程序演示如下：
import requests
import re

def parse_page(url):
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'
    }
    response = requests.get(url , headers = headers)
    text = response.text
    titles = re.findall(r'<div\sclass="cont">.*?<b>(.*?)</b>' ,text , re.DOTALL) #re.DOTALL让.可以匹配换行符\n
    authors = re.findall(r'<p class="source">.*?<a.*?>(.*?)</a>',text , re.DOTALL)
    dynasties = re.findall(r'<p class="source".*?<a.*?>.*?<a.*?>(.*?)</a>', text ,re.DOTALL) #因为朝代在p标签下的第二个a标签，所以要用两个写两个a标签
    contents_tags = re.findall(r'<div class="contson".*?>(.*?)</div>',text,re.DOTALL)
    contents = []

    for content in contents_tags:
        x = re.sub(r'<.*?>' ,'',content)
        contents.append(x.strip())        #.strip()把换行符去掉
    poems = []
    for value in zip(titles,dynasties,authors,contents):
        title,dynastie,author,content = value
        poem = {
            'title':title,
            'author':author,
            'dynastie':dynastie,
            'content':content

        }
        poems.append(poem)
    for poem in poems:
        print(poem)
        print('='*40)
def main():
    url = 'https://www.gushiwen.cn/default_1.aspx'
    for x in range(1,5):
        url = 'https://www.gushiwen.cn/default_%s.aspx' %x
        parse_page(url)

if __name__ == '__main__':
    main()

总结：re正则表达式无非是将html所有标签以及网页内容变成文本进行定位提取

项目中使用到的zip如下程序演示：

#zip函数：
a = [1,2]
b = [3,4]
c = zip(a,b)
c = [
    (1,3),
    (2,4)
]

value =(1,2,3)
a,b,c=value
a=1
b=2
c=3