Created
July 23, 2021 13:28
-
-
Save BrunoMoreno/3af5af53acc8a49c8b1b4f19c6460964 to your computer and use it in GitHub Desktop.
Scraper for imdb movies
This file contains hidden or 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
import requests | |
from bs4 import BeautifulSoup | |
import pandas as pd | |
import csv | |
url = "https://www.imdb.com/search/title/?groups=top_1000" | |
results = requests.get(url) | |
soup = BeautifulSoup(results.text, "html.parser") | |
titles = [] | |
years = [] | |
time = [] | |
imdb_ratings = [] | |
genre = [] | |
votes = [] | |
movie_div = soup.find_all("div", class_="lister-item mode-advanced") | |
for movieSection in movie_div: | |
name = movieSection.h3.a.text | |
titles.append(name) | |
year = movieSection.h3.find("span", class_="lister-item-year").text | |
years.append(year) | |
ratings = movieSection.strong.text | |
imdb_ratings.append(ratings) | |
category = movieSection.find("span", class_="genre").text.strip() | |
genre.append(category) | |
runTime = movieSection.find("span", class_="runtime").text | |
time.append(runTime) | |
nv = movieSection.find_all("span", attrs={"name": "nv"}) | |
vote = nv[0].text | |
votes.append(vote) | |
movies = pd.DataFrame( | |
{ | |
"Movie": titles, | |
"Year": years, | |
"RunTime": time, | |
"imdb": imdb_ratings, | |
"Genre": genre, | |
"votes": votes, | |
} | |
) | |
# cleaning | |
movies["Year"] = movies["Year"].str.extract("(\\d+)").astype(int) | |
movies["RunTime"] = movies["RunTime"].str.replace("min", "minutes") | |
movies["votes"] = movies["votes"].str.replace(",", "").astype(int) | |
print(movies) | |
movies.to_csv(r"movies.csv", index=False, header=True) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment