什么是图片爬虫:所谓图片爬虫,就是从互联网中自动把对方服务器上的图片爬下来的爬虫程序。
淘宝图片爬虫实战:
import urllib.request
import re
headers = ("user-agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36")
opener = urllib.request.build_opener()
opener.addheader = [headers]
urllib.request.install_opener(opener)
keyname = '连衣裙'
key = urllib.request.quote(keyname)
for i in range(1,3):
url = 'https://s.taobao.com/list?q='+key+'&cat=16&style=grid&seller_type=taobao&spm=a217f.8051907.1000187.1&bcoffset=0&s='+str(i*60)
data = urllib.request.urlopen(url).read().decode('utf-8','ignore')
pat = '"pic_url":"//(.*?)'
imglist = re.compile(pat).findall(data)
print(imglist)
for j in range(0,len(imglist)):
thisname = imglist[j]
thisurl = 'http://'+thisname
file = 'D:/spider/urllib_crawler/taobaoimg/'+str(i)+str(j)+'jpg'
data = urllib.request.urlretrieve(thisurl,file)