今年おすすめの映画とドラマをPythonを使って探し出す

import re
import numpy as np
from time import sleep
from time import time
from random import randint
from requests import get
from bs4 import BeautifulSoup
from IPython.core.display import clear_output
# ループ監視の準備
start_time = time()
requests = 0
pages = [str(i) for i in range(1,2002,50)]
headers = {"Accept-Language": "en-US, en;q=0.5"}
movieTitle = []
movieDate = []
movieRunTime = []
movieGenre = []
movieRating = []
movieScore = []
movieDescription = []
movieDirector = []
movieStars = []
movieVotes = []
movieGross = []

for page in pages:

    # get requestをする
    response = get('https://www.imdb.com/search/title/?release_date=2019-01-01,2019-12-31&sort=num_votes,desc&start=' + page +
    '&ref_=adv_nxt', headers = headers, proxies = proxies)

    # ループをポーズする
    sleep(randint(8,15))

    # requestsをモニターする
    requests += 1
    elapsed_time = time() - start_time
    print('Request:{}; Frequency: {} requests/s'.format(requests, requests/elapsed_time))
    clear_output(wait = True)

    # non-200 status codesに対して警告する
    if response.status_code != 200:
        warn('Request: {}; Status code: {}'.format(requests, response.status_code))

    # 下記の数字以上になったらブレークする
    if requests > 41:
        warn('Number of requests was greater than expected.')
        break

    # BeautifulSoupでrequestの内容をパースする
    page_html = BeautifulSoup(response.text, 'html.parser')

    # 単ページの全50作品を選択する
    mv_containers = page_html.find_all('div', class_ = 'lister-item mode-advanced')
        
    for movie in mv_containers:
        movieFirstLine = movie.find("h3", class_="lister-item-header")
        movieTitle.append(movieFirstLine.find("a").text)
        movieDate.append(re.sub(r"[()]","", movieFirstLine.find_all("span")[-1].text))
        try:
            movieRunTime.append(movie.find("span", class_="runtime").text[:-4])
        except:
            movieRunTime.append(np.nan)
        movieGenre.append(movie.find("span", class_="genre").text.rstrip().replace("\n","").split(","))
        try:
            movieRating.append(movie.find("strong").text)
        except:
            movieRating.append(np.nan)
        try:
            movieScore.append(movie.find("span", class_="metascore").text.rstrip())
        except:
            movieScore.append(np.nan)
        movieDescription.append(movie.find_all("p", class_="text-muted")[-1].text.lstrip())
        movieCast = movie.find("p", class_="")
    
        try:
            casts = movieCast.text.replace("\n","").split('|')
            casts = [x.strip() for x in casts]
            casts = [casts[i].replace(j, "") for i,j in enumerate(["Director:", "Stars:"])]
            movieDirector.append(casts[0])
            movieStars.append([x.strip() for x in casts[1].split(",")])
        except:
            casts = movieCast.text.replace("\n","").strip()
            movieDirector.append(np.nan)
            movieStars.append([x.strip() for x in casts.split(",")])
    
        movieNumbers = movie.find_all("span", attrs={"name": "nv"})
    
        if len(movieNumbers) == 2:
            movieVotes.append(movieNumbers[0].text)
            movieGross.append(movieNumbers[1].text)
        elif len(movieNumbers) == 1:
            movieVotes.append(movieNumbers[0].text)
            movieGross.append(np.nan)
        else:
            movieVotes.append(np.nan)
            movieGross.append(np.nan)

movieData = [movieTitle, movieDate, movieRunTime, movieGenre, movieRating, movieScore, movieDescription,
					movieDirector, movieStars, movieVotes, movieGross]   

import pandas as pd
df = pd.DataFrame(movieData).T
df.tail()

df.columns = ['タイトル','公開年','上映時間','ジャンル','IMDBスコア','メタスコア',\
 'あらすじ','監督','出演者','投票数','興行収入']

print(df.info())

df.sort_values(by='IMDBスコア',ascending=False).head(10)

df['投票数'] = df['投票数'].str.replace(',','')
df['投票数'] = df['投票数'].apply(pd.to_numeric, errors="coerce").astype(int)
df1 = df[(df['投票数'] > 1e4)]
df1.sort_values(by='IMDBスコア',ascending=False).head(10)

df2 = df[(df['投票数'] > 5e4)]
df2.sort_values(by='IMDBスコア',ascending=False).head(10)

df.sort_values(by='メタスコア',ascending=False).head(10)

df['あらすじ'][1517]

df['あらすじ'][216]

df['あらすじ'][135]