python爬虫——BeautifulSoup 抓取图片

python 利用BeautifulSoup 抓取图片

# -*- coding: utf-8 -*-
"""

"""
import urllib
from bs4 import BeautifulSoup
#beautifulsoup方法，第三方库的方法，爬找网页 
## 下载网页
def get_content(url):
    '''
    @url:需要下载的网址
    下载网址
    '''
    html = urllib.request.urlopen(url)
    content = html.read().decode('utf-8')#转码
    html.close()#记得要将打开的网页关闭，否则会出现意想不到的问题
#    print (type(content))
    return content

def get_image(info):
    '''
    利用Soup第三方库实现抓取
    '''
    soup = BeautifulSoup(info,'html.parser')#设置解析器为“lxml”
    all_image = soup.find_all('img',class_ = "BDE_Image")
    x=1  
    for image in all_image:
        print(all_image)
        urllib.request.urlretrieve(image['src'],"E:\\WORK\\py\\TensorFlow\\爬取树叶图片\\BS-Soup\\%s.jpg"%(x))
        x+=1

url = "https://tieba.baidu.com/p/5114003992" 
info = get_content(url)  
#print (info) 
get_image(info)