##目标

爬取美图天空的图片，并自动下载至本地

##环境

Python3.4+BeautifulSoup

##步骤

  1. 首先打开http://www.tootk.net/tupian/bizhi/分析网页内容 QQ20150718-2@2x

  2. class="w170img"为每一条内容

  3. 里面的img内的src、alt分别为图片链接和名字

  4. 有了这两样就可以把图片下载下来了

##代码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
#   语言：Python 3.4

import urllib.request
import bs4,os

page_sum = 10  #设置下载页数

path = os.getcwd()
path = os.path.join(path,'images')
if not os.path.exists(path):
    os.mkdir(path)                                  #创建文件夹
url = "http://www.tootk.net"     #url地址
headers = {                                         #伪装浏览器
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko)'
                 ' Chrome/32.0.1700.76 Safari/537.36'
}

for count in range(page_sum):
    req = urllib.request.Request(
        url = url+"/tupian/bizhi/list_13_"+str(count+1)+".html",
        headers = headers
    )#url拼接
    print(req.full_url)
    content = urllib.request.urlopen(req).read()

    soup = bs4.BeautifulSoup(content,"html5lib")                   # BeautifulSoup 获取网页内容

    liResult = (soup.find_all("div", attrs={"class": "w170img"}))

    for content in liResult:
        image = content.img#遍历img
    
        lplink = image.get('src')#获取图片链接
        title = image.get('alt')#获取图片名称
        link = url+lplink.replace("-lp","")#转换高清图片链接
        filename = path + os.sep + title + ".jpg"#本地存储目录

        print(link)

        urllib.request.urlretrieve(link,filename) #存储

参考链接：