# coding=utf-8

# __author__ = 'zhouyin'

import urllib

import time

'''

============================把网页下载到本地，然后通过url作为文件名=====================================================

str0 = '地震思考录'

title = str0.find(r'

print title

href = str0.find(r'href=')

print href

html = str0.find(r'.html')

print html

url = str0[href+6:html+5]

print url

filename = url[-26:]

content = urllib.urlopen(url).read()

# print content

open(filename, 'w').write(content)  #

把网页下载到本地，然后通过url作为文件名

====================================================================================================================

'''

'''

==============================================================================================

con =

urllib.urlopen('http://blog.sina.com.cn/s/articlelist_1191258123_0_1.html').read()

# 访问韩寒博客首页博文地址

title = con.find(r'

print html

url = con[href+6:html+5]  #

因为你是从href开始搜索的，所以你不需要href=的字符，而.html则需要，所以尾要+5

# print con

print url

========================================================================================

'''

'''

=====================================把韩寒博客的某一页的50篇文章下载到本地===========================================================================

url = [''] * 50  # 存储40个url的列表

con =

urllib.urlopen('http://blog.sina.com.cn/s/articlelist_1191258123_0_1.html').read()

# 访问韩寒博客首页博文地址

print con

title = con.find(r'

url[0] = con[href + 6:html + 5]

i = 0

while title != -1 and href != -1 and html != -1 and i <

50:

url[i] = con[href +

6:html + 5]

print url[i]

title =

con.find(r'

i = i + 1

else:

print 'findall!'

j = 0

while j < 50:

content =

urllib.urlopen(url[j]).read()

open(r'hanhan/'+url[j][-26:], 'w+').write(content)

print 'downing....',

url[j]

j = j + 1

time.sleep(15)

else:

print 'download all

pages!'

========================================================================================================================

'''

'''

=======================================把韩寒的博客的7个页面的所有文章下载=================================================================================

url = [''] * 350  # 存储40个url的列表

page = 1

link = 1

while page <= 7:

con =

urllib.urlopen('http://blog.sina.com.cn/s/articlelist_1191258123_0_'+str(page)+'.html').read()

# 访问韩寒博客首页博文地址

# print con

title =

con.find(r'

url[0] = con[href +

6:html + 5]

i = 0

while title != -1 and

href != -1 and html != -1 and i < 350:

url[i] = con[href + 6:html + 5]

print url[i]

title = con.find(r'

i = i + 1

else:

print 'findall!'

page = page + 1

link = link + 1

j = 0

while j < 50:

content =

urllib.urlopen(url[j]).read()

open(r'hanhan/'+url[j][-26:], 'w+').write(content)

print 'downing....',

url[j]

j = j + 1

time.sleep(15)

else:

print 'download all

pages!'

========================================================================================================================

'''