Data scrape imdb movies using python

Question

I am beginner to python, I have been trying to do data scrape imdb movies but it doesn't worked out. then, I try linked the data I scrape to save it as CSV file but it only produce blank sheet.

from bs4 import BeautifulSoup
    import requests,csv
    source = requests.get('http://www.imdb.com/chart/top')
    soup = BeautifulSoup(source.text, 'html.parser')
    
    movies = soup.find('tbody', class_="lister-list").find_all('tr')
    
    for movie in movies: 
        name = movie.find('td',class_="titleColumn").a.text
        rank = movie.find('td',class_="titleColumn").get_text(strip=True).split('.')[0]
        year = movie.find('td',class_="titleColumn").span.text.strip('()')
        rating = movie.find('td',class_="ratingColumn imdbRating").strong.text
    
        print(rank,name,year,rating)

import files 
data.to_csv('sample.csv') 
files.download("sample.csv")

Answer 1

You're not writing to csv in any part of your code. This would be the way to go (taking into account the colab environment):

from bs4 import BeautifulSoup
from google.colab import files
import requests, csv

source = requests.get('http://www.imdb.com/chart/top')
soup = BeautifulSoup(source.text, 'html.parser')

movies = soup.find('tbody', class_="lister-list").find_all('tr')

with open('sample.csv', 'w', newline='') as csvfile:
    fieldnames=['rank','name','year','rating']
    wtr = csv.DictWriter(csvfile, fieldnames=fieldnames)
    wtr.writeheader()

    for movie in movies[0:10]: 
        name = movie.find('td',class_="titleColumn").a.text
        rank = movie.find('td',class_="titleColumn").get_text(strip=True).split('.')[0]
        year = movie.find('td',class_="titleColumn").span.text.strip('()')
        rating = movie.find('td',class_="ratingColumn imdbRating").strong.text

        print(rank,name,year,rating)    
        wtr.writerow({'rank':rank,'name':name,'year':year,'rating':rating})

files.download('sample.csv')

Answer 2

Here's an efficient way using a popular data science library

from bs4 import BeautifulSoup
import requests
import pandas as pd #import pandas here

source = requests.get('http://www.imdb.com/chart/top')
soup = BeautifulSoup(source.text, 'html.parser')
data = pd.DataFrame() #define a dataframe
movies = soup.find('tbody', class_="lister-list").find_all('tr')
    
for movie in movies: 
        name = movie.find('td',class_="titleColumn").a.text
        rank = movie.find('td',class_="titleColumn").get_text(strip=True).split('.')[0]
        year = movie.find('td',class_="titleColumn").span.text.strip('()')
        rating = movie.find('td',class_="ratingColumn imdbRating").strong.text

        _movie = pd.DataFrame({
            'name': [name],
            'rank': [rank],
            'year': [year],
            'rating': [rating]
          )}
          data=data.append(movie) # append each movie to dataframe
    
        print(rank,name,year,rating)

data.to_csv('sample.csv') # save dataframe to csv