一方、同じ2016年の作品でも製作された年がURLに入っていない作品もあります。例えば、『BRAHMAN NAMAN』や『THE SIEGE OF JADOTVILLE』がそうです。
『BRAHMAN NAMAN』であれば「https://www.rottentomatoes.com/m/brahman_naman」、『THE SIEGE OF JADOTVILLE』であれば「https://www.rottentomatoes.com/m/the_siege_of_jadotville」という感じです。
例えば、wikipediaでは「True Memoirs of an International Assassin」という作品ですが、rotten tomatoでは「THE TRUE MEMOIRS OF AN INTERNATIONAL ASSASSIN」と「THE」がついてしまっています。（大文字小文字は全てURLが小文字であり、URLにする際にタイトルを小文字に変えているので問題ないです）
高得点の点数の映画をcsvファイルに出力する
この記事の頭でも書きました以下の手順の「3」のところの実装に移ります。
wikipediaのnetflix original映画一覧をスクレイピングで取得
取得した映画一覧データを元にrotten tomatoesにアクセスして評価の値を取得
取得した評価の値から値の高い映画を求める
点数を取得するところまでできたので後は「ある閾値以上の映画をcsvに出力する」だけです。
上記プログラムに対して、以下のようにコードを追記します。
from rotten_tomatoes_scraper.rt_scraper import MovieScraper
import pandas as pd
import requests
from urllib.error import HTTPError
import re
import time
url_20152017 = "https://en.wikipedia.org/wiki/List_of_Netflix_original_films_(2015%E2%80%932017)"
df_20152017 = pd.read_html(url_20152017)
dict_20152017 = df_20152017[0].to_dict()
base_tomato_url = "https://www.rottentomatoes.com/m/"
high_score_rotten_point_list = []
high_score_rotten_name_list = []
high_score_audience_point_list = []
high_score_audience_name_list = []
both_high_rotten_audience_rotten_point_list = []
both_high_rotten_audience_audience_point_list = []
both_high_rotten_audience_name_list = []
for (title, premiere_day) in zip(dict_20152017['Title'].values(), dict_20152017['Premiere'].values()):
original_title = title.replace(' ', '_')
original_title = original_title.replace("'", '')
original_title = original_title.replace("-", '_')
original_title = original_title.lower()
year = re.findall('\S\d\d\d', premiere_day)
title_with_year = original_title + "_" + year[0]
time.sleep(3)
try:
movie_url = base_tomato_url + original_title
movie_scraper = MovieScraper(movie_url=movie_url)
movie_scraper.extract_metadata()
#### 👇👇👇ここから追加👇👇👇 ####
if movie_scraper.metadata["Score_Rotten"] is not '':
if int(movie_scraper.metadata["Score_Rotten"]) >= 80:
high_score_rotten_name_list.append(original_title)
high_score_rotten_point_list.append(movie_scraper.metadata["Score_Rotten"])
if movie_scraper.metadata["Score_Audience"] is not '':
if int(movie_scraper.metadata["Score_Audience"]) >= 75:
high_score_audience_name_list.append(original_title)
high_score_audience_point_list.append(movie_scraper.metadata["Score_Audience"])
if (movie_scraper.metadata["Score_Rotten"] is not '') and (movie_scraper.metadata["Score_Audience"] is not ''):
if ( int(movie_scraper.metadata["Score_Rotten"]) >= 80 ) and ( int(movie_scraper.metadata["Score_Audience"]) >= 75 ):
both_high_rotten_audience_name_list.append(original_title)
both_high_rotten_audience_rotten_point_list.append(movie_scraper.metadata["Score_Rotten"])
both_high_rotten_audience_audience_point_list.append(movie_scraper.metadata["Score_Audience"])
#### 👆👆👆ここまで追加👆👆👆 ####
except UnicodeEncodeError:
print("unicode error")
except HTTPError:
try:
movie_url = base_tomato_url + title_with_year
movie_scraper = MovieScraper(movie_url=movie_url)
movie_scraper.extract_metadata()
#### 👇👇👇ここから追加👇👇👇 ####
if movie_scraper.metadata["Score_Rotten"] is not '':
if int(movie_scraper.metadata["Score_Rotten"]) >= 80:
high_score_rotten_name_list.append(original_title)
high_score_rotten_point_list.append(movie_scraper.metadata["Score_Rotten"])
if movie_scraper.metadata["Score_Audience"] is not '':
if int(movie_scraper.metadata["Score_Audience"]) >= 75:
high_score_audience_name_list.append(original_title)
high_score_audience_point_list.append(movie_scraper.metadata["Score_Audience"])
if (movie_scraper.metadata["Score_Rotten"] is not '') and (movie_scraper.metadata["Score_Audience"] is not ''):
if ( int(movie_scraper.metadata["Score_Rotten"]) >= 80 ) and ( int(movie_scraper.metadata["Score_Audience"]) >= 75 ):
both_high_rotten_audience_name_list.append(original_title)
both_high_rotten_audience_rotten_point_list.append(movie_scraper.metadata["Score_Rotten"])
both_high_rotten_audience_audience_point_list.append(movie_scraper.metadata["Score_Audience"])
#### 👆👆👆ここまで追加👆👆👆 ####
except:
pass
#### 👇👇👇ここから追加👇👇👇 ####
dict_both_high_point = {'name': both_high_rotten_audience_name_list, \
'rotten point': both_high_rotten_audience_rotten_point_list, \
'audience point': both_high_rotten_audience_audience_point_list}
df_both_high_point = pd.DataFrame(dict_both_high_point)
df_both_high_point.to_csv('both_high_point.csv')
#### 👆👆👆ここまで追加👆👆👆 ####
www.rottentomatoes.com
www.rottentomatoes.com
www.rottentomatoes.com
www.rottentomatoes.com
www.rottentomatoes.com
www.rottentomatoes.com
www.rottentomatoes.com
www.rottentomatoes.com
www.rottentomatoes.com
www.rottentomatoes.com
www.rottentomatoes.com
www.rottentomatoes.com
www.rottentomatoes.com
www.rottentomatoes.com
www.rottentomatoes.com
・・・【略】・・・
