mirror of
https://github.com/TheAlgorithms/Python.git
synced 2024-12-24 12:10:16 +00:00
51b769095f
* Create get_imdb_top_250_movies_csv.py * Update get_imdb_top_250_movies_csv.py * Update get_imdb_top_250_movies_csv.py * get_imdb_top_250_movies() Co-authored-by: Christian Clauss <cclauss@me.com>
30 lines
913 B
Python
30 lines
913 B
Python
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()
|