GitHub:https://github.com/unclecode/crawl4ai
更多AI开源软件:发现分享好用的AI工具、AI开源软件、AI模型、AI变现 - 小众AI
Crawl4AI旨在让网页爬取和数据提取变得简单而高效。无论构建复杂的 AI 应用程序还是增强大语言模型,Crawl4AI 都能提供简化工作流程所需的工具。凭借完全的异步支持,Crawl4AI 可确保爬取任务快速、可靠且可扩展。
Markdown 生成
结构化数据提取
浏览器集成
爬行和刮擦
部署
附加功能
# Install the package
pip install -U crawl4ai
# For pre release versions
pip install crawl4ai --pre
# Run post-installation setup
crawl4ai-setup
# Verify your installation
crawl4ai-doctor
如果您遇到任何与浏览器相关的问题,您可以手动安装它们:
python -m playwright install --with-deps chromium
import asyncio
from crawl4ai import *
async def main():
async with AsyncWebCrawler() as crawler:
result = await crawler.arun(
url="https://www.nbcnews.com/business",
)
print(result.markdown)
if __name__ == "__main__":
asyncio.run(main())
# Basic crawl with markdown output
crwl https://www.nbcnews.com/business -o markdown
# Deep crawl with BFS strategy, max 10 pages
crwl https://docs.crawl4ai.com --deep-crawl bfs --max-pages 10
# Use LLM extraction with a specific question
crwl https://www.example.com/products -q "Extract all product prices"
import asyncio
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode
from crawl4ai.content_filter_strategy import PruningContentFilter, BM25ContentFilter
from crawl4ai.markdown_generation_strategy import DefaultMarkdownGenerator
async def main():
browser_config = BrowserConfig(
headless=True,
verbose=True,
)
run_config = CrawlerRunConfig(
cache_mode=CacheMode.ENABLED,
markdown_generator=DefaultMarkdownGenerator(
content_filter=PruningContentFilter(threshold=0.48, threshold_type="fixed", min_word_threshold=0)
),
# markdown_generator=DefaultMarkdownGenerator(
# content_filter=BM25ContentFilter(user_query="WHEN_WE_FOCUS_BASED_ON_A_USER_QUERY", bm25_threshold=1.0)
# ),
)
async with AsyncWebCrawler(config=browser_config) as crawler:
result = await crawler.arun(
url="https://docs.micronaut.io/4.7.6/guide/",
config=run_config
)
print(len(result.markdown.raw_markdown))
print(len(result.markdown.fit_markdown))
if __name__ == "__main__":
asyncio.run(main())
import asyncio
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode
from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
import json
async def main():
schema = {
"name": "KidoCode Courses",
"baseSelector": "section.charge-methodology .w-tab-content > div",
"fields": [
{
"name": "section_title",
"selector": "h3.heading-50",
"type": "text",
},
{
"name": "section_description",
"selector": ".charge-content",
"type": "text",
},
{
"name": "course_name",
"selector": ".text-block-93",
"type": "text",
},
{
"name": "course_description",
"selector": ".course-content-text",
"type": "text",
},
{
"name": "course_icon",
"selector": ".image-92",
"type": "attribute",
"attribute": "src"
}
}
}
extraction_strategy = JsonCssExtractionStrategy(schema, verbose=True)
browser_config = BrowserConfig(
headless=False,
verbose=True
)
run_config = CrawlerRunConfig(
extraction_strategy=extraction_strategy,
js_code=["""(async () => {const tabs = document.querySelectorAll("section.charge-methodology .tabs-menu-3 > div");for(let tab of tabs) {tab.scrollIntoView();tab.click();await new Promise(r => setTimeout(r, 500));}})();"""],
cache_mode=CacheMode.BYPASS
)
async with AsyncWebCrawler(config=browser_config) as crawler:
result = await crawler.arun(
url="https://www.kidocode.com/degrees/technology",
config=run_config
)
companies = json.loads(result.extracted_content)
print(f"Successfully extracted {len(companies)} companies")
print(json.dumps(companies[0], indent=2))
if __name__ == "__main__":
asyncio.run(main())
import os
import asyncio
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode, LLMConfig
from crawl4ai.extraction_strategy import LLMExtractionStrategy
from pydantic import BaseModel, Field
class OpenAIModelFee(BaseModel):
model_name: str = Field(..., description="Name of the OpenAI model.")
input_fee: str = Field(..., description="Fee for input token for the OpenAI model.")
output_fee: str = Field(..., description="Fee for output token for the OpenAI model.")
async def main():
browser_config = BrowserConfig(verbose=True)
run_config = CrawlerRunConfig(
word_count_threshold=1,
extraction_strategy=LLMExtractionStrategy(
# Here you can use any provider that Litellm library supports, for instance: ollama/qwen2
# provider="ollama/qwen2", api_token="no-token",
llm_config = LLMConfig(provider="openai/gpt-4o", api_token=os.getenv('OPENAI_API_KEY')),
schema=OpenAIModelFee.schema(),
extraction_type="schema",
instruction="""From the crawled content, extract all mentioned model names along with their fees for input and output tokens.
Do not miss any models in the entire content. One extracted model JSON format should look like this:
{"model_name": "GPT-4", "input_fee": "US$10.00 / 1M tokens", "output_fee": "US$30.00 / 1M tokens"}."""
),
cache_mode=CacheMode.BYPASS,
)
async with AsyncWebCrawler(config=browser_config) as crawler:
result = await crawler.arun(
url='https://openai.com/api/pricing/',
config=run_config
)
print(result.extracted_content)
if __name__ == "__main__":
asyncio.run(main())
import os, sys
from pathlib import Path
import asyncio, time
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode
async def test_news_crawl():
# Create a persistent user data directory
user_data_dir = os.path.join(Path.home(), ".crawl4ai", "browser_profile")
os.makedirs(user_data_dir, exist_ok=True)
browser_config = BrowserConfig(
verbose=True,
headless=True,
user_data_dir=user_data_dir,
use_persistent_context=True,
)
run_config = CrawlerRunConfig(
cache_mode=CacheMode.BYPASS
)
async with AsyncWebCrawler(config=browser_config) as crawler:
url = "ADDRESS_OF_A_CHALLENGING_WEBSITE"
result = await crawler.arun(
url,
config=run_config,
magic=True,
)
print(f"Successfully crawled {url}")
print(f"Content length: {len(result.markdown)}")