[源码] 使用Python爬虫一键爬取XX阁小说

import os
 
import requests
from lxml import etree
 
def download_txt(name):
    params = {
        "keyword": name
    }
    host = "https://www.1biqug.com"
    resp = requests.get("https://www.1biqug.com/searchbook.php", params=params)
    html = resp.content.decode()
    html = etree.HTML(html)
    ret_list = html.xpath("//li/span[@class='s2']/a/@href")
    detail_url = host + ret_list[0]
    resp = requests.get(detail_url)
    html = etree.HTML(resp.content.decode())
    ret_list = html.xpath("//div[@id='list']//dd//a/@href")
    print(ret_list)
    if not os.path.exists("./{}".format(name)):
        os.mkdir("./{}".format(name))
    for ret in ret_list[12:]:
        url = host + ret
        resp = requests.get(url)
        info = resp.content.decode()
        html = etree.HTML(info)
        title = html.xpath("//h1/text()")
        print(title[0])
        path = os.path.join(name, title[0] + ".html")
        path = path.replace("*", "")
        with open(path, 'w', encoding="utf8") as f:
            f.write(info)
    print(name, "下载完成了")
 
if __name__ == '__main__':
    story = input("请输入小说名")
    download_txt(story)