unclecode/crawl4ai

pip install -U crawl4ai
crawl4ai-setup      # installs and sets up the browser
crawl4ai-doctor     # checks the installation

python -m playwright install --with-deps chromium

git clone https://github.com/unclecode/crawl4ai.git
cd crawl4ai
pip install -e ".[all]"     # or: pip install -e .   (the core only)

export 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

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

# A page as Markdown
crwl https://news.ycombinator.com -o markdown

# Deep crawl, breadth first, at most 10 pages
crwl https://docs.crawl4ai.com --deep-crawl bfs --max-pages 10

# Ask a question about a page (needs an LLM key: crwl config)
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 PruningContentFilterLXML
from crawl4ai.markdown_generation_strategy import 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
from crawl4ai import 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"}]},
    ],
}

async 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.")

async 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
from crawl4ai import 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())

<!-- Disco Theme (Animated) -->
<a href="https://github.com/unclecode/crawl4ai">
  <img src="https://raw.githubusercontent.com/unclecode/crawl4ai/main/docs/assets/powered-by-disco.svg" alt="Powered by Crawl4AI" width="200"/>
</a>

<!-- Night Theme (Dark with Neon) -->
<a href="https://github.com/unclecode/crawl4ai">
  <img src="https://raw.githubusercontent.com/unclecode/crawl4ai/main/docs/assets/powered-by-night.svg" alt="Powered by Crawl4AI" width="200"/>
</a>

<!-- Dark Theme (Classic) -->
<a href="https://github.com/unclecode/crawl4ai">
  <img src="https://raw.githubusercontent.com/unclecode/crawl4ai/main/docs/assets/powered-by-dark.svg" alt="Powered by Crawl4AI" width="200"/>
</a>

<!-- Light Theme (Classic) -->
<a href="https://github.com/unclecode/crawl4ai">
  <img src="https://raw.githubusercontent.com/unclecode/crawl4ai/main/docs/assets/powered-by-light.svg" alt="Powered by Crawl4AI" width="200"/>
</a>

<!-- Simple Shield Badge -->
<a href="https://github.com/unclecode/crawl4ai">
  <img src="https://img.shields.io/badge/Powered%20by-Crawl4AI-blue?style=flat-square" alt="Powered by Crawl4AI"/>
</a>