Function extract_structured_data_using_llm

docs/examples/quickstart_async.py:110–137

(provider: str, api_token: str = None, extra_headers: Dict[str, str] = None)

    )

async def extract_structured_data_using_llm(provider: str, api_token: str = None, extra_headers: Dict[str, str] = None):
    print(f"\n--- Extracting Structured Data with {provider} ---")
    
    if api_token is None and provider != "ollama":
        print(f"API token is required for {provider}. Skipping this example.")
        return

    extra_args = {}
    if extra_headers:
        extra_args["extra_headers"] = extra_headers

    async with AsyncWebCrawler(verbose=True) as crawler:
        result = await crawler.arun(
            url="https://openai.com/api/pricing/",
            word_count_threshold=1,
            extraction_strategy=LLMExtractionStrategy(
                provider=provider,
                api_token=api_token,
                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"}.""",
                extra_args=extra_args
            ),
            bypass_cache=True,
        )
        print(result.extracted_content)

async def extract_structured_data_using_css_extractor():
    print("\n--- Using JsonCssExtractionStrategy for Fast Structured Output ---")