酷虎小说网爬虫

import requests
from pyquery import PyQuery
import re
import os

# 构造请求头
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",
    "Connection": "close"
}


# TODO 1.根据小说链接得到小说目录和对应的url
def get_catalogue(url):
    # 发送请求
    response = requests.get(url=url, headers=headers)
    response.encoding = "gbk"  # 指定编码
    chapter_info_list = []  # 用来存储获取到的所有url和章节标题数据
    doc = PyQuery(response.text)
    # print(doc)
    pages_url = doc(".list-charts li a").items()
    # print(pages_url)
    for page_url in pages_url:
        title = page_url.text()
        chapter_url = "http://www.kuhu168.com" + page_url.attr("href")
        # print(title, chapter_url)
        # 使用字典存储url和title
        chapter = {"title": title, "url": chapter