服务器需要一个令牌。没有令牌，它只会在其容器内部响应。

导出 CRAWL4AI_API_TOKEN="$(openssl rand -hex 32)"
docker run -d -p 11235:11235 --name crawl4ai --shm-size=1g \
  -e CRAWL4AI_API_TOKEN="$CRAWL4AI_API_TOKEN" \
  unclecode/crawl4ai:latest

测试它（启动大约需要 10 秒）：

curl -s http://localhost:11235/md \
  -H "Authorization: Bearer $CRAWL4AI_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://news.ycombinator.com"}' | jq -r .markdown

仪表板在 http://localhost:11235/dashboard，操场在 http://localhost:11235/playground。LLM 密钥、MCP 和所有设置：自托管指南。

# 将页面作为 Markdown
crwl https://news.ycombinator.com -o markdown

# 深度爬取，广度优先，最多 10 个页面
crwl https://docs.crawl4ai.com --deep-crawl bfs --max-pages 10

# 对页面提问（需要 LLM 密钥：crwl 配置）
crwl https://www.example.com/products -q "提取所有产品价格"

import asyncio
从 crawl4ai 导入 AsyncWebCrawler、BrowserConfig、CrawlerRunConfig、CacheMode 从 crawl4ai.content_filter_strategy 导入 PruningContentFilterLXML 从 crawl4ai.markdown_generation_strategy 导入 DefaultMarkdownGenerator

async def main():
    run_config = CrawlerRunConfig(
        cache_mode=CacheMode.BYPASS,
        markdown_generator=DefaultMarkdownGenerator(
            content_filter=PruningContentFilterLXML(threshold=0.48, threshold_type="fixed", min_word_threshold=0)
        ),
    )
    async with AsyncWebCrawler(config=BrowserConfig(headless=True)) as crawler:
        result = await crawler.arun(url="https://en.wikipedia.org/wiki/Web_crawler", config=run_config)
        print(len(result.markdown.raw_markdown), "characters of raw Markdown")
        print(len(result.markdown.fit_markdown), "characters after the filter")

asyncio.run(main())

import asyncio, json
从 crawl4ai 导入 AsyncWebCrawler、BrowserConfig、CrawlerRunConfig、CacheMode、JsonCssExtractionStrategy

schema = {
    "name": "Quotes",
    "baseSelector": "div.quote",
    "fields": [
        {"name": "text", "selector": "span.text", "type": "text"},
        {"name": "author", "selector": "small.author", "type": "text"},
        {"name": "tags", "selector": "a.tag", "type": "list", "fields": [{"name": "tag", "type": "text"}]},
    ],
}

异步 def main():
    run_config = CrawlerRunConfig(
        extraction_strategy=JsonCssExtractionStrategy(schema),
        scan_full_page=True,   # scroll to the end, so the page loads every quote
        scroll_delay=0.5,
        cache_mode=CacheMode.BYPASS,
    )
    async with AsyncWebCrawler(config=BrowserConfig(headless=True)) as crawler:
        result = await crawler.arun(url="https://quotes.toscrape.com/scroll", config=run_config)
        quotes = json.loads(result.extracted_content)
        print(f"Extracted {len(quotes)} quotes")
        print(json.dumps(quotes[0], indent=2))

asyncio.run(main())

import os, asyncio
from pydantic import BaseModel, Field
from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, CacheMode, LLMConfig, LLMExtractionStrategy

class ModelFee(BaseModel):
    model_name: str = Field(..., description="Name of the model.")
    input_fee: str = Field(..., description="Fee for input tokens.")
    output_fee: str = Field(..., description="Fee for output tokens.")

异步 def main():
    run_config = CrawlerRunConfig(
        cache_mode=CacheMode.BYPASS,
        extraction_strategy=LLMExtractionStrategy(
            # any provider LiteLLM supports, e.g. "ollama/llama3.3" with api_token="no-token"
            llm_config=LLMConfig(provider="openai/gpt-4o-mini", api_token=os.getenv("OPENAI_API_KEY")),
            schema=ModelFee.model_json_schema(),
            extraction_type="schema",
            instruction="Extract every model name with its input and output token fee.",
        ),
    )
    async with AsyncWebCrawler() as crawler:
        result = await crawler.arun(url="https://openai.com/api/pricing/", config=run_config)
        print(result.extracted_content)

asyncio.run(main())

import os, asyncio
from pathlib import Path 从 crawl4ai 导入 AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode

async def main():
    user_data_dir = os.path.join(Path.home(), ".crawl4ai", "browser_profile")
    os.makedirs(user_data_dir, exist_ok=True)
    browser_config = BrowserConfig(headless=True, user_data_dir=user_data_dir, use_persistent_context=True)
    run_config = CrawlerRunConfig(cache_mode=CacheMode.BYPASS, magic=True)
    async with AsyncWebCrawler(config=browser_config) as crawler:
        result = await crawler.arun(url="ADDRESS_OF_A_CHALLENGING_WEBSITE", config=run_config)
        print(result.success, len(result.markdown))

asyncio.run(main())

将以下徽章之一添加到您的 README、文档或网站中：

添加徽章的HTML代码：

<!-- 迪斯科主题（动画效果） -->
<a href="https://github.com/unclecode/crawl4ai">

</a>

<!-- 夜间主题（暗色带霓虹） -->
<a href="https://github.com/unclecode/crawl4ai">

</a>

<!-- 黑暗主题（经典） -->
<a href="https://github.com/unclecode/crawl4ai">

</a>

<!-- 明亮主题（经典） -->
<a href="https://github.com/unclecode/crawl4ai">

</a>

<!-- 简易盾徽章 -->
<a href="https://github.com/unclecode/crawl4ai">

</a>