下载cnblogs所有博客内容

import urllib,os,sys

def getUrlContent(url):
fp =urllib.urlopen(url)
cont =fp.read()
fp.close()
return cont

# to read blog urls in one page
class findBlog:
def __init__(self,cont):
self.p=0
self.cont =cont
def get(self):
p1 =self.cont.find('<div class="post">',self.p)
if p1>0:
p2 =self.cont.find('<h2><a id="homepage1_HomePageDays',p1)
if p2>0:
p3 =self.cont.find('href="',p2)
if p3>0:
p4 =self.cont.find('">',p3)
if p4>0:
url =self.cont[(p3+len('href="')):p4]
p5 =self.cont.find('</a>',p4)
if p5>0:
title =self.cont[(p4+len('">')):p5]
self.p =p5
return [url, title]
return None

def logFile(fname, cont):
if os.path.isfile(fname):
print fname, 'esist!'
#    return
fp=open(fname,'w')
fp.write(cont)
fp.close()

def appendFile(fname, cont):
fp=open(fname,'a')
fp.write(cont)
fp.close()

def MyCmd(x):
print x
os.system(x)

#to read all blog contents in all pages
class blogReader:
def __init__(self):
self.is_latest_written =0
self.latest_url =''

#update self.latest_url
fname ='cfg.txt'
if os.path.isfile(fname):
fp =open(fname,'r')
self.latest_url =fp.readline().strip()
fp.close()

print 'latest_url', self.latest_url
def readPage(self,pid):
is_latest =0
cont =getUrlContent('http://www.cnblogs.com/cutepig/default.html?page=%d&OnlyTitle=1'%pid)
fpLog =open('log.txt','a')
fb =findBlog(cont)
print >>fpLog, '--------page', pid
print '--------page', pid
while 1:
ret =fb.get()
if ret is None: break
[url, title] =ret
print >>fpLog, ret
#print ret    #why cannot print chinses?
if not self.is_latest_written:
logFile('cfg.txt', url)
self.is_latest_written =1

print title.decode('utf-8')

if url==self.latest_url:
is_latest =1
break

blogFname =url.replace(';','').replace('&','').replace('?','').replace(':','').replace('/','')+'.htm'
logFile( blogFname, getUrlContent(url))
appendFile( 'index2.htm', '<a href=%s>%s</a><br>\n'%(blogFname, title))

fpLog.close()
MyCmd('copy /y index2.htm+index.htm index.htm')
return is_latest

def read_all(self):
pid =1
while 1:
is_latest =self.readPage(pid)
if is_latest:
break
pid =pid+1

br =blogReader()
br.read_all()