What it does
We extract the data from the GameRant excel sheet. Once, we have acquired the urls to the GameRant articles, we scrape the article web page for title and article text. We then feed it to the AI so it can return key-words. The same process is then repeated for other news article sources, along with scraping their tweets. After that, we compare the keywords from the GameRant article and outside news articles. If there is a match, we go back to the GameRant and outside source news article and scrape the article text. When that's completed, we feed the two articles to the AI for comparison. When a match occurs, we calculate the difference between the two articles timestamps and output it in an csv file.
Challenges we ran into
Twitter API is very expensive, meaning we needed to scrape twitter accounts for information. That also entails restrictions like rate limits. Scraping websites was another challenge since each website is built differently. We didn't have enough time to implement scrapers for the other websites.
Accomplishments that we're proud of
We are proud of implementing the AI since it works well.
What we learned
We deepened our knowledge of python. We learned how to scrape websites for their contents and how to implement AI into our project.
What's next for GameRantNewsTimeliness
We are planning to add more website scrapers and use the twitter API for faster loading times.
Log in or sign up for Devpost to join the conversation.