爬虫实例——html、img保存

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)
		img_href = html.xpath('//*/ul[@class="article-related-img clearfix"]/li/a/img/@src')
		img_url = img_href[0]
		print(img_url)
		img = requests.get(img_url, headers=headers)
		img = img.content
		
		# img 图片写入文件
		output_img_path = './zh-' + img_href[0].split('/')[-1]
		with open(output_img_path, 'wb') as f_img:
		    f_img.write(img)
         
         
if __name__=='__main__':           
	D = Download()
	data = D.html_data()
	D.download_html(data)
	D.download_img(data)

向utl发起请求，读html网页两种方法：

• import urllib.request
  r = urllib.request.urlopen(url)
  r = r.read()

• import requests
  r = requests.get(url, headers=headers)
  r = r.content