#encoding:utf-8 import urllib from lxml import etree import requests def Schedule(blocknum,blocksize,totalsize): ''' :param blocknum: 已经下载的数据块 :param blocksize: 数据块大小 :param totalsize: 远程文件大小 :return: ''' per = 100.0*blocknum*blocksize/totalsize if per>100: per = 100 print('当前下载进度:%d'%per) user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)' headers = {'User-Agent':user_agent} r = requests.get('http://www.ivsky.com/tupian/jita_renwu_v47051/',headers=headers) #使用lxml解析网页 html = etree.HTML(r.text) img_urls = html.xpath('.//img/@src')#先找到所用的img i=0 for img_url in img_urls: urllib.urlretrieve(img_url,'img'+str(i)+'.jpg',Schedule) i+=1
Python下载网页图片存储到本地
最新推荐文章于 2024-06-28 05:54:53 发布