import re import urllib.request -----1 def gethtml(url): page=urllib.request.urlopen(url) ------2 html=page.read() return html def getimg(html): reg = r'src="(.*?\.jpg)"' img=re.compile(reg) html=html.decode('utf-8')#python3 ---------3 imglist=re.findall(img,html) x = 0 for imgurl in imglist: urllib.request.urlretrieve(imgurl,'%s.jpg'%x) x = x+1 html=gethtml("http://news.ifeng.com/a/20161115/50258273_0.shtml") print(getimg(html))
上面標了1,2,3,的三個地方Python3.0及以上版本在學爬蟲是須要注意的, 若是沒有這代碼的話可能會出現如下狀況html
參考於> http://blog.csdn.net/lxh199603/article/details/53192883python