爬小说 

import requests
from bs4 import BeautifulSoup


def getID():
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36",
        'Connection': 'keep-alive'
    }

    url = "https://www.duquanben.com/xiaoshuo/13/13977/"
    r = requests.get(url, headers=headers)
    r.encoding = r.apparent_encoding
    soup = BeautifulSoup(r.text, "html.parser")
    return soup
ID=[]
def getId(soup):
    ids = soup.find("ul",{"class":"mulu_list"})
    idss = ids.find_all("li")

    for i in idss:
        id = i.a["href"]
        ID.append(id)
posted @ 2021-06-29 18:11  /**serenity*/  阅读(344)  评论(0)    收藏  举报