firecrawl-browser by firecrawl/cli
npx skills add https://github.com/firecrawl/cli --skill firecrawl-browser
browser命令已弃用。 请改用scrape+interact。interact允许您先抓取页面,然后点击、填写表单和导航,而无需手动管理会话。
在实时浏览器会话中与已抓取的页面进行交互。先抓取一个页面,然后使用自然语言提示或代码来点击、填写表单、导航和提取数据。
scrape 失败,因为内容隐藏在 JavaScript 交互之后search广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
# 1. 抓取一个页面(抓取 ID 会自动保存)
firecrawl scrape "<url>"
# 2. 使用自然语言与页面交互
firecrawl interact --prompt "点击登录按钮"
firecrawl interact --prompt "在邮箱字段填写 test@example.com"
firecrawl interact --prompt "提取价格表"
# 3. 或者使用代码进行精确控制
firecrawl interact --code "agent-browser click @e5" --language bash
firecrawl interact --code "agent-browser snapshot -i" --language bash
# 4. 完成后停止会话
firecrawl interact stop
| 选项 | 描述 |
|---|---|
--prompt <文本> | 自然语言指令(使用此选项或 --code) |
--code <代码> | 在浏览器会话中执行的代码 |
--language <语言> | 代码语言:bash、python、node |
--timeout <秒数> | 执行超时时间(默认:30,最大:300) |
--scrape-id <id> | 指定特定的抓取目标(默认:最后一次抓取) |
-o, --output <路径> | 输出文件路径 |
在抓取时使用 --profile 以在多次抓取之间保持浏览器状态(cookies、localStorage):
# 会话 1:登录并保存状态
firecrawl scrape "https://app.example.com/login" --profile my-app
firecrawl interact --prompt "填写邮箱 user@example.com 并点击登录"
# 会话 2:返回时已认证
firecrawl scrape "https://app.example.com/dashboard" --profile my-app
firecrawl interact --prompt "提取仪表板数据"
只读重新连接(不写入配置文件状态):
firecrawl scrape "https://app.example.com" --profile my-app --no-save-changes
interact 需要来自先前 firecrawl scrape 调用的抓取 ID--scrape-idfirecrawl interact stop 来释放资源--scrape-id 与每个页面交互每周安装量
6.1K
代码仓库
GitHub 星标数
205
首次出现
14 天前
安全审计
安装于
codex6.0K
opencode6.0K
gemini-cli6.0K
github-copilot6.0K
cursor6.0K
amp6.0K
The
browsercommand is deprecated. Usescrape+interactinstead. Interact lets you scrape a page and then click, fill forms, and navigate without managing sessions manually.
Interact with scraped pages in a live browser session. Scrape a page first, then use natural language prompts or code to click, fill forms, navigate, and extract data.
scrape failed because content is behind JavaScript interactionsearch instead# 1. Scrape a page (scrape ID is saved automatically)
firecrawl scrape "<url>"
# 2. Interact with the page using natural language
firecrawl interact --prompt "Click the login button"
firecrawl interact --prompt "Fill in the email field with test@example.com"
firecrawl interact --prompt "Extract the pricing table"
# 3. Or use code for precise control
firecrawl interact --code "agent-browser click @e5" --language bash
firecrawl interact --code "agent-browser snapshot -i" --language bash
# 4. Stop the session when done
firecrawl interact stop
| Option | Description |
|---|---|
--prompt <text> | Natural language instruction (use this OR --code) |
--code <code> | Code to execute in the browser session |
--language <lang> | Language for code: bash, python, node |
--timeout <seconds> | Execution timeout (default: 30, max: 300) |
--scrape-id <id> | Target a specific scrape (default: last scrape) |
-o, --output <path> |
Use --profile on the scrape to persist browser state (cookies, localStorage) across scrapes:
# Session 1: Login and save state
firecrawl scrape "https://app.example.com/login" --profile my-app
firecrawl interact --prompt "Fill in email with user@example.com and click login"
# Session 2: Come back authenticated
firecrawl scrape "https://app.example.com/dashboard" --profile my-app
firecrawl interact --prompt "Extract the dashboard data"
Read-only reconnect (no writes to profile state):
firecrawl scrape "https://app.example.com" --profile my-app --no-save-changes
interact requires a scrape ID from a previous firecrawl scrape call--scrape-id for subsequent interact callsfirecrawl interact stop to free resources when done--scrape-idWeekly Installs
6.1K
Repository
GitHub Stars
205
First Seen
14 days ago
Security Audits
Gen Agent Trust HubPassSocketPassSnykFail
Installed on
codex6.0K
opencode6.0K
gemini-cli6.0K
github-copilot6.0K
cursor6.0K
amp6.0K
97,600 周安装
| Output file path |