Python - Webscraping "pollution" articles from New Zealand Herald and Guardian newspapers to do the Text Mining and Text
This corpus analysis is about to find out how the pollutions were represented in New Zealand Herald and Guardian. The project was processed based on Python (os, re, requests, and BeautifulSoup) and AntConc to collect the texts and find out the unique patterns in the way the articles were written. Following that, the folder includes 5 files:
- Webscraping folder includes 2 Python files which were used to scrape articles from the New Zealand Herald and the Guardian.
- Corpora folder includes all the texts from scraping
- English stoplist text file
- Instruction text file (instructed how the process was done)
- Analysis report in Word file