口コミ保存用スクリプト

AI画像生成用に、シティヘブンネットの口コミをローカルにテキスト保存するスクリプトを作成しました。不完全＆不要な部分が混ざっていますが、とりあえず動いたので、参考までに。

##############
# 機能
#   heaven口コミ全文保存
# 
#  2023.10.31

import ssl
ssl._create_default_https_context = ssl._create_unverified_context
import urllib
from urllib.parse import urlparse
import os, sys
import pprint
# import config
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import datetime
from selenium.common.exceptions import NoSuchElementException
import time

## jouname
girl='jou'

## chromedriver path

chrome_driver_path = r'C:/work/aaaaa/chromedriver.exe'

### Create URLs #######################################################################

review_urls = []
for i in range(1,8):
    review_urls.append("https://www.cityheaven.net/saitama/A1101/A110101/loveomiya/reviews/"+str(i)+"/?girlid=nnnnnnnnn")

print(review_urls)

# chrome driver #####################################################

options = Options()
options.page_load_strategy = 'normal'
# options.add_argument('--blink-settings=imagesEnabled=false')
# driver = webdriver.Chrome(executable_path = chrome_driver_path ,options=options)
driver = webdriver.Chrome(options=options)

if os.path.isdir('shop_a') == False:
    os.makedirs('shop_a')
if os.path.isdir('./shop_a/'+ girl) == False:
    os.makedirs('./shop_a/' + girl)


log_file_path = "./jou_log.txt"
sys.stdout = open(log_file_path, "w", encoding='utf-8') 

for url in review_urls:
    driver.get(url)

    review_elements = driver.find_elements(By.CLASS_NAME,"review-item")

    for review_element in review_elements:
        usernameurl = review_element.find_element(By.XPATH,'.//div[1]/div[1]/div/a').get_attribute('href') # UsernameURL
        usernametext = review_element.find_element(By.XPATH,'.//div[1]/div[1]/div/a').text
        visitdate = review_element.find_element(By.XPATH,'.//div[1]/div[2]/div[1]/dl/dd[1]').text
        review_item_rate1 = review_element.find_element(By.XPATH,'.//div[2]/ul/li[1]/span').text
        review_item_rate2 = review_element.find_element(By.XPATH,'.//div[2]/ul/li[2]/span').text
        review_item_rate3 = review_element.find_element(By.XPATH,'.//div[2]/ul/li[3]/span').text
        review_item_rate4 = review_element.find_element(By.XPATH,'.//div[2]/ul/li[4]/span').text
        review_item_rate5 = review_element.find_element(By.XPATH,'.//div[2]/ul/li[5]/span').text

        review_title = review_element.find_element(By.XPATH,'.//div[2]/div[2]/span') # review_title
        review_postdate = review_element.find_element(By.XPATH,'div[2]/p[2]') # review post date
        review_post = review_element.find_element(By.XPATH,'.//div[2]/p[@class="review-item-post"]') # review_post

        print('='*40)
        print("usernameurl : ",usernameurl)
        print("usernametext : ",usernametext)
        print("visitdate : ", visitdate)
        print("point : 女の子 : "+review_item_rate1+
              " プレイ : "+review_item_rate2+
              " 料金 : "+review_item_rate3+
              " スタッフ : "+review_item_rate4+
              " 写真 : "+review_item_rate5)
        print("title : ", review_title.text)
        print("date : ", review_postdate.text)
        print("---poststart---\n", review_post.text)
        print("---postend---") 


sys.stdout.close()
sys.stdout = sys.__stdout__

print("END of RESULT")
while True:
    pass

※取得データ差し上げます。