11.9. 全部放在一起

你已经看到了构造一个智能的 HTTP web 客户端的所有片断。现在让我们看看如何将它们整合到一起。

例 11.17. openanything 函数

这个函数定义在 openanything.py 中。

 def openAnything(source, etag=None, lastmodified=None, agent=USER_AGENT):
    # non-HTTP code omitted for brevity
    if urlparse.urlparse(source)[0] == 'http':                                       
        # open URL with urllib2 
        request = urllib2.Request(source)                                           
        request.add_header('User-Agent', agent)                                      
        if etag:                                                                    
            request.add_header('If-None-Match', etag)                                
        if lastmodified:                                                            
            request.add_header('If-Modified-Since', lastmodified)                    
        request.add_header('Accept-encoding', 'gzip')                                
        opener = urllib2.build_opener(SmartRedirectHandler(), DefaultErrorHandler()) 
        return opener.open(request)

例 11.18. fetch 函数

这个函数定义在 openanything.py 中。

 def fetch(source, etag=None, last_modified=None, agent=USER_AGENT):  
    '''Fetch data and metadata from a URL, file, stream, or string'''
    result = {}                                                      
    f = openAnything(source, etag, last_modified, agent)              
    result['data'] = f.read()                                         
    if hasattr(f, 'headers'):                                        
        # save ETag, if the server sent one 
        result['etag'] = f.headers.get('ETag')                        
        # save Last-Modified header, if the server sent one 
        result['lastmodified'] = f.headers.get('Last-Modified')       
        if f.headers.get('content-encoding', '') == 'gzip':           
            # data came back gzip-compressed, decompress it 
            result['data'] = gzip.GzipFile(fileobj=StringIO(result['data']])).read()
    if hasattr(f, 'url'):                                             
        result['url'] = f.url                                        
        result['status'] = 200                                       
    if hasattr(f, 'status'):                                          
        result['status'] = f.status                                  
    f.close()                                                        
    return result

例 11.19. 使用 openanything.py

>>> import openanything
>>> useragent = 'MyHTTPWebServicesApp/1.0'
>>> url = 'http://diveintopython.org/redir/example301.xml'
>>> params = openanything.fetch(url, agent=useragent)              
>>> params                                                         
{'url': 'http://diveintomark.org/xml/atom.xml', 
'lastmodified': 'Thu, 15 Apr 2004 19:45:21 GMT', 
'etag': '"e842a-3e53-55d97640"', 
'status': 301,
'data': '<?xml version="1.0" encoding="iso-8859-1"?>
<feed version="0.3"
<-- rest of data omitted for brevity -->'}
>>> if params['status'] == 301:                                    
... url = params['url']
>>> newparams = openanything.fetch(
... url, params['etag'], params['lastmodified'], useragent)    
>>> newparams
{'url': 'http://diveintomark.org/xml/atom.xml', 
'lastmodified': None, 
'etag': '"e842a-3e53-55d97640"', 
'status': 304,
'data': ''}