一个简单的下载网页上图片的程序

最新推荐文章于 2017-09-23 22:25:00 发布

RITIAN_Jan

最新推荐文章于 2017-09-23 22:25:00 发布

阅读量691

点赞数

分类专栏： python学习文章标签： python 学习 python3 应用

本文链接：https://blog.csdn.net/xuxotot/article/details/49703635

版权

python学习专栏收录该内容

9 篇文章 0 订阅

订阅专栏

<pre name="code" class="python">import urllib.request as    urllib
from html.parser import HTMLParser
import zipfile
from random import sample
class MyHTMLParser(HTMLParser):                                              # 创建HTML解析类    
            def __init__(self):    
                    HTMLParser.__init__(self)    
                    self.gifs = []                                                          # 创建列表，保存gif    
                    self.jpgs = []                                                          # 创建列表，保存jpg    
            def handle_starttag(self, tags, attrs):# 处理起始标记
                    if tags == 'img' or tags == 'input':                       # 处理图片
                            
                            for attr in attrs:
                                    
                                    for t in attr:
                                        if t:
                                            
                                            if 'gif' in t:    
                                                    self.gifs.append(t)        # 添加到gif列表    
                                            elif 'jpg' in t:    
                                                    self.jpgs.append(t)         # 添加到jpg列表    
                                            else:    
                                                    pass

            def get_gifs(self):                                                             # 返回gif列表    
                    return self.gifs    
            def get_jpgs(self):                                                             # 返回jpg列表    
                    return self.jpgs  
url = input('请输入url:')
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) '}
req = urllib.Request(url=url, headers=headers)
page = urllib.urlopen(req)
data = page.read()
pathname = 'd:\im\age\'.join(sample('asdfghjklqwyeiuzxc,mb',3))
parser = MyHTMLParser()
parser.feed(data.decode('gbk'))
gifs = parser.get_gifs()
jpgs = parser.get_jpgs()
i=1
z=zipfile.ZipFile(r'%simage.zip'%pathname,'a')
all_img=len(gifs)+len(jpgs)


for gif in gifs:
    req = urllib.Request(url=gif, headers=headers)
    conn = urllib.urlopen(req)  
    f = open(r'%s%i.gif'%(pathname,i),'wb')
    bs = 1024*8
    print('下载开始   %d/%d'%(i,all_img))
    while True:
        block=conn.read(bs)
        if not block:
                 break
        f.write(block)
    z.write(r'%s%i.gif'%(pathname,i))
    i+=1
    conn.close()
    f.close()

for jpg in jpgs:
    req = urllib.Request(url=jpg, headers=headers)
    conn = urllib.urlopen(req)  
    f = open(r'%s%i.jpg'%(pathname,i),'wb')
    bs = 1024*8
    print('下载开始   %d/%d'%(i,all_img))
    while True:
        block=conn.read(bs)
        if not block:
                 break
        f.write(block)
    z.write(r'%s%i.jpg'%(pathname,i))
    i+=1
    conn.close()
    f.close()