python 图片爬取

import urllib.request
import re
import random
import urllib.error

uapools=[
    'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)',
    'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
    'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)',
    'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)',
    '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)',
    'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)',
    'User-Agent:Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
]
def ua(uapools):
    thisua=random.choice(uapools)
    #print(thisua)
    headers=('User-Agent',thisua)
    opn=urllib.request.build_opener()
    opn.addheaders=[headers]
    urllib.request.install_opener(opn)
keyname='手套'
key=urllib.request.quote(keyname)
for i in  range(0,20):
    url='https://s.taobao.com/search?q='+key+'&s='+str(i*44)
    ua(uapools)
    data=urllib.request.urlopen(url).read().decode('utf-8','ignore')
    pat='"pic_url":"(.*?)"'
    data_list=re.compile(pat).findall(data)
    for j in range(len(data_list)):
        try:
            img_addr='http:'+data_list[j]
            #print(img_addr)
            img_name='d:\\data\\taobao1\\'+str(i+1)+str(j)+'.jpg'
            urllib.request.urlretrieve(img_addr,filename=img_name)
        except urllib.error.URLError  as err:
            if hasattr(err, "code"):
                print(err.code)
            if hasattr(err, "reason"):
                print(err.reason)

转载于:https://www.cnblogs.com/xiesongyou/p/7886833.html