practice

In [1]:

pip install requests

Requirement already satisfied: requests in c:\users\shuos\anaconda3\lib\site-packages (2.32.2)
Requirement already satisfied: charset-normalizer<4,>=2 in c:\users\shuos\anaconda3\lib\site-packages (from requests) (2.0.4)
Requirement already satisfied: idna<4,>=2.5 in c:\users\shuos\anaconda3\lib\site-packages (from requests) (3.7)
Requirement already satisfied: urllib3<3,>=1.21.1 in c:\users\shuos\anaconda3\lib\site-packages (from requests) (2.2.2)
Requirement already satisfied: certifi>=2017.4.17 in c:\users\shuos\anaconda3\lib\site-packages (from requests) (2024.8.30)
Note: you may need to restart the kernel to use updated packages.

In [2]:

pip install html5lib

Collecting html5libNote: you may need to restart the kernel to use updated packages.

  Downloading html5lib-1.1-py2.py3-none-any.whl.metadata (16 kB)
Requirement already satisfied: six>=1.9 in c:\users\shuos\anaconda3\lib\site-packages (from html5lib) (1.16.0)
Requirement already satisfied: webencodings in c:\users\shuos\anaconda3\lib\site-packages (from html5lib) (0.5.1)
Downloading html5lib-1.1-py2.py3-none-any.whl (112 kB)
   ---------------------------------------- 0.0/112.2 kB ? eta -:--:--
   --- ------------------------------------ 10.2/112.2 kB ? eta -:--:--
   ------------------------ -------------- 71.7/112.2 kB 975.2 kB/s eta 0:00:01
   -------------------------------------- 112.2/112.2 kB 926.7 kB/s eta 0:00:00
Installing collected packages: html5lib
Successfully installed html5lib-1.1

In [3]:

pip install bs4

Requirement already satisfied: bs4 in c:\users\shuos\anaconda3\lib\site-packages (0.0.2)
Requirement already satisfied: beautifulsoup4 in c:\users\shuos\anaconda3\lib\site-packages (from bs4) (4.12.3)
Requirement already satisfied: soupsieve>1.2 in c:\users\shuos\anaconda3\lib\site-packages (from beautifulsoup4->bs4) (2.5)
Note: you may need to restart the kernel to use updated packages.

In [4]:

pip install pandas

Requirement already satisfied: pandas in c:\users\shuos\anaconda3\lib\site-packages (2.2.2)
Requirement already satisfied: numpy>=1.26.0 in c:\users\shuos\anaconda3\lib\site-packages (from pandas) (1.26.4)
Requirement already satisfied: python-dateutil>=2.8.2 in c:\users\shuos\anaconda3\lib\site-packages (from pandas) (2.9.0.post0)
Requirement already satisfied: pytz>=2020.1 in c:\users\shuos\anaconda3\lib\site-packages (from pandas) (2024.1)
Requirement already satisfied: tzdata>=2022.7 in c:\users\shuos\anaconda3\lib\site-packages (from pandas) (2023.3)
Requirement already satisfied: six>=1.5 in c:\users\shuos\anaconda3\lib\site-packages (from python-dateutil>=2.8.2->pandas) (1.16.0)
Note: you may need to restart the kernel to use updated packages.

In [5]:

from bs4 import BeautifulSoup
import requests
import re
import pandas as pd

In [6]:

# Downloading imdb top 250 movie's data
url = 'http://www.imdb.com/chart/top'
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")

In [7]:

movies = soup.select('td.titleColumn')
crew = [a.attrs.get('title') for a in soup.select('td.titleColumn a')]
ratings = [b.attrs.get('data-value')
        for b in soup.select('td.posterColumn span[name=ir]')]

In [8]:

# create a empty list for storing
# movie information
list = []

# Iterating over movies to extract
# each movie's details
for index in range(0, len(movies)):
    
    # Separating movie into: 'place',
    # 'title', 'year'
    movie_string = movies[index].get_text()
    movie = (' '.join(movie_string.split()).replace('.', ''))
    movie_title = movie[len(str(index))+1:-7]
    year = re.search('\((.*?)\)', movie_string).group(1)
    place = movie[:len(str(index))-(len(movie))]
    data = {"place": place,
            "movie_title": movie_title,
            "rating": ratings[index],
            "year": year,
            "star_cast": crew[index],
            }
    list.append(data)

<>:14: SyntaxWarning: invalid escape sequence '\('
<>:14: SyntaxWarning: invalid escape sequence '\('
C:\Users\shuos\AppData\Local\Temp\ipykernel_18892\3357486278.py:14: SyntaxWarning: invalid escape sequence '\('
  year = re.search('\((.*?)\)', movie_string).group(1)

In [9]:

for movie in list:
    print(movie['place'], '-', movie['movie_title'], '('+movie['year'] +
        ') -', 'Starring:', movie['star_cast'], movie['rating'])

In [10]:

#saving the list as dataframe
#then converting into .csv file
df = pd.DataFrame(list)
df.to_csv('imdb_top_250_movies.csv',index=False)

In [11]:

from bs4 import BeautifulSoup
import requests
import re
import pandas as pd


# Downloading imdb top 250 movie's data
url = 'http://www.imdb.com/chart/top'
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")
movies = soup.select('td.titleColumn')
crew = [a.attrs.get('title') for a in soup.select('td.titleColumn a')]
ratings = [b.attrs.get('data-value')
        for b in soup.select('td.posterColumn span[name=ir]')]




# create a empty list for storing
# movie information
list = []

# Iterating over movies to extract
# each movie's details
for index in range(0, len(movies)):
    
    # Separating movie into: 'place',
    # 'title', 'year'
    movie_string = movies[index].get_text()
    movie = (' '.join(movie_string.split()).replace('.', ''))
    movie_title = movie[len(str(index))+1:-7]
    year = re.search('\((.*?)\)', movie_string).group(1)
    place = movie[:len(str(index))-(len(movie))]
    data = {"place": place,
            "movie_title": movie_title,
            "rating": ratings[index],
            "year": year,
            "star_cast": crew[index],
            }
    list.append(data)

# printing movie details with its rating.
for movie in list:
    print(movie['place'], '-', movie['movie_title'], '('+movie['year'] +
        ') -', 'Starring:', movie['star_cast'], movie['rating'])


##.......##
df = pd.DataFrame(list)
df.to_csv('imdb_top_250_movies.csv',index=False)

<>:32: SyntaxWarning: invalid escape sequence '\('
<>:32: SyntaxWarning: invalid escape sequence '\('
C:\Users\shuos\AppData\Local\Temp\ipykernel_18892\1921033849.py:32: SyntaxWarning: invalid escape sequence '\('
  year = re.search('\((.*?)\)', movie_string).group(1)

Downloading imdb top 250 movie’s data