python爬取笔趣阁小说案例

import requests
from bs4 import BeautifulSoup

if __name__ == "__main__":
	# 请求头 
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36 Edg/96.0.1054.62'
    }
    # 获取网站地址
    url = 'https://www.bbiquge.net/book_133312/'
    page_text = requests.get(url=url, headers=headers).text

    # 在首页中解析出章节的标题和详情页的url
    # 实例化BeautifulSoup对象，需要将页面源码数据加载到该对象中
    soup = BeautifulSoup(page_text, 'lxml')
    # 解析章节标题和详情页的url
    li_list = soup.select('.zjbox > dl > dd')
    fp = open('./book.txt', 'w', encoding='utf-8')
    for li in li_list:
        title = li.a.string
        detail_url = 'https://www.bbiquge.net/book_133312/' + li.a['href']
        detail_page_text = requests.get(url=detail_url, headers=headers).text
        # 解析出详情页中相关的章节内容
        detail_soup = BeautifulSoup(detail_page_text, 'lxml')
        div_tag = detail_soup.find('div', class_='border')
        # 解析到了章节的内容
        content = div_tag.text
        fp.write(title + ':' + content + 'n')
        print(title, '打印成功！')