Python script to gather the text of a html web page and display it in the console. Addtitionally, has the ability to speak the provided text. There is "The Hacker News" rendition in theHackerNews folder and "Artificial Intelligence News" is in the artificialintelligence-news folder.
This folder contains a python file that scrapes thehackernews.com and then passes the data to ChatGPT API to summarize the page. The data from thehackernews.com and summary from ChatGPT is saved in working directory THN_yyymmdd.txt.
The Hacker News
python3 pagescraperTHN.pyFirst, the terminal may request the URL or ask for the text to be spoken. Page text will appear in rainbowtext and can be removed from the scrape() function. Tested on Ubuntu.
Example Usage:
Add URL as argument and y/n for verbal response
python3 pagescraper.py https://www.cnet.com/news/ nOr pipe it to tee command to store in a text file
python3 pagescraper.py https://www.cnet.com/news/ n | tee news_9_20_23.txtOr without any arguments
python3 pagescraper.pyArtificial Intelligence News
python3 pagescraperAINews.py yTo grab python requirements do:
sudo pip3 install espeak rainbowtext PyAudio bs4 openai