故宫博物馆爬虫基础代码后续总代码 基础代码 import requests,re,time from lxml import etree url = r'https://img.dpm.org.cn/Public/static/CCP/index.html' base_url = r'https://img.dpm.org.cn/Public/static/CCP/' def getHtml(url):#获取网页源代码 header = {'User-Agent': 'Mozilla/5