Marvin Vista marvinvista
marvinvista
/ mathpix2gpt.py
Last active
April 29, 2023 23:08
— forked from danielgross/mathpix2gpt.py
A version of Daniel Gross' mathpix2gpt.py that anyone can run on Replit.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import os | |
| import sys | |
| import time | |
| import requests | |
| import openai | |
| import tiktoken | |
| from termcolor import colored | |
| openai.api_key = os.getenv('OPENAI_API_KEY') | |
| USE_GPT_4_32K = True |
marvinvista
/ pdf_scraper_to_markdown.py
Created
April 29, 2023 03:54
Scrape PDF files from a website and convert them to markdown.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import os | |
| import requests | |
| from bs4 import BeautifulSoup | |
| import PyPDF2 | |
| # Convert PDF to text | |
| def pdf2text(pdf_path): | |
| with open(pdf_path, "rb") as f: | |
| pdf_reader = PyPDF2.PdfReader(f) | |
| text = "" |
marvinvista
/ rss_feed_scraper_to_text.py
Last active
June 15, 2024 11:16
Scrape webpages from the links in an RSS feed and save their content as text files with the same name as the page link.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import os | |
| import re | |
| import requests | |
| import feedparser | |
| from bs4 import BeautifulSoup | |
| from urllib.parse import urlparse | |
| def save_text_file(content, filename): | |
| with open(filename, 'w') as file: | |
| file.write(content) |