使用Python爬虫一键爬取XX阁小说
本帖最后由 lovemm 于 2022-8-2 16:33 编辑超级简单爬取笔趣阁小说的Python代码，只需要一个Python环境就能运行技术栈：requests，xpath直接上代码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
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:
url = host + ret
resp = requests.get(url)
info = resp.content.decode()
html = etree.HTML(info)
title = html.xpath("//h1/text()")
print(title)
path = os.path.join(name, title + ".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)
谢谢分享！ 多谢楼主分享 谢谢分享 感谢大佬分享，大佬666666 6666666666 谢谢大牛
感谢楼主的分享 谢谢大佬分享 先收藏了，万一用到呢
页:
[1]
2