抓取霹雳轻小说爬虫代码

Posted 2022-12-14 青蛙~~

今天花了一天写的一个爬虫小程序

# -*- coding: utf-8 -*-
# @Time    : 2020/5/9 19:03
# @Author  : 贺林森
# @FileName:  抓取霹雳轻小说
# @Software: PyCharm
# @Email : [e-mail]

import requests
import re
import os

headers = 
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (Khtml, "
                  "like Gecko) Chrome/81.0.4044.138 Safari/537.36"



def get_catalogue(url):
    # 发送请求
    response = requests.get(url=url, headers=headers)
    response.encoding = "utf-8"
    chapter_info_list = []
    if response.status_code == 200:
        li_list = re.findall(r"<li class=.*</li>", response.text)
        for li in li_list:
            # print(li)
            result = re.search(r'href="(.*?)">(.*?)<', li)
            if result:
                chapter_url = "https://www.linovelib.com" + result.group(1)
                title = result.group(2)
                chapter = "title": title, "url": chapter_url
                chapter_info_list.append(chapter)
    print(chapter_info_list)
    return chapter_info_list


def get_content(chapter_info_list):
    for chapter_info in chapter_info_list:
        response = requests.get(url=chapter_info["url"], headers=headers)
        if response.status_code == 200:
            if os.path.exists("霹雳轻小说"):
                pass
            else:
                os.makedirs("霹雳轻小说")
            content_list = re.findall(r"<p>(.*?)</p>", response.content.decode("utf8"))[1:-1]
            with open("./霹雳轻小说/" + chapter_info["title"] + ".txt", "w", encoding="utf8") as file:
                for content in content_list:
                    file.write(content + "\\n")


if __name__ == "__main__":
    get_content(get_catalogue("https://www.linovelib.com/novel/2834/catalog"))