爬取中华古诗词网站python代码

以下是爬取中华古诗词网站的Python代码：

import requests
from bs4 import BeautifulSoup

# 获取诗人信息
def get_poet_info(url):
    res = requests.get(url)
    soup = BeautifulSoup(res.text, 'html.parser')
    poet_name = soup.select_one('.son1 h1').text
    poet_intro = soup.select_one('.son2 p').text
    return {'name': poet_name, 'intro': poet_intro}

# 获取诗词详情页链接
def get_detail_links(url):
    res = requests.get(url)
    soup = BeautifulSoup(res.text, 'html.parser')
    detail_links = [a['href'] for a in soup.select('.typecont a')]
    return detail_links

# 获取诗词内容
def get_poem_content(url):
    res = requests.get(url)
    soup = BeautifulSoup(res.text, 'html.parser')
    poem_title = soup.select_one('.cont h1').text
    poem_dynasty = soup.select_one('.cont p a').text
    poem_author = soup.select_one('.cont p a:nth-of-type(2)').text
    poem_content = soup.select_one('.cont .contson').text.strip()
    return {'title': poem_title, 'dynasty': poem_dynasty, 'author': poem_author, 'content': poem_content}

# 爬取诗人的全部诗词
def crawl_poet(url):
    poet_info = get_poet_info(url)
    print('诗人：', poet_info['name'])
    print('简介：', poet_info['intro'])
    detail_links = get_detail_links(url)
    for link in detail_links:
        poem_content = get_poem_content(link)
        print('题目：', poem_content['title'])
        print('朝代：', poem_content['dynasty'])
        print('作者：', poem_content['author'])
        print('内容：', poem_content['content'])
        print('------------------------')

# 测试
crawl_poet('https://so.gushiwen.cn/authors/authorvsw_4d5dd6f7f59aA1.aspx')