Last active
June 1, 2022 06:23
-
-
Save hughlilly/83eaad4ca3a12c5ba04a6bb9b3456ec2 to your computer and use it in GitHub Desktop.
IMDbExtractor.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Based on https://github.com/yogeshp1426/IMDB_Top_50_Web_Scrapper/blob/master/IMDB_csv_out.ipynb | |
from bs4 import BeautifulSoup as soup | |
from urllib.request import urlopen | |
import csv | |
IMDb_url = ( | |
"https://www.imdb.com/search/title/?sort=num_votes,desc&start=1&title_type=feature&year=1950,1960") | |
connection = urlopen(IMDb_url) | |
page_html = connection.read() | |
connection.close() | |
page_soup = soup(page_html, "html.parser") | |
movie_container = page_soup.findAll("div", {"class": "lister-item-content"}) | |
f = open('imdb_dataout.csv', 'w', newline='') | |
writer = csv.writer(f) | |
writer.writerow(['ID', 'title', 'director', 'releaseYear', | |
'runtimeMinutes', 'IMDbURL']) | |
count = 1 | |
for movie in movie_container: | |
title = movie.h3.a.text | |
director = movie.find('p', {"class": ""}).a.text | |
release_year = movie.find( | |
'span', {"class": "lister-item-year"}).text.replace('(', '').replace(')', '') | |
runtime = movie.find('span', {"class": "runtime"}).text.replace(' min', '') | |
imdb_id = movie.h3.a.attrs['href'] | |
url = "https://www.imdb.com" + str(imdb_id) | |
row = [count, title, director, release_year, | |
runtime, url] | |
print(row) | |
writer.writerow(row) | |
count += 1 | |
f.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment