extraction-data

🦜⛏️ Did you say you like data?

Django based Resume Parser

WebStripper is a Python CLI tool for digital forensics and ethical hacking that extracts and decrypts credentials, history, bookmarks, and autofill data from Chrome, Firefox, Edge, Brave, and Opera on Windows. Built for automation, and offline analysis of exported browser profiles.

This repo contains google colab notebook for handing Docling for data extraction such as text, image, table etc.

Web application designed to showcase the potential of Data Science and Natural Language Processing (NLP) in the legal domain.

Explore ethical and effective techniques to extract data from Cloudflare-protected websites.

Streamline your invoice processing with AI-powered data extraction and intelligent management tools.

Research about ageism in tweets on the discussion about the Covid-19 vaccine.

"SQL Where Clause" Extraction from User Chat Query with LLM

This Azure Document Intelligence extraction tool converts unstructured documents into structured data. It accurately extracts text and tables, making your information ready for LLMs and immediate use.

MedSummarize AI Medical research assistant that extracts and simplifies complex articles for doctors and patients. 🔍 Features: Dual-mode summaries (expert/patient) Medical term & relationship extraction PubMed-optimized processing Interactive Q&A For: Researchers, doctors.

A **GPT-3 based Resume Parser REST API** that converts resume PDFs into clean, structured JSON files. This service accurately extracts key fields such as contact information, education, job experience, and project history.

Web scraping

Extracting and Visualizing Stock Data (Assignment IBM developper)

Extracción, clasificación y modelización de noticias de El País.