python - 下载小说

这里以小说网站https://www.biqgg.cc/为例,其他小说类网站并不适用,需要具体分析,主要是小说内容部分的html标签,大同小异.

import requests
from bs4 import BeautifulSoup
def save(sub_title, cont):
    with open('xiaoshuo\\' + sub_title + '.txt', 'w') as f:
        f.write(cont)


if __name__ == '__main__':
    url = 'https://www.biqgg.cc/book/4422/'
    headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36'}
    html = requests.get(url=url, headers=headers).text
    soup = BeautifulSoup(html, "lxml")
    Title = soup.select('h1')[0].string #小说名
    down_urls = soup.select(".listmain dl dd a")
    for i, down_url in enumerate(down_urls):
        if i != 10:
            d_url = 'https://www.biqgg.cc' + down_url.attrs.get('href')
        html_conts = requests.get(url=d_url, headers=headers).text
        soup_html = BeautifulSoup(html_conts, 'lxml')
        sub_title = soup_html.select(".content h1")[0].string
        cont = soup_html.select(".content #chaptercontent")[0].get_text()
        save(sub_title, cont)