Our eighth session of 2024 will be held at the space NOISE. Need guidance in getting around? Have a look here https://bit.ly/3zUDYFy, or ask for it at the Info Desk on the ground floor of the main building.

ScrapeGraphAI is an open-source Python library designed for extracting information from websites by simply using a URL and a user prompt. It leverages Large Language Models (LLMs) to comprehend the HTML structure, selectively focusing on the content relevant to fulfilling the user's request. The resulting output is structured in a format (JSON, CSV, etc.) tailored to the user's needs. The library adopts a directed graph approach, enabling the construction of varied scraping pipelines through the addition or removal of specific nodes, or by employing pre-configured pipelines. This approach ensures flexibility and modularity for adapting to diverse scenarios.

Register now!

18:30 Marco Perini: Software Developers' Thursdays - ScrapeGraphAI: Web Scraping Using Generative AI
19:00 Open discussion