rotten_tomatoes_alex.py

# adapted from https://github.com/alaw1290/CS591B1/blob/master/RTscrapers/moviescraper.py

from bs4 import BeautifulSoup
from selenium import webdriver
import locale
locale.setlocale( locale.LC_ALL, 'en_US.UTF-8' )
import datetime

driver = webdriver.Chrome("/usr/lib/chromium-browser/chromedriver")
# driver = webdriver.PhantomJS() # oesn't work, for whatever reason
# driver.set_window_size(1120, 550)

def get_rotten_tomatoes_result(url):
    """Input URL of Rotten Tomatoes movie, and get dictionary of its ratings"""
    driver.get(url)
    html = driver.page_source
    soup = BeautifulSoup(html, "lxml")
    results = {}    

    # all critics
    all_critics = soup.find("div", { "id" : "all-critics-numbers" })
    all_critics_2 = all_critics.find("div", { "id" : "scoreStats" })
    all_critics_info = all_critics_2.findAll("span", { "class" : '' })

    results["all critics"] = {
        'tomatometer': int(all_critics.find("a", { "id" : 'tomato_meter_link' }).text.strip().replace("%", "")),
        'average_rating': float(all_critics_2.find("div", { "class" : 'superPageFontColor' }).text.split("\n")[2].strip().replace("/10", "")),
        'reviews_counted': int(all_critics_info[0].text),
        'fresh': int(all_critics_info[1].text),
        'rotten': int(all_critics_info[2].text)
    }

    # top critics
    find_top = soup.find("div", { "id" : "top-critics-numbers" }).text
    if "Not Available" in find_top:
        pass
    else:
        top_critics = soup.find("div", { "id" : "top-critics-numbers" })
        top_critics_2 = top_critics.find("div", { "id" : "scoreStats" })
        top_critics_info = top_critics_2.findAll("span", { "class" : '' })

        results["top critics"] = {
            'tomatometer': int(top_critics.find("a", { "id" : 'tomato_meter_link' }).text.strip().replace("%", "")),
            'average_rating': float(top_critics_2.find("div", { "class" : 'superPageFontColor' }).text.split("\n")[2].strip().replace("/10", "")),
            'reviews_counted': int(top_critics_info[0].text),
            'fresh': int(top_critics_info[1].text),
            'rotten': int(top_critics_info[2].text)            
        }

    # audience
    """Consider using a strip() first before split"""
    audience_info =  soup.find("div", { "class" : 'audience-info hidden-xs superPageFontColor' }).text.split("\n")

    results["audience"] = {
        'score': int(soup.find("div", { "class" : "meter-value" }).text.split("\n")[1].replace("%","")),
        'average_rating': float(audience_info[3].strip().replace("/5","")),
        'number_of_ratings': int(audience_info[7].strip().replace(",", ""))
    }

    return results