第一個小爬蟲--爬取圖片並儲存
阿新 • • 發佈:2019-01-08
import urllib.request import re import os def url_open(url): req=urllib.request.Request(url) req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36') response=urllib.request.urlopen(url) html=response.read().decode('utf-8') return html def get_img(html): p=r'<img src="([^"]+\.jpg)"' imglist=re.findall(p,html) ''' for each in imglist: print (each) ''' for each in imglist: filename=each.split("/")[-1] urllib.request.urlretrieve(each,filename,None) if __name__=='__main__': os.mkdir("E:\Pict") os.chdir("E:\Pict") url='https://www.zhihu.com/question/40007169' get_img(url_open(url))