下载python标准库--python

 #coding:utf-8
 import urllib2
 import os,sys
 from BeautifulSoup import BeautifulSoup          # For processing HTML
 from bs4 import BeautifulSoup
 class BookSave():
     '''
     dir:html文件保存目录  url：index.html目录 static_url:js、css所在目录的上级目录
     distinguish:用来区分相同tag.name   dis_key:所需的tag属性  key1:所取tag
     key2:tag属性   key3:tag属性值
     '''
     def __init__(self,dir,url,static_url,distinguish,dis_key,key1,key2,key3):
         self.dir=dir
         self.url = url
         self.static_url = static_url
         self.distinguish = distinguish
         self.dis_key = dis_key
         self.key1 = key1
         self.key2 = key2
         self.key3 = key3

     def AddUrl(self):
         if self.dir != '':
             list = os.listdir(self.dir)  #列出目录下的所有文件和目录
             for line in list:
                 if os.path.isdir(line):
                     continue
                 elif os.path:
                     self.JieXiCsss(line)
                     self.JieXiJs(line)

     def JieXiCsss(self,file):
         filePath = os.path.join(self.dir,file)
         print filePath
         fp = open(filePath)
         soup = BeautifulSoup(fp)
         head = soup.head
         tags = head.findAll('link')#,{'rel':'stylesheet'}
         if tags != []:
             for item in tags:
                 try:
                     item['href'] = self.static_url + item['href']
                     print item['href']
                 except KeyError:
                     continue
         else :
             print tags,filePath
         self.SaveHtml(soup,filePath)

     def JieXiJs(self,file):
         filePath = os.path.join(self.dir,file)
         fp = open(filePath)
         soup = BeautifulSoup(fp)
         head = soup.head
         tags = head.findAll('script')#,{'rel':'stylesheet'}
         if tags != []:
             for item in tags:
                 try:
                     item['src'] = self.static_url + item['src']
                     print item['src']
                     self.SaveHtml(soup,filePath)
                 except KeyError:
                     continue
         else :
             print tags,filePath
         self.SaveFile(soup,filePath)

     def SaveFile(self,soup,file):
         html = str(soup)
         with open(file,'wb') as code:
             code.write(html)

     def IsNullArr(self,Arr):
         if Arr != []:
             return Arr
         else:
             print 'array is null'

     def DownLoadHtml(self,arr):
         tags = bs.IsNullArr(arr)
         for item in tags:
             liName = item.parent.name
             if any(liName in s for s in self.distinguish):
                 continue
             else:
                 htmlUrl = self.url + item[self.dis_key]
                 print htmlUrl
                 fileName = os.path.join(self.dir,item[self.dis_key])
                 print 'saving:' + htmlUrl
                 self.SaveHtml(fileName,htmlUrl)

     def SaveHtml(self,fileName,htmlUrl):
         f = urllib2.urlopen(htmlUrl)
         html = f.read()
         with open(fileName,"wb") as code:
             code.write(html)#.decode('utf-8')

     def GetSearchResult(self):
         doc = urllib2.urlopen(self.url)
         soup = BeautifulSoup(doc)
         soup.originalEncoding
         tag = soup.findAll(self.key1,{self.key2:self.key3})
         return tag

     def SplitString(self,source,sep):
         return source.strip().split('/')

     def CreateDir(self):
         if not os.path.exists(self.dir):
             os.makedirs(os.path.join(self.dir))
 if __name__=='__main__':
     urls = 'http://docs.python.org/2/library/'
     static_url = 'http://docs.python.org/2/'
     dirs = 'E:/demo/PythonLib1/'
     bs = BookSave(dirs,urls,static_url,'p','href','a','class','reference internal')
     bs.CreateDir()
     fileName = os.path.join(dirs,'index.html')
     htmlUrl = urls + 'index.html'
     bs.SaveHtml(fileName,htmlUrl)
     tags = bs.GetSearchResult()
     #print tags
     bs.DownLoadHtml(tags)
     bs.AddUrl()