Software Developer's Thursday

ScrapeGraphAI: Web Scraping Using Generative AI
Marco Perini

Keen to find a focused, flexible and modular approach to web scraping that can be adapted to different scenarios? Look no further and join us at our August meeting:

ScrapeGraphAI is an open source Python library designed to extract information from web pages using only a URL and a user query. It uses Large Language Models (LLMs) to understand the HTML structure and selectively focus on the content relevant to the user's query. The resulting output is structured in a format (JSON, CSV, etc.) tailored to the user's needs. The library adopts a directed graph approach, allowing the construction of different scraping pipelines by adding or removing specific nodes, or by using pre-configured pipelines, ensuring flexibility and modularity.

Register now and look forward to an inspiring Software Developers Thursday with Marcon Perini.