import requests

import sys,re

#设置提取图片url 的正则表达式

imgre = re.compile(r"

#存放找到的 图片url的列表

all_img_urls = []

#图片下载后存放位置

save_path = r‘/root‘

#获取指定网页中的图片url

def get_img_url(tmpurl,tmpre,allimgurl,timeout=10):

headers = {‘User-Agent‘: ‘Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36‘}

link = requests.get(tmpurl,headers=headers,timeout = timeout)

content = link.text

retsults = tmpre.findall(content)

for i in retsults:

allimgurl.append(i)

#对图片url进行下载保存

def save_img(tmpurl,tmppath,timeout=10):

headers = {‘User-Agent‘: ‘Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36‘}

ret = requests.get(tmpurl,headers=headers,timeout=timeout)

img = ret.content

filename = ‘{}/{}‘.format(tmppath,tmpurl.split(‘/‘)[-1])

with open(filename,‘wb‘) as f:

f.write(img)

if name == ‘main‘:

urls = [‘http://www.ivsky.com/bizhi/death_note_v17111/pic_{}.html#al_tit‘.format(385791+x) for x in range(10)]

try:

for url in urls:

imgurls = get_img_url(url, imgre, all_img_urls)

except Exception as e:

print(e)

for img in all_img_urls:

try:

save_img(img,save_path)

except Exception as e:

print(e)

原文：http://blog.51cto.com/13308811/2060142