爬虫類はxpath解析を使っています。（固定形式のファイルに保存します。）

広西チワン族自治区博物館に登ります。

import requests
# from bs4 import BeautifulSoup
import urllib
from lxml import etree
import time
import re

url = 'http://www.gxmuseum.cn/plus/guestbook.php?gotopagerank=&totalresult=188&pageno='
def get_info(url, data=None):
    headers = {"User_Agent": "Mozilla/5.0(compatible; MSIE 5.5; Windows 10)"}
    data =requests.get(url,headers).text

    #print(data)
    content = etree.HTML(data)

    titles = content.xpath('//*[@class="timetd"]/strong/text()')
    questions = content.xpath('///*[@class="msgtd"]/div/text()')
    replys = content.xpath('///*[@class="msgtd"]//span/text()')
    times = content.xpath('///*[@class="timetd"]/text()')
    primary_class = '          '
    times = times[1:2]
    #time = re.findall('\d+', times)
    print(times)
    for x in range(len(titles)-1):
        with open('          .txt', 'a', encoding='utf-8') as file:
            file.write('' + '
')
            file.write('=' + str(titles[x]) + '
')
            file.write('=' + str(times) + '
')
            file.write('=' + str(questions[x]) + '
')
            file.write('=' + str(replys[x]) + '
')
            file.write('=' + str(primary_class) + '
')
            file.write('' + '
')

def get_more(start, end):
    for one in range(start, end):
        get_info(url + str(one))
        time.sleep(1)


get_more(1, 19)