。选中的文本会在响应的 `highlights` 字段中返回。", "properties": { "query": { "description": "要对页面执行的文本选择查询。最大长度为 10,000 个字符。", "maxLength": 10000, "type": "string" }, "type": { "enum": [ "highlights" ], "type": "string" } }, "required": [ "type", "query" ], "title": "Highlights", "type": "object" } ] }, "type": "array" }, "headers": { "description": "随请求发送的请求头。可用于传递 cookies、User-Agent 等信息。", "type": "object" }, "includeTags": { "description": "在输出中要包含的标签。", "items": { "type": "string" }, "type": "array" }, "location": { "description": "请求的地理位置设置。指定后，如果有可用的代理，将使用合适的代理，并模拟相应的语言和时区设置。如果未指定，则默认为“US”。", "properties": { "country": { "default": "US", "description": "ISO 3166-1 alpha-2 国家/地区代码（例如：“US”、“AU”、“DE”、“JP”）", "pattern": "^[A-Z]{2}$", "type": "string" }, "languages": { "description": "按优先级排序的请求首选语言和区域设置。默认为指定位置的语言。详情请参阅：https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Accept-Language", "items": { "example": "en-US", "type": "string" }, "type": "array" } }, "type": "object" }, "lockdown": { "default": false, "description": "如果为 true，则仅从 Firecrawl 的缓存中返回该请求的结果，绝不会向目标 URL 发出外部请求。此选项专为受合规要求限制或隔离网络环境而设计，因为爬取请求本身可能会泄露敏感信息。若缓存未命中，则返回 404 和错误代码 SCRAPE_LOCKDOWN_CACHE_MISS（未命中时绝不会记录该 URL）。Lockdown 请求按零数据保留处理。默认 maxAge 会延长至 2 年，因此现有缓存页面仍然仍可使用。命中缓存时计费 5 个额度，缓存未命中时计费 1 个额度。", "type": "boolean" }, "maxAge": { "default": 172800000, "description": "如果页面的缓存版本的生成时间距今少于该毫秒数，则返回该缓存页面；如果缓存版本距今超过该时间，则会重新抓取页面。若你不需要特别新的数据，启用此选项可将抓取速度提升至 5 倍。默认值为 2 天。", "type": "integer" }, "minAge": { "description": "<[\n {\n \"key\": \"0\",\n \"translation\": \"设置后，请求将仅检查缓存，不会触发新的抓取。该值以毫秒为单位，指定缓存数据必须满足的最小存在时长。如果存在匹配的缓存数据，将立即返回。若未找到缓存数据，则返回 404，错误代码为 SCRAPE_NO_CACHED_DATA。将其设为 1 可接受任意缓存数据，不受时长限制。\"\n }\n]", "type": "integer" }, "mobile": { "default": false, "description": "若要模拟在移动设备上进行抓取，请将其设置为 true。适用于测试响应式页面并获取移动端截图。", "type": "boolean" }, "onlyCleanContent": { "default": false, "description": "测试版。在已生成的 markdown 上额外执行一轮基于 LLM 的处理，以移除 `onlyMainContent` 可能遗漏的残余样板内容（如 cookie 横幅、广告块、社交分享组件、面包屑导航、新闻简报订阅区、评论区、相关文章列表）。标题、列表、表格、代码块、图片引用和内联链接都会保留。可与 `onlyMainContent` 结合使用（最常见的配置），也可单独使用。当 markdown 超过清理模型的输出 token 限制时，将跳过此步骤并发出警告（原始 markdown 会保留）。不支持零数据保留请求。", "type": "boolean" }, "onlyMainContent": { "default": true, "description": "仅返回页面主体内容，不包括页眉、导航栏、页脚等。这是在生成 markdown 之前应用的确定性 HTML 层级过滤；不涉及 LLM。", "type": "boolean" }, "parsers": { "default": [ "pdf" ], "description": "用于控制在抓取过程中如何处理文件。包含 \"pdf\" 时（默认），会提取 PDF 内容并转换为 Markdown 格式，计费基于页数（每页 1 点数）。当传入空数组时，会以 base64 编码返回整个 PDF 文件，并对整份 PDF 按单一费率收取 1 点数。", "items": { "oneOf": [ { "additionalProperties": false, "properties": { "maxPages": { "description": "从该 PDF 中最多解析的页数。必须为不超过 10000 的正整数。", "maximum": 10000, "minimum": 1, "type": "integer" }, "mode": { "default": "auto", "description": "PDF 解析模式。\"fast\"：仅执行基于文本的提取（提取内嵌文本，速度最快）。\"auto\"（默认）：优先尝试 fast 提取，如有需要再回退到 OCR。\"ocr\"：对每一页强制执行 OCR 识别。", "enum": [ "fast", "auto", "ocr" ], "type": "string" }, "type": { "enum": [ "pdf" ], "type": "string" } }, "required": [ "type" ], "type": "object" } ] }, "type": "array" }, "profile": { "description": "在抓取和交互会话之间启用持久化浏览器存储。抓取时传入一个 profile，以保留 cookies、localStorage 和会话数据。使用相同 profile 名称的会话会共享浏览器状态。", "properties": { "name": { "description": "配置文件的名称。使用相同名称的抓取任务会共享浏览器状态（cookies、localStorage、会话）。", "maxLength": 128, "minLength": 1, "type": "string" }, "saveChanges": { "default": true, "description": "为 true 时，交互会话停止后，浏览器状态会保存回该 profile。设为 false 则只加载现有数据而不写入。同一时间只允许一个会话执行保存。", "type": "boolean" } }, "required": [ "name" ], "type": "object" }, "proxy": { "default": "auto", "description": "指定要使用的代理类型。\n\n - **basic**：用于抓取几乎没有或只有基础反爬策略的网站的代理。速度快，通常可用。\n - **enhanced**：用于抓取具有高级反爬策略的网站的增强型代理。速度较慢，但在某些站点上更可靠。每个请求最多消耗 5 点积分。\n - **auto**：当 basic 代理抓取失败时，Firecrawl 会自动重试并切换为 enhanced 代理。如果使用 enhanced 重试成功，该次抓取将收取 5 点积分；如果使用 basic 一次就成功，则只按常规定价计费。", "enum": [ "basic", "enhanced", "auto" ], "type": "string" }, "redactPII": { "default": false, "description": "对返回的 markdown 中的个人身份识别信息进行脱敏。传入 `true` 可使用默认值，或传入一个对象来自定义模式、实体和替换样式。", "oneOf": [ { "type": "boolean" }, { "additionalProperties": false, "description": "PII 脱敏的配置选项。", "properties": { "entities": { "description": "将脱敏限制为这些实体类别。如果省略，则会对所有支持的实体进行脱敏。", "items": { "description": "Firecrawl 脱敏支持的公开 PII 实体类别。", "enum": [ "PERSON", "EMAIL", "PHONE", "LOCATION", "FINANCIAL", "SECRET" ], "type": "string" }, "type": "array" }, "mode": { "default": "accurate", "description": "脱敏策略。`accurate` 仅使用模型，针对准确性进行了优化；`aggressive` 通过额外的启发式规则提高召回率；`fast` 则仅使用启发式规则，不调用模型。", "enum": [ "accurate", "aggressive", "fast" ], "type": "string" }, "replaceStyle": { "default": "tag", "description": "`tag` 会将文本片段替换为 `` 这类占位符，`mask` 会用 `*` 替换字符，`remove` 会删除该文本片段。", "enum": [ "tag", "mask", "remove" ], "type": "string" } }, "type": "object" } ] }, "removeBase64Images": { "default": true, "description": "从 markdown 输出中移除所有 base 64 图像，以避免输出内容过长。这不会影响 html 或 rawHtml formats。图像的 alt 文本会保留在输出中，但 URL 会替换为占位符。", "type": "boolean" }, "skipTlsVerification": { "default": true, "description": "在发起请求时跳过 TLS 证书验证。", "type": "boolean" }, "storeInCache": { "default": true, "description": "如果为 true，该页面会存储到 Firecrawl 的索引和缓存中。如果你的抓取操作可能涉及数据保护方面的顾虑，将其设置为 false 会很有用。使用某些与敏感抓取相关的参数（例如 actions、headers）时，会被强制将此参数设为 false。", "type": "boolean" }, "threatProtection": { "description": "此请求的[威胁防护](https://docs.firecrawl.dev/features/threat-protection)按请求覆盖配置。你提供的字段仅会替换此次请求中你所在组织策略的对应字段；未提供的字段则保留组织级配置值。你的团队必须已启用威胁防护（企业版功能），否则该请求会因 403 被拒绝。如果你的组织已禁用请求级覆盖，任何包含此对象的请求都会因 403 被拒绝。如果你的团队强制启用了威胁防护，则不得将 `mode` 设为 `off`。", "properties": { "blacklist": { "description": "始终封禁的域名，可使用普通域名（`example.com`）或通配符模式（`*.example.com`）。不包含协议、路径或端口。", "items": { "type": "string" }, "maxItems": 1000, "type": "array" }, "blockedTlds": { "description": "直接封禁的顶级域名，使用不带前导点的小写形式（例如 `zip`）。", "items": { "type": "string" }, "maxItems": 1000, "type": "array" }, "failurePolicy": { "description": "当无法访问 classifier 时的处理方式：`closed` 会封禁该请求，`open` 则允许该请求。", "enum": [ "open", "closed" ], "type": "string" }, "mode": { "description": "此次请求的 URL 扫描模式。`normal` 使用 Google Web Risk 检查 URL（每扫描 1 个 URL 额外消耗 2 个额度）。", "enum": [ "off", "normal" ], "type": "string" }, "riskScoreThreshold": { "description": "归一化风险评分（0–100）阈值。达到或超过该值时，分类器判定会封禁该 URL。值越低，限制越严格。", "example": 75, "maximum": 100, "minimum": 0, "type": "integer" }, "whitelist": { "description": "始终允许的域名，可使用普通域名或通配符模式。优先级高于其他所有规则。", "items": { "type": "string" }, "maxItems": 1000, "type": "array" } }, "title": "Threat Protection Override", "type": "object" }, "timeout": { "default": 60000, "description": "请求超时时间（以毫秒为单位）。最小值为 1000（1 秒）。默认值为 60000（60 秒）。最大值为 300000（300 秒）。", "maximum": 300000, "minimum": 1000, "type": "integer" }, "waitFor": { "default": 0, "description": "指定在抓取内容前的延迟时间（毫秒），以便页面有足够时间完成加载。该等待时间是在 Firecrawl 的智能等待功能基础上的额外等待。", "type": "integer" } }, "type": "object" }, "sitemap": { "default": "include", "description": "爬取时的 Sitemap 处理模式。若设置为“skip”，爬虫会忽略站点的 Sitemap，只爬取你提供的起始 URL，并从该页面开始按发现的链接继续爬取。若设置为“only”，爬虫只会根据 Sitemap 中的 URL（加上起始 URL）进行爬取，不会再从页面 HTML 中继续发现并跟进新的链接。", "enum": [ "skip", "include", "only" ], "type": "string" }, "url": { "description": "用于开始爬取的基础 URL", "format": "uri", "type": "string" }, "webhook": { "description": "一个 Webhook 规范对象。", "properties": { "events": { "description": "应发送到 webhook URL 的事件类型。（默认：全部）", "items": { "enum": [ "completed", "page", "failed", "started" ], "type": "string" }, "type": "array" }, "headers": { "additionalProperties": { "type": "string" }, "description": "发送到 webhook URL 的请求头。", "type": "object" }, "metadata": { "additionalProperties": true, "description": "将包含在本次抓取所有 webhook 负载中的自定义元数据", "type": "object" }, "url": { "description": "用于接收 webhook 的 URL。该 webhook 会在以下事件触发：爬取开始时（crawl.started）、每当有页面被爬取时（crawl.page）、以及爬取结束时（crawl.completed 或 crawl.failed）。其响应将与 `/scrape` 端点相同。", "type": "string" } }, "required": [ "url" ], "type": "object" }, "zeroDataRetention": { "default": false, "description": "如果设置为 true，将为本次抓取任务启用零数据保留。要启用此功能，请联系 help@firecrawl.dev", "type": "boolean" } }, "required": [ "url" ], "type": "object" } } }, "required": true }, "responses": { "200": { "content": { "application/json": { "schema": { "properties": { "id": { "type": "string" }, "success": { "type": "boolean" }, "url": { "format": "uri", "type": "string" } }, "type": "object" } } }, "description": "成功的响应" }, "402": { "content": { "application/json": { "schema": { "properties": { "error": { "example": "Payment required to access this resource.", "type": "string" } }, "type": "object" } } }, "description": "需要支付" }, "429": { "content": { "application/json": { "schema": { "properties": { "error": { "example": "Request rate limit exceeded. Please wait and try again later.", "type": "string" } }, "type": "object" } } }, "description": "请求次数过多" }, "500": { "content": { "application/json": { "schema": { "properties": { "error": { "example": "An unexpected error occurred on the server.", "type": "string" } }, "type": "object" } } }, "description": "服务器错误" } } } ```