代码实例 | 使用python、xpath解析爬取html网页内容、img网页图片

爬虫实例，整个网页保存为本地文档，图片下载保存为本地图片

import requests
import random
from lxml import etree
import urllib.request


class Download:
	def html_data(self):
		"""获取目标 url 内容
		"""
		url = "http://military.china.com/weapon/aircraft/zdj/130002600/20190724/10390.html" 
		USER_AGENT = "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)"
		headers = {'User-Agent': USER_AGENT}
		r = requests.get(url, headers=headers)
		data = r.content
		return data
    
    def download_html(self, data):
		"""html页面写入文件，存为.html格式文档
		"""
		output_html_path = './zh.html'
		with open(output_html_path, 'wb') as f_html:
		    f_html.write(data)
		    
    def download_img(self, data):
		"""解析img-url, 保存图片
		"""
		html = etree.HTML(data)