标签：headers python url bs4 import div 小说 requests 下载
# https://url/kan/45458/1.html
import time
from asyncio import threads
# 1.单章节下载url.bq02.cc
# 2.数据解析（静态数据 xpath re正则 bs4 css）
from bs4 import BeautifulSoup
#
# 请求url 数据类型 字符串
import threading
import requests
from bs4 import BeautifulSoup
def getbook(i):
# 这是有20个活
# for i in range(1,21):
book_url = requests.get(f"url/{i}.html")
headers = {
'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36'
}
# 静态提取页面数据 动态用点json
# respuest = requests.get(url = book_url.url,headers=headers).text
respuest = requests.get(url=book_url.url).text
# 数据解析 bs4解析
soup = BeautifulSoup(respuest, 'html.parser')
# div_element = soup.find('div', attrs={'class': 'kan'})
div_element = (soup.find('div',id='
标签：headers,
python,
url,
bs4,
import,
div,
小说,
requests,
下载
From： https://blog.csdn.net/qq_30863945/article/details/145192622