🔥 Open-source no-code web data extraction platform. Turn websites to APIs and spreadsheets with no-code robots in minutes! [In Beta]

Extract Keywords from sentence or Replace keywords in sentences.

Undetectable, Lightning-Fast, and Adaptive Web Scraping for Python

Converts a pdf file into a text file while keeping the layout of the original pdf. Useful to extract the content from a table in a pdf file for instance. This is a subclass of PDFTextStripper class (from the Apache PDFBox library).

🚚 Agile Data Preparation Workflows made easy with Pandas, Dask, cuDF, Dask-cuDF, Vaex and PySpark

Lightweight library for scraping web-sites with LLMs

📰 Let ChatGPT Summarize Hacker News for You

🚜 Parse text and tables from PDF files.

A powerful Python library for getting rich data from the Vietnam Stock Market using just a few lines of code

Pure Python, lightweight, Pillow-based solver for Amazon's text captcha.

Benchmarking PDF libraries

Wikipedia information extraction library

A tool for scraping emails, social media accounts, and much more information from websites using Google Search Results.

A python client for the Sypht API

This repository provides usage examples for the Python module Newspaper3k.

Accurate, private and configurable document retrieval LLM

A Python utility to digitize plots.

Data processing and modelling framework for automating tasks (incl. Python & SQL transformations).

Structured HTML table data extraction from URLs in Go that has almost no external dependencies

Superpipe - optimized LLM pipelines for structured data