Skip to content

Create get_imdb_top_250_movies_csv.py #1659

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Jan 5, 2020
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 29 additions & 0 deletions web_programming/get_imdb_top_250_movies_csv.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
import csv
from typing import Dict

import requests
from bs4 import BeautifulSoup


def get_imdb_top_250_movies(url: str = "") -> Dict[str, float]:
url = url or "https://www.imdb.com/chart/top/?ref_=nv_mv_250"
soup = BeautifulSoup(requests.get(url).text, "html.parser")
titles = soup.find_all("td", attrs="titleColumn")
ratings = soup.find_all("td", class_="ratingColumn imdbRating")
return {
title.a.text: float(rating.strong.text)
for title, rating in zip(titles, ratings)
}


def write_movies(filename: str = "IMDb_Top_250_Movies.csv") -> None:
movies = get_imdb_top_250_movies()
with open(filename, "w", newline="") as out_file:
writer = csv.writer(out_file)
writer.writerow(["Movie title", "IMDb rating"])
for title, rating in movies.items():
writer.writerow([title, rating])


if __name__ == "__main__":
write_movies()