爬虫

兴趣是最好的导师。
看中一个免费的美漫网站，但是被墙起来了，除了校门不能看
打算把上面的图片爬下来。

# -*- coding: utf-8 -*-
import urllib2

from bs4 import BeautifulSoup

import socket



baseurl = "http://www.readcomics.tv/loki-agent-of-asgard/chapter-1/full"

#伪装浏览器,以免被封

def user_agent(url):

    req_header = {'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'}

    req_timeout = 20

    try:

        req = urllib2.Request(url,None,req_header)

        page = urllib2.urlopen(req,None,req_timeout)

        html = page

    except urllib2.URLError as e:

        print e.message

    except socket.timeout as e:

        user_agent(url)

    return html



def page_loop(pageid):

    url = baseurl+'?p=%s'%pageid

    print url

    page = user_agent(url)

    soup = BeautifulSoup(page)

    total_img = 0

    img = soup.find_all(['img'])

    for myimg in img:

        link = myimg.get('src')

        total_img += 1

        print link

      #  content2 = urllib2.urlopen(link).read()

        content2 = user_agent(link).read()

        #这句代码直接从OSC上面弄下来的

        #D:\myimg是保存路径,你可以自己改成自己的,但是路径必须要自己创建好

        with open(u'ImageDownload'+'/'+link[link.rfind('/'):],'wb') as code:

            code.write(content2)

    print total_img

    return total_img

page_start = 0

page_stop = 4

total = 0

for i in range(page_start,page_stop):

    total+=page_loop(i)



print total

#total就是统计下总共保存到本地的图片数量

不是很完善，问题如下：
1.没有生成文件夹
2.保存的文件名称不合规范

reference：

http://blog.csdn.net/cruise_h/article/details/25737737

https://www.lylinux.org/python%E7%88%AC%E8%99%AB%E6%8A%93%E5%8F%96%E7%BD%91%E7%AB%99%E5%9B%BE%E7%89%87%E5%B9%B6%E4%BF%9D%E5%AD%98.html