File size: 8,285 Bytes
097eaf0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
# Firecrawl Python SDK

The Firecrawl Python SDK is a library that lets you easily search, scrape, and interact with the web for AI agents — returning clean Markdown or structured data your agents can ship with. It provides a simple and intuitive interface for the Firecrawl API.

## Installation

To install the Firecrawl Python SDK, you can use pip:

```bash 
pip install firecrawl-py
```

## Usage

1. Get an API key from [firecrawl.dev](https://firecrawl.dev)
2. Set the API key as an environment variable named `FIRECRAWL_API_KEY` or pass it as a parameter to the `Firecrawl` class.

Here's an example of how to use the SDK:

```python 
from firecrawl import Firecrawl
from firecrawl.types import ScrapeOptions

firecrawl = Firecrawl(api_key="fc-YOUR_API_KEY")

# Scrape a website (v2):
data = firecrawl.scrape(
  'https://firecrawl.dev', 
  formats=['markdown', 'html']
)
print(data)

# Crawl a website (v2 waiter):
crawl_status = firecrawl.crawl(
  'https://firecrawl.dev', 
  limit=100, 
  scrape_options=ScrapeOptions(formats=['markdown', 'html'])
)
print(crawl_status)
```

### Scraping a URL

To scrape a single URL, use the `scrape` method. It takes the URL as a parameter and returns a document with the requested formats.

```python 
# Scrape a website (v2):
scrape_result = firecrawl.scrape('https://firecrawl.dev', formats=['markdown', 'html'])
print(scrape_result)
```

### Video extraction

Use the `video` format on supported video URLs, including YouTube and TikTok. The returned `video` field is a signed URL to the extracted video file.

```python
doc = firecrawl.scrape('https://www.youtube.com/watch?v=dQw4w9WgXcQ', formats=['video'])
print(doc.video)
```

### Parsing uploaded files

Use `parse` to upload local bytes/files (`html`, `pdf`, `docx`, etc.) as multipart form data and return the parsed document.
`parse` does not support change tracking or browser-only options (actions, wait_for, location, mobile, screenshot, branding, audio, video).

```python
from firecrawl import Firecrawl
from firecrawl.v2.types import ParseOptions

firecrawl = Firecrawl(api_key="fc-YOUR_API_KEY")

doc = firecrawl.parse(
  b"<!DOCTYPE html><html><body><h1>Python Parse</h1></body></html>",
  filename="upload.html",
  content_type="text/html",
  options=ParseOptions(formats=["markdown"]),
)

print(doc.markdown)
```

### Crawling a Website

To crawl a website, use the `crawl` method. It takes the starting URL and optional parameters as arguments. You can control depth, limits, formats, and more.

```python 
crawl_status = firecrawl.crawl(
  'https://firecrawl.dev', 
  limit=100, 
  scrape_options=ScrapeOptions(formats=['markdown', 'html']),
  poll_interval=30
)
print(crawl_status)
```

### Asynchronous Crawling

<Tip>Looking for async operations? Check out the [Async Class](#async-class) section below.</Tip>

To enqueue a crawl asynchronously, use `start_crawl`. It returns the crawl `ID` which you can use to check the status of the crawl job.

```python 
crawl_job = firecrawl.start_crawl(
  'https://firecrawl.dev', 
  limit=100, 
  scrape_options=ScrapeOptions(formats=['markdown', 'html']),
)
print(crawl_job)
```

### Checking Crawl Status

To check the status of a crawl job, use the `get_crawl_status` method. It takes the job ID as a parameter and returns the current status of the crawl job.

```python 
crawl_status = firecrawl.get_crawl_status("<crawl_id>")
print(crawl_status)
```

### Manual Pagination (v2)

Crawl and batch scrape status responses may include a `next` URL when more data is available. The SDK auto-paginates by default; to page manually, disable auto-pagination and pass the opaque `next` URL back to the SDK.

```python
from firecrawl.v2.types import PaginationConfig

# Crawl: fetch one page at a time
crawl_job = firecrawl.start_crawl("https://firecrawl.dev", limit=100)
status = firecrawl.get_crawl_status(
  crawl_job.id,
  pagination_config=PaginationConfig(auto_paginate=False),
)
if status.next:
  page2 = firecrawl.get_crawl_status_page(status.next)

# Batch scrape: fetch one page at a time
batch_job = firecrawl.start_batch_scrape(["https://firecrawl.dev"])
status = firecrawl.get_batch_scrape_status(
  batch_job.id,
  pagination_config=PaginationConfig(auto_paginate=False),
)
if status.next:
  page2 = firecrawl.get_batch_scrape_status_page(status.next)
```

### Cancelling a Crawl

To cancel an asynchronous crawl job, use the `cancel_crawl` method. It takes the job ID of the asynchronous crawl as a parameter and returns the cancellation status.

```python 
cancel_crawl = firecrawl.cancel_crawl(id)
print(cancel_crawl)
```

### Map a Website

Use `map` to generate a list of URLs from a website. Options let you customize the mapping process, including whether to use the sitemap or include subdomains.

```python 
# Map a website (v2):
map_result = firecrawl.map('https://firecrawl.dev')
print(map_result)
```

### Scrape-bound interactive browsing (v2)

Use a scrape job ID to keep interacting with the replayed browser context:

```python
doc = firecrawl.scrape(
  "https://example.com",
  actions=[{"type": "click", "selector": "a[href='/pricing']"}],
)

scrape_job_id = doc.metadata_typed.scrape_id
if not scrape_job_id:
  raise RuntimeError("Missing scrape job id")

run = firecrawl.interact(
  scrape_job_id,
  code="print(await page.url())",
  language="python",
  timeout=60,
)
print(run.stdout)

firecrawl.stop_interaction(scrape_job_id)
```

{/* ### Extracting Structured Data from Websites

  To extract structured data from websites, use the `extract` method. It takes the URLs to extract data from, a prompt, and a schema as arguments. The schema is a Pydantic model that defines the structure of the extracted data.

  <ExtractPythonShort /> */}

### Crawling a Website with WebSockets

To crawl a website with WebSockets, use the `crawl_url_and_watch` method. It takes the starting URL and optional parameters as arguments. The `params` argument allows you to specify additional options for the crawl job, such as the maximum number of pages to crawl, allowed domains, and the output format.

```python 
# inside an async function...
nest_asyncio.apply()

# Define event handlers
def on_document(detail):
    print("DOC", detail)

def on_error(detail):
    print("ERR", detail['error'])

def on_done(detail):
    print("DONE", detail['status'])

    # Function to start the crawl and watch process
async def start_crawl_and_watch():
    # Initiate the crawl job and get the watcher
    watcher = app.crawl_url_and_watch('firecrawl.dev', exclude_paths=['blog/*'], limit=5)

    # Add event listeners
    watcher.add_event_listener("document", on_document)
    watcher.add_event_listener("error", on_error)
    watcher.add_event_listener("done", on_done)

    # Start the watcher
    await watcher.connect()

# Run the event loop
await start_crawl_and_watch()
```

## Error Handling

The SDK handles errors returned by the Firecrawl API and raises appropriate exceptions. If an error occurs during a request, an exception will be raised with a descriptive error message.

## Async Class

For async operations, you can use the `AsyncFirecrawl` class. Its methods mirror the `Firecrawl` class, but you `await` them.

```python 
from firecrawl import AsyncFirecrawl

firecrawl = AsyncFirecrawl(api_key="YOUR_API_KEY")

# Async Scrape (v2)
async def example_scrape():
  scrape_result = await firecrawl.scrape(url="https://example.com")
  print(scrape_result)

# Async Parse (v2)
async def example_parse():
  parse_result = await firecrawl.parse(
    b"<!DOCTYPE html><html><body><h1>Async Parse</h1></body></html>",
    filename="upload.html",
    content_type="text/html",
  )
  print(parse_result)

# Async Crawl (v2)
async def example_crawl():
  crawl_result = await firecrawl.crawl(url="https://example.com")
  print(crawl_result)
```

## v1 compatibility

For legacy code paths, v1 remains available under `firecrawl.v1` with the original method names.

```python
from firecrawl import Firecrawl

firecrawl = Firecrawl(api_key="YOUR_API_KEY")

# v1 methods (feature‑frozen)
doc_v1 = firecrawl.v1.scrape_url('https://firecrawl.dev', formats=['markdown', 'html'])
crawl_v1 = firecrawl.v1.crawl_url('https://firecrawl.dev', limit=100)
map_v1 = firecrawl.v1.map_url('https://firecrawl.dev')
```