import os
import urllib
import requests
#import wx
import time
from fake_useragent import UserAgent
from lxml import etree
from urllib import request
ua = UserAgent()
headers ={
‘user-agent‘: ua.random
}
opener=urllib.request.build_opener()
opener.addheaders=[(‘User-Agent‘,‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML,like Gecko) Chrome/36.0.1941.0 Safari/537.36‘)]
for i in range(2,7):
url = "https://www.fb532.com/tupian/list-清纯唯美-%d.html"%i
print(url)
#https://www.fb532.com/tupian/list-%E6%B8%85%E7%BA%AF%E5%94%AF%E7%BE%8E-3.html
#url = "https://www.128nm.com/"
response = requests.get(url,headers = headers)
print(url)
html = response.content.decode("utf-8")
content = etree.HTML(html)
li_list = content.xpath(‘//ul[@class="clearfix"]/li‘)
print(li_list)
print(len(li_list))
for li in li_list:
img_name = li.xpath(‘./a/@title‘)[0]
print(img_name)
img_url = li.xpath(‘./a/@data-original‘)[0]
# print("url:" + img_url)
print(img_name,img_url)
styles = img_url.split(".")
laststyle = styles[len(styles)-1]
print(img_url)
path = "imgs3"
if not os.path.exists(path):
os.mkdir(path)
filename = path + "/" + img_name + "."+laststyle
print(filename) urllib.request.install_opener(opener) urllib.request.urlretrieve(img_url,filename)
