()
| 508 | |
| 509 | |
| 510 | async def main(): |
| 511 | await simple_crawl() |
| 512 | await simple_example_with_running_js_code() |
| 513 | await simple_example_with_css_selector() |
| 514 | await use_proxy() |
| 515 | await capture_and_save_screenshot("https://www.example.com", os.path.join(__location__, "tmp/example_screenshot.jpg")) |
| 516 | await extract_structured_data_using_css_extractor() |
| 517 | |
| 518 | # LLM extraction examples |
| 519 | await extract_structured_data_using_llm() |
| 520 | await extract_structured_data_using_llm("huggingface/meta-llama/Meta-Llama-3.1-8B-Instruct", os.getenv("HUGGINGFACE_API_KEY")) |
| 521 | await extract_structured_data_using_llm("openai/gpt-4o", os.getenv("OPENAI_API_KEY")) |
| 522 | await extract_structured_data_using_llm("ollama/llama3.2") |
| 523 | |
| 524 | # You always can pass custom headers to the extraction strategy |
| 525 | custom_headers = { |
| 526 | "Authorization": "Bearer your-custom-token", |
| 527 | "X-Custom-Header": "Some-Value" |
| 528 | } |
| 529 | await extract_structured_data_using_llm(extra_headers=custom_headers) |
| 530 | |
| 531 | # await crawl_dynamic_content_pages_method_1() |
| 532 | # await crawl_dynamic_content_pages_method_2() |
| 533 | await crawl_dynamic_content_pages_method_3() |
| 534 | |
| 535 | await crawl_custom_browser_type() |
| 536 | |
| 537 | await speed_comparison() |
| 538 | |
| 539 | |
| 540 | if __name__ == "__main__": |
no test coverage detected
searching dependent graphs…