python爬虫 -- 抓取网页中链接的静态图片

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

#http://tieba.baidu.com/p/2460150866
#抓取图片地址

from bs4 import BeautifulSoup
import urllib.request
from time import sleep

html_doc = "http://tieba.baidu.com/p/2460150866"

def get_image(url):
req = urllib.request.Request(url)
webpage = urllib.request.urlopen(req)

html = webpage.read()
soup = BeautifulSoup(html, 'html.parser')

#抓取图片地址
#抓取img标签且class为BDE_Image的所有内容
img_src=soup.findAll("img",{'class':'BDE_Image'})
i = 1
for img in img_src:
img_url = img.get('src')   #抓取src
#    print(img)
req = urllib.request.Request(img_url)
u = urllib.request.urlopen(req)
data = u.read()
with open("AutoCodePng20180119-"+str(i)+".jpg", 'wb') as f:
sleep(2)
f.write(data)
i += 1

def getImg(url):
html = urllib.request(url)
page = html.read()
soup = BeautifulSoup(page, "html.parser")
imglist = soup.find_all('img')  #发现html中带img标签的数据，输出格式为<img xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx，存入集合
lenth = len(imglist)  #计算集合的个数
for i in range(lenth):
print imglist[i].attrs['src']  #抓取img中属性为src的信息,例如<img src="123456" xxxxxxxxxxxxxxxx,则输出为123456