'''
思路: 从缩略图页面开始爬取
1) 先爬取所有缩略图的a标签
2)
3)
'''
import requests
from bs4 import BeautifulSoup
import os
if not os.path.exists("男神图集"):
os.makedirs("男神图集")
import lxml
from urllib import request
url = "http://www.shuaia.net/index_50.html"
if __name__ == '__main__':
for i in range(5):
url = "http://www.shuaia.net/index_5%d.html"%i
req = requests.get(url = url)
req.encoding = 'utf-8'
print("响应码: ", req.status_code)
html = req.text
bf2 = BeautifulSoup(html, 'lxml')
a_list = bf2.find_all("a", class_="itemimg-view")
for item in a_list:
print (item)
#print(item.get('href'), item.get("title"))
name = item.get("title")
down_url = "http://www.shuaia.net" + item.get("href")
#下载
request.urlretrieve(filename="男神图集/%s.jpg" %name, url = down_url)
print("%s下载成功"%name + '>'*10)
Python爬取图片并存储
猜你喜欢
转载自blog.csdn.net/AK47red/article/details/103777322
今日推荐
周排行