从表格中提取网站文字代码

import requests
from bs4 import BeautifulSoup
import re
import xlwings as xw

wb = xw.Book('E:\\Tim下载文件\\1224.xlsx')   #这是excel表格中存放网址的文件位置
sht = wb.sheets["Sheet1"]   #Sheet1：选择表格中某一个表格

rng = sht.range('i1').expand('table')
nrows = rng.rows.count  # nrows代表表格中有多少行数据
print(nrows)

start = 1
end = 10


urlList = sht.range(f'i{start}:i{end}').value   #i{start}  表示从表格中的i列
i = start

for url in urlList:
    string = ''
    # 确定目标网页
    url = url
    print(url)
    user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36'
    headers = {'User-Agent': user_agent}
    res = requests.get(url=url, headers=headers)
    res.encoding = res.apparent_encoding
    soup = BeautifulSoup(res.text, 'lxml')
    news = soup.find('html')  # 只识别外层的div里面的文字
    string = string + news.get_text()

    # 1.处理空行----------------------------------------success
    string = re.sub('\n{1,100}', '\n', string)
    # 2.处理只含有空格的行--------------------------------success
    string = re.sub('\40{0,100}\n\40{0,100}\n', '\n', string)
    string = re.sub('\40{0,100}\n\40{0,100}', '\n', string)

    # 3.将所有中文冒号转成英文冒号--------------------------success
    string = re.sub('：', ':', string)

    # 4.处理冒号换行空格----------------------------------success
    string = re.sub('\40{0,100}:\40{0,100}\n\40{0,100}', ':', string)
    # 5.处理冒号后面的空格--------------------------------default
    string = re.sub(': {1,100}', ':', string)
    # 6.处理空格----------------------------------------default  怀疑读取出来的不是空格，因为 2. 是可以处理空格的
    string = re.sub('\40{2,100}', '\40', string)

    fileName = 'E:\\网站文件\\' + str(i) + '.txt'
    print(fileName)
    fh = open(fileName, 'w', encoding='utf-8')
    fh.write(string)
    fh.close()
    i = i + 1