需要事先安装好BeautifulSoup,官网:https://www.crummy.com/software/BeautifulSoup/bs4/doc/index.zh.html
抓取地址:http://tieba.baidu.com/p/2772656630
代码
#-*- coding:utf-8 -*-
import urllib
from bs4 import BeautifulSoup
def get_content(url):
html = urllib.urlopen(url)
content = html.read()
html.close()
return content
def get_images(content):
oSoup = BeautifulSoup(content)
all_images = oSoup.find_all('img', class_="BDE_Image")
x = 1
for img in all_images:
print img['src']
image_name = "%s.jpg" % x
urllib.urlretrieve(img['src'], image_name)
x+=1
url = "http://tieba.baidu.com/p/2772656630"
content = get_content(url)
get_images(content)