[python]Filmarksのレビューをスクレイピングする

# import & パラメータ定義
from time import sleep, time
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.options import Options 

CONNECTION_RETRY = 10

options = Options()
options.binary_location = '/Applications/Google Chrome Beta.app/Contents/MacOS/Google Chrome Beta'
driver = webdriver.Chrome(service=Service('./chromedriver-bata'), options=options)

# タイトルを入れてそのタイトルページの映画レビューを取得
def get_page_review(film_title, i=1):
  if not select_movie_item_with_retry(film_title):
    exit()
  else:
    basepath = driver.current_url 
    
  while True:
    access_url = basepath + f'?page={i}'
    print(access_url)
    try:
      driver.get(access_url)
    except:
      break

    sleep(0.2)
    try:
      reviews = driver.find_elements(by=By.CLASS_NAME, value='p-mark__review')
      goods = driver.find_elements(by=By.CLASS_NAME, value='c-reactions__count')
      scores = driver.find_elements(by=By.CLASS_NAME, value='c-rating__score')
    except:
      print('continue')
      i += 1
      continue
    
    # no review
    if len(reviews)==0 and len(goods)==0 and len(scores)==0:
      break

    for review, good, score in zip(reviews, goods, scores):
      print(review.text, good.text, score.text)
    i += 1
    
    # 100ページ分取得したら終了
    if i >= 100:
      break
    
def select_movie_item_with_retry(film_title):
  print(f'https://filmarks.com/search/movies?q="{film_title}"')
  driver.get(f'https://filmarks.com/search/movies?q="{film_title}"')
  
  for i in range(1, CONNECTION_RETRY + 1):
    try:
      driver.find_elements(by=By.CLASS_NAME, value="p-content-cassette__jacket")[0].click()
    except Exception as e:
      print("error:{e} retry:{i}/{max}".format(e=e, i=i, max=CONNECTION_RETRY))
      sleep(1)
    else:
      return True
  return False

get_page_review('Joker')