AI/firecrawl
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/mendableai/firecrawl synced 2025-08-12 06:49:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

Nick: python sdk 2.0

Browse Source
This commit is contained in:
Nicolas 2025-04-18 01:15:14 -07:00
parent f3522666db
commit a3f3168212
2 changed files with 20 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
apps/python-sdk/example_async.py
View File

@ -6,51 +6,47 @@ from firecrawl.firecrawl import AsyncFirecrawlApp
from pydantic import BaseModel, Field
from typing import List
app = AsyncFirecrawlApp(api_key="fc-")
app = AsyncFirecrawlApp(api_url="https://api.firecrawl.dev")
async def example_scrape():
# Scrape a website:
scrape_result = await app.scrape_url('firecrawl.dev')
print(scrape_result['markdown'])
scrape_result = await app.scrape_url('example.com', formats=["markdown", "html"])
print(scrape_result.markdown)
async def example_batch_scrape():
# Batch scrape
urls = ['https://example.com', 'https://docs.firecrawl.dev']
batch_scrape_params = {
'formats': ['markdown', 'html'],
}
# Synchronous batch scrape
batch_result = await app.batch_scrape_urls(urls, batch_scrape_params)
batch_result = await app.batch_scrape_urls(urls, formats=["markdown", "html"])
print("Synchronous Batch Scrape Result:")
print(batch_result['data'][0]['markdown'])
print(batch_result.data[0].markdown)
# Asynchronous batch scrape
async_batch_result = await app.async_batch_scrape_urls(urls, batch_scrape_params)
async_batch_result = await app.async_batch_scrape_urls(urls, formats=["markdown", "html"])
print("\nAsynchronous Batch Scrape Result:")
print(async_batch_result)
async def example_crawl():
# Crawl a website:
idempotency_key = str(uuid.uuid4()) # optional idempotency key
crawl_result = await app.crawl_url('firecrawl.dev', {'excludePaths': ['blog/*']}, 2, idempotency_key)
print(crawl_result)
crawl_result = await app.crawl_url('firecrawl.dev', exclude_paths=['blog/*'])
print(crawl_result.data[0].markdown)
# Asynchronous Crawl a website:
async_result = await app.async_crawl_url('firecrawl.dev', {'excludePaths': ['blog/*']}, "")
async_result = await app.async_crawl_url('firecrawl.dev', exclude_paths=['blog/*'])
print(async_result)
crawl_status = await app.check_crawl_status(async_result['id'])
crawl_status = await app.check_crawl_status(async_result.id)
print(crawl_status)
attempts = 15
while attempts > 0 and crawl_status['status'] != 'completed':
while attempts > 0 and crawl_status.status != 'completed':
print(crawl_status)
crawl_status = await app.check_crawl_status(async_result['id'])
crawl_status = await app.check_crawl_status(async_result.id)
attempts -= 1
await asyncio.sleep(1) # Use async sleep instead of time.sleep
crawl_status = await app.check_crawl_status(async_result['id'])
crawl_status = await app.check_crawl_status(async_result.id)
print(crawl_status)
async def example_llm_extraction():
@ -64,18 +60,15 @@ async def example_llm_extraction():
class TopArticlesSchema(BaseModel):
top: List[ArticleSchema] = Field(..., description="Top 5 stories")
llm_extraction_result = await app.scrape_url('https://news.ycombinator.com', {
'formats': ['extract'],
'extract': {
'schema': TopArticlesSchema.model_json_schema()
}
})
extract_config = ExtractConfig(schema=TopArticlesSchema.model_json_schema())
print(llm_extraction_result['extract'])
llm_extraction_result = await app.scrape_url('https://news.ycombinator.com', formats=["extract"], extract=extract_config)
print(llm_extraction_result.extract)
async def example_map_and_extract():
# Map a website:
map_result = await app.map_url('https://firecrawl.dev', { 'search': 'blog' })
map_result = await app.map_url('https://firecrawl.dev', search="blog")
print(map_result)
# Extract URLs:
@ -88,10 +81,7 @@ async def example_map_and_extract():
extract_schema = ExtractSchema.schema()
# Perform the extraction
extract_result = await app.extract(['https://firecrawl.dev'], {
'prompt': "Extract the title, description, and links from the website",
'schema': extract_schema
})
extract_result = await app.extract(['https://firecrawl.dev'], prompt="Extract the title, description, and links from the website", schema=extract_schema)
print(extract_result)
# Define event handlers for websocket

2
apps/python-sdk/firecrawl/__init__.py
View File

@ -13,7 +13,7 @@ import os
from .firecrawl import FirecrawlApp # noqa
__version__ = "1.17.0"
__version__ = "2.0.0"
# Define the logger for the Firecrawl project
logger: logging.Logger = logging.getLogger("firecrawl")