Python下载网页图片

#coding:utf-8
import requests
from bs4 import BeautifulSoup
import re
DownPath = "/jiaoben/python/meizitu/pic/"
import urllib
head = {‘User-Agent‘:‘Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6‘}
TimeOut = 5
PhotoName = 0
c = ‘.jpeg‘
PWD="/jiaoben/python/meizitu/pic/"
for x in range(1,4):
  site = "http://www.meizitu.com/a/qingchun_3_%d.html" %x
  Page = requests.session().get(site,headers=head,timeout=TimeOut)
  Coding =  (Page.encoding)
  Content = Page.content#.decode(Coding).encode(‘utf-8‘)
  ContentSoup = BeautifulSoup(Content)
  jpg = ContentSoup.find_all(‘img‘,{‘class‘:‘scrollLoading‘})
  for photo in jpg:
    PhotoAdd = photo.get(‘data-original‘)
    PhotoName +=1
    Name =  (str(PhotoName)+c)
    r = requests.get(PhotoAdd,stream=True)
    with open(PWD+Name, ‘wb‘) as fd:
        for chunk in r.iter_content():
                fd.write(chunk)
print ("You have down %d photos" %PhotoName)

# -*- coding:utf-8 -*-
import urllib.request
path = "D:\\Download"
url = "http://pic2.sc.chinaz.com/files/pic/pic9/201309/apic520.jpg"
name ="D:\\download\\1.jpg"
#保存文件时候注意类型要匹配，如要保存的图片为jpg，则打开的文件的名称必须是jpg格式，否则会产生无效图片
conn = urllib.request.urlopen(url)
f = open(name,‘wb‘)
f.write(conn.read())
f.close()
print(‘Pic Saved!‘)   

很简单，打开个url链接，然后save到某个文件夹下就可以了。

有时候不如不想输入路径，那就需要用os模块来修改当前路径

os.chdir("D:\\download")
os.getcwd()  

这样保存的文件就只需要名字就可以了

f = open(‘1.jpg‘,‘wb‘)

这上面的url是给定的，只能下载一张图片，如果要是批量下载，就需要用循环来判断不同的url，

下面是从其他地方看到的一个例子，就是把图片url中的图片名字修改，然后就可以循环保存了，不过也是先确定了某个url

来源：http://www.oschina.net/code/snippet_1016509_21961 开源中国社区，自己修改的地方是提出了相同代码def了个函数

import os
import urllib.request
def rename(name):
    if len(name) == 2:
        name = ‘0‘ + name + ‘.jpg‘
    elif len(name) == 1:
        name = ‘00‘ + name + ‘.jpg‘
    else:
        name = name + ‘.jpg‘
    return name  

os.chdir("D:\\download")
os.getcwd()
count = 1
name=str(count)
name = rename(name)
print(name)
url = ‘http://bgimg1.meimei22.com/list/2012-5-24/2/sa‘ + name
while count < 15:
    a = urllib.request.urlopen(url)
    f = open(name, "wb")
    f.write(a.read())
    f.close()
    print(url + ‘ Saved!‘)
    count = count + 1
    name=str(count)
    name = rename(name)
    print(name)
    url = ‘http://bgimg1.meimei22.com/list/2012-5-24/2/sa‘ + name
    try:
        a = urllib.request.urlopen(url)
        pass
    except (Exception) as e:
        print(e)
    else:
        pass
else:
    print(url + ‘ not found‘)

当然也可以自己建立http连接，然后动态获取.jpg的图片

url = "desk.zol.com.cn"
conn = http.client.HTTPConnection(url)
conn.request("GET", "/dongman/")
r = conn.getresponse()
print (r.status, r.reason)
data1 = r.read()#.decode(‘utf-8‘) #编码根据实际情况酌情处理

开始时候写的老是提示目标计算机主动拒绝， 后来才发现我选的函数是HTTPSConnection() ，当然会被拒绝了，这一点应该注意，要选择HTTPConnection()