Scrape Top Box Office movies from Rotten Tomatoes.

!rt-scraper.py

#!/usr/bin/python3
# Display Top Box Office movies from Rotten Tomatoes.

import requests
import colored
from pprint import pprint
from bs4 import BeautifulSoup
#  from colored import fg, bg, attr
from colored import stylize
from prettytable import PrettyTable

# get the data
data = requests.get('https://www.rottentomatoes.com/')

# load data into bs4
soup = BeautifulSoup(data.text, 'html.parser')

leaderboard = soup.find('table', { 'id': 'Top-Box-Office' })

movie_table = PrettyTable()
movie_table.field_names = ["Score", "Name", "BO"]
movie_table.align["Name"] = "l"
movie_table.align["BO"] = "l"

for tr in leaderboard.find_all('tr'):
    try:
        movie_score = tr.find('td', class_="left_col").find('span', class_="tMeterScore").getText()
    except AttributeError:
        movie_score = 'n/a'
    movie_name = tr.find('td', class_="middle_col").find('a').getText()
    box_office = tr.find('td', class_="right_col").find('a').getText()
    #  print(stylize(movie_score, colored.bg("red")), movie_name, box_office)
    movie_table.add_row([movie_score, movie_name, box_office])
    #  print(movie_score, movie_name, box_office)

print(movie_table)

.gitignore

*.txt

todo.md

• venv
• put data into table (with coloring)
  • header
  • learn pandas?
• convert % into number
• opening movies
• sort
• cache
  • show diff since last checked
• pip