​
Define the environment

First, we’ll define our environment. For this project. we’ll need the following libraries:

app.py
import beam

app = beam.App(
    name="web-scraper",
    cpu=4,
    memory="4Gi",
    gpu=0,
    python_version="python3.8",
    python_packages=["bs4", "transformers", "torch"],
)

​
Starting the environment

Spin up the environment by running beam start <your app>.py You’ll see the red beam text at the end of your shell path, which means you’ve entered the Beam environment!

​
Write scraping logic

Now, we’ll write logic to scrape the headlines from The New York Times. Create a new file - let’s call it scraper.py.

scraper.py
import time
import requests
from bs4 import BeautifulSoup
from transformers import pipeline


def scrape_nyt():
    res = requests.get("https://www.nytimes.com")
    soup = BeautifulSoup(res.content, "html.parser")
    # Grab all headlines
    headlines = soup.find_all("h3", class_="indicate-hover", text=True)

    total_headlines = len(headlines)
    negative_headlines = 0

    # Iterate through each headline
    for h in headlines:
        title = h.get_text()
        print(title)
        sentiment = predict_sentiment(title)

        print(sentiment)

        if sentiment.get("NEGATIVE") > sentiment.get("POSITIVE"):
            negative_headlines += 1

    print(f"{negative_headlines} negative headlines / {total_headlines} total")


def predict_sentiment(title):
    model = pipeline(
        "sentiment-analysis", model="siebert/sentiment-roberta-large-english"
    )
    result = model(title, truncation=True, top_k=2)
    prediction = {i["label"]: i["score"] for i in result}

    return prediction


if __name__ == "__main__":
    scrape_nyt()

​
Running the scraper

Now, we’re ready to run our code using Beam. In your terminal, run:

python scraper.py

You should see the headlines and the detected sentiment!