正则古诗词练习

import re
import requests
from fake_useragent import UserAgent
url = 'https://www.gushiwen.cn/shiju/xiejing.aspx'
#随机请求头
headers = {
    'user-agent':UserAgent().random
}
#构造请求
response = requests.get(url,headers=headers)
info  = response.text

# # print(info)
# infos = re.findall(r'<div class="cont">.*?<span .*?>(.*?)</span><a .*?>(.*?)</a>', info, re.DOTALL)
# print(infos)


# print(info)
infos = re.findall(r'<div .*cont', info, re.DOTALL)
contents = []
for m in infos:
    num = re.findall(r'\s<span .*?>(.*?)</span>',info,re.DOTALL)
    txt = re.findall(r'</span><a .*?>(.*?)</a>.*?',info,re.DOTALL)
    contents.append(m)
    poems = []

    for value in zip(num,txt):
        num, txt = value
        poems.append(
            {
                'num': num,
                'txt': txt,

            }
        )
        print(poems)



'''
<div class="cont">.*?<span .*?>(.*?)</span><a .*?>(.*?)</a>.*?<span .*?>(.*?)</span><a .*?>(.*?)</a>'
'''

#'<a .*?>(.*?)</a>'

#'<a .*?>(.*?)</a>'

分析页面

总结
学习了一下正则一些简单语法
对于一些获取的文本正则是不错但是较难编写