爬取小说龙族5

"""

姓名 ：赵康乐

职业 ：学生

任务 ：爬取小说龙族5并保存

日期 ：2022-2-3

"""

import requests
from bs4 import BeautifulSoup

url = "https://www.75xs.cc/book/longzuV/"
headers = {
    "User-Agent":
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:96.0) Gecko/20100101 Firefox/96.0"
}
response = requests.get(url=url, headers=headers).text.encode("iso-8859-1")
# print(response)
soup = BeautifulSoup(response, "lxml")
list = soup.find("div", class_="m-book-list")
# print(list)
lis = list.find_all("li", class_="line3")
for li in lis:
    title = li.a.text
    new_url = "https://www.75xs.cc" + li.a["href"]
    resp = requests.get(new_url,headers=headers).text.encode("iso-8859-1")
    new_soup = BeautifulSoup(resp,"lxml")
    con = new_soup.find("div",class_="content")
    content = con.text
    with open("D:\桌面\龙族5.txt",mode="a",encoding="utf-8") as fp:
        fp.write(title)
        fp.write(content)
    print(title+"下载完成")

标签：龙族,soup,url,list,li,爬取,headers,new,小说
来源： https://www.cnblogs.com/zhaokangle/p/15861816.html