Back to Details

firecrawl-browser

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

firecrawl browser

firecrawl browser

Cloud Chromium sessions in Firecrawl's remote sandboxed environment. Interact with pages that require clicks, form fills, pagination, or login.
Firecrawl远程沙箱环境中的云Chromium会话。可与需要点击、表单填写、分页或登录的页面进行交互。

When to use

使用场景

  • Content requires interaction: clicks, form fills, pagination, login
  • scrape
    failed because content is behind JavaScript interaction
  • You need to navigate a multi-step flow
  • Last resort in the workflow escalation pattern: search → scrape → map → crawl → browser
  • Never use browser for web searches — use 
    search
    instead
  • 内容需要交互：点击、表单填写、分页、登录
  • 因内容需通过JavaScript交互加载，导致
    scrape
    失败
  • 需要导航多步骤流程
  • 工作流升级模式中的最后手段：搜索 → 抓取 → 映射 → 爬取 → browser
  • 切勿使用browser进行网页搜索——请改用
    search

Quick start

快速开始

bash
undefined
bash
undefined

Typical browser workflow

典型browser工作流

firecrawl browser "open <url>" firecrawl browser "snapshot -i" # see interactive elements with @ref IDs firecrawl browser "click @e5" # interact with elements firecrawl browser "fill @e3 'search query'" # fill form fields firecrawl browser "scrape" -o .firecrawl/page.md # extract content firecrawl browser close

Shorthand auto-launches a session if none exists — no setup required.
firecrawl browser "open <url>" firecrawl browser "snapshot -i" # 查看带@ref ID的交互元素 firecrawl browser "click @e5" # 与元素交互 firecrawl browser "fill @e3 'search query'" # 填写表单字段 firecrawl browser "scrape" -o .firecrawl/page.md # 提取内容 firecrawl browser close

简写模式会自动启动会话（若不存在）——无需设置。

Commands

命令

CommandDescription
open <url>
Navigate to a URL
snapshot -i
Get interactive elements with 
@ref
IDs
screenshot
Capture a PNG screenshot
click <@ref>
Click an element by ref
type <@ref> <text>
Type into an element
fill <@ref> <text>
Fill a form field (clears first)
scrape
Extract page content as markdown
scroll <direction>
Scroll up/down/left/right
wait <seconds>
Wait for a duration
eval <js>
Evaluate JavaScript on the page
Session management: 
launch-session --ttl 600
, 
list
, 
close
命令描述
open <url>
导航至指定URL
snapshot -i
获取带
@ref
ID的交互元素
screenshot
捕获PNG格式截图
click <@ref>
通过ref点击元素
type <@ref> <text>
在元素中输入文本
fill <@ref> <text>
填写表单字段（先清空原有内容）
scrape
以markdown格式提取页面内容
scroll <direction>
向上/向下/向左/向右滚动
wait <seconds>
等待指定时长
eval <js>
在页面上执行JavaScript代码
会话管理：
launch-session --ttl 600
, 
list
, 
close

Options

选项

OptionDescription
--ttl <seconds>
Session time-to-live
--ttl-inactivity <seconds>
Inactivity timeout
--session <id>
Use a specific session ID
--profile <name>
Use a named profile (persists state)
--no-save-changes
Read-only reconnect (don't write to session state)
-o, --output <path>
Output file path
选项描述
--ttl <seconds>
会话存活时间（TTL）
--ttl-inactivity <seconds>
无活动超时时间
--session <id>
使用指定的会话ID
--profile <name>
使用命名配置文件（持久化状态）
--no-save-changes
只读重连（不写入会话状态）
-o, --output <path>
输出文件路径

Profiles

配置文件

Profiles survive close and can be reconnected by name. Use them for login-then-work flows:
bash
undefined
配置文件在会话关闭后仍会保留，可通过名称重新连接。适用于“登录后操作”的流程：
bash
undefined

Session 1: Login and save state

会话1：登录并保存状态

firecrawl browser launch-session --profile my-app firecrawl browser "open https://app.example.com/login" firecrawl browser "snapshot -i" firecrawl browser "fill @e3 'user@example.com'" firecrawl browser "click @e7" firecrawl browser "wait 2" firecrawl browser close
firecrawl browser launch-session --profile my-app firecrawl browser "open https://app.example.com/login" firecrawl browser "snapshot -i" firecrawl browser "fill @e3 'user@example.com'" firecrawl browser "click @e7" firecrawl browser "wait 2" firecrawl browser close

Session 2: Come back authenticated

会话2：已认证状态下返回

firecrawl browser launch-session --profile my-app firecrawl browser "open https://app.example.com/dashboard" firecrawl browser "scrape" -o .firecrawl/dashboard.md firecrawl browser close

Read-only reconnect (no writes to session state):

```bash
firecrawl browser launch-session --profile my-app --no-save-changes
Shorthand with profile:
bash
firecrawl browser --profile my-app "open https://example.com"
firecrawl browser launch-session --profile my-app firecrawl browser "open https://app.example.com/dashboard" firecrawl browser "scrape" -o .firecrawl/dashboard.md firecrawl browser close

只读重连（不写入会话状态）：

```bash
firecrawl browser launch-session --profile my-app --no-save-changes
带配置文件的简写模式：
bash
firecrawl browser --profile my-app "open https://example.com"

Tips

提示

  • If you get forbidden errors, the session may have expired — create a new one.
  • For parallel browser work, launch separate sessions and operate them via 
    --session <id>
    .
  • Always 
    close
    sessions when done to free resources.
  • 若收到禁止访问错误，可能是会话已过期——请创建新会话。
  • 如需并行browser操作，请启动独立会话并通过
    --session <id>
    进行管理。
  • 使用完成后务必
    close
    会话以释放资源。

See also

另请参阅

  • firecrawl-scrape — try scrape first, escalate to browser only when needed
  • firecrawl-search — for web searches (never use browser for searching)
  • firecrawl-agent — AI-powered extraction (less manual control)
  • firecrawl-scrape — 优先尝试scrape，仅在必要时升级为browser
  • firecrawl-search — 用于网页搜索（切勿使用browser进行搜索）
  • firecrawl-agent — 基于AI的提取工具（手动控制较少）