Skip to content

Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. πŸ”₯

docs(readme): replace Browse with Interact section

firecrawl-spring[bot]24eadc934bbb
diff --git a/README.md b/README.md
index 099077643..f38a70474 100644
--- a/README.md
+++ b/README.md
@@ -137,7 +137,7 @@ See the full [Skill + CLI documentation](https://docs.firecrawl.dev/sdks/cli) fo
|---------|-------------|
| [**Scrape**](#scraping) | Convert any URL to markdown, HTML, screenshots, or structured JSON |
| [**Search**](#search) | Search the web and get full page content from results |
-| [**Browse**](#browse) | Let agents safely interact with the web |
+| [**Interact**](#interact) | Scrape a page, then interact with it via prompts or code |
| [**Map**](#map) | Discover all URLs on a website instantly |
| [**Crawl**](#crawling) | Scrape all URLs of a website with a single request |
| [**Agent**](#agent) | Automated data gathering, just describe what you need |
@@ -293,62 +293,76 @@ results = firecrawl.search(
---
-## Browse
+## Interact
-Give your agents a secure browser environment. Let them run code safely to gather data and take action on the web.
-```bash
-curl -X POST 'https://api.firecrawl.dev/v2/browser' \
- -H 'Authorization: Bearer fc-YOUR_API_KEY' \
- -H 'Content-Type: application/json'
-```
+Scrape a page, then interact with it β€” click buttons, fill forms, extract dynamic content, or navigate deeper. Use natural language prompts or run code for full control. [Learn more β†’](https://docs.firecrawl.dev/features/interact)
-Response:
-```json
-{
- "success": true,
- "id": "550e8400-e29b-41d4-a716-446655440000",
- "cdpUrl": "wss://cdp-proxy.firecrawl.dev/cdp/550e8400-e29b-41d4-a716-446655440000",
- "liveViewUrl": "https://liveview.firecrawl.dev/550e8400-e29b-41d4-a716-446655440000"
-}
+```python
+from firecrawl import Firecrawl
+
+app = Firecrawl(api_key="fc-YOUR_API_KEY")
+
+# 1. Scrape a page
+result = app.scrape("https://www.amazon.com", formats=["markdown"])
+scrape_id = result.metadata["scrapeId"]
+
+# 2. Interact with it using natural language
+app.interact(scrape_id, prompt="Search for iPhone 16 Pro Max")
+response = app.interact(scrape_id, prompt="Click on the first result and tell me the price")
+print(response.output) # "The iPhone 16 Pro Max (256GB) is priced at $1,199.00."
+
+# 3. Stop the session
+app.stop_interaction(scrape_id)
```
-### Execute Code in the Browser
+### Run Code in the Browser
-Run Playwright code, Python, or bash commands remotely:
+For full control, execute Playwright code directly β€” `page` is already connected:
```javascript
import Firecrawl from '@mendable/firecrawl-js';
const firecrawl = new Firecrawl({ apiKey: "fc-YOUR_API_KEY" });
-// 1. Launch a session
-const session = await firecrawl.browser();
+// 1. Scrape a page
+const scrapeResult = await firecrawl.scrape("https://news.ycombinator.com", { formats: ["markdown"] });
+const scrapeId = scrapeResult.metadata.scrapeId;
-// 2. Execute code
-const result = await firecrawl.browserExecute(session.id, {
+// 2. Execute Playwright code
+const result = await firecrawl.interact(scrapeId, {
code: `
- await page.goto("https://news.ycombinator.com");
+ await page.click('#next-page');
+ await page.waitForLoadState('networkidle');
const title = await page.title();
- console.log(title);
+ JSON.stringify({ title });
`,
language: "node",
});
-console.log(result.result); // "Hacker News"
+console.log(result.result);
-// 3. Close
-await firecrawl.deleteBrowser(session.id);
+// 3. Stop
+await firecrawl.stopInteraction(scrapeId);
```
-### Persistent Sessions
+### Persistent Profiles
Save and reuse browser state (cookies, localStorage) across sessions:
-```javascript
-const session = await firecrawl.browser({
- ttl: 600,
- profile: {
- name: "my-profile",
- saveChanges: true,
- },
-});
+```python
+result = app.scrape(
+ "https://app.example.com/login",
+ formats=["markdown"],
+ profile={"name": "my-app", "save_changes": True},
+)
+scrape_id = result.metadata["scrapeId"]
+
+app.interact(scrape_id, prompt="Fill in [email protected] and password, then click Login")
+app.stop_interaction(scrape_id)
+
+# Next session β€” already logged in
+result = app.scrape(
+ "https://app.example.com/dashboard",
+ formats=["markdown"],
+ profile={"name": "my-app", "save_changes": True},
+)
```
### agent-browser (Bash Mode)