Source Code for Module httxlib.httxrequest

  1  #!/usr/bin/env python 
  2  # -*- coding: latin-1; py-indent-offset:4 -*- 
  3  ################################################################################ 
  4  #  
  5  # This file is part of HttxLib 
  6  # 
  7  # HttxLib is an HTTP(s) Python library suited multithreaded/multidomain 
  8  # applications 
  9  # 
 10  # Copyright (C) 2010-2011 Daniel Rodriguez (aka Daniel Rodriksson) 
 11  # Copyright (C) 2011 Sensible Odds Ltd 
 12  # 
 13  # You can learn more and contact the author at: 
 14  # 
 15  #    http://code.google.com/p/httxlib/ 
 16  # 
 17  # HttxLib is free software: you can redistribute it and/or modify 
 18  # it under the terms of the GNU General Public License as published by 
 19  # the Free Software Foundation, either version 3 of the License, or 
 20  # (at your option) any later version. 
 21  # 
 22  # HttxLib is distributed in the hope that it will be useful, 
 23  # but WITHOUT ANY WARRANTY; without even the implied warranty of 
 24  # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the 
 25  # GNU General Public License for more details. 
 26  # 
 27  # You should have received a copy of the GNU General Public License 
 28  # along with HttxLib. If not, see <http://www.gnu.org/licenses/>. 
 29  # 
 30  ################################################################################ 
 31  ''' 
 32  urllib2 compatible Request object with additional functionality 
 33   
 34  It can therefore be supplied to urllib2 objects (like a CookieJar) 
 35  ''' 
 36   
 37  from urllib2 import Request 
 38  from urlparse import urlparse, urlsplit 
 39   
 40   
 41 -class HttxRequest(Request): 
 42      ''' 
 43      A subclass of urllib2 Request to retain compatibility and make it usable 
 44      for cookies and whatever may be needed 
 45   
 46      @ivar parsed: It holds the result of the urlsplit(url) done in the constructor 
 47                    for practical purposes 
 48      @type parsed: namedtuple result of urlsplit (check the Python docs) 
 49      ''' 
 50   
 51 -    def __init__(self, url, data=None, headers=None, origin_req_host=None, unverifiable=False): 
 52          ''' 
 53          Constructor. It delegates construction to the base class 
 54          Request and initializes the member variables 
 55   
 56          It performs an additional call of Request.get_type and Request.get_host 
 57          to ensure that the Request object is properly initialized. Because this 
 58          is done by the urllib2 library, but we are just using the request 
 59   
 60          @param url: url to be requested in the HTTP request 
 61          @type url: str 
 62          @param data: data for the HTTP request body (which enforces a POST) 
 63          @type data: str 
 64          @param headers: dictionary of header name/header value 
 65          @type headers: dict 
 66          @param origin_req_host: request host of the origin transaction as per 
 67                                  RFC 2965 - Host name or IP address of the host 
 68          @type origin_req_host: str 
 69          @param unverifiable: if the request was not verified/requested by the end 
 70                               user and it is rather automatic (redirection, download 
 71                               of a picture inside a web page) - RFC 2965 
 72          @type unverifiable: bool 
 73          ''' 
 74          if headers is None: 
 75              headers = dict() 
 76          Request.__init__(self, url, data, headers, origin_req_host, unverifiable) 
 77          self.parsed = urlsplit(url) 
 78          # Done to force split of the url fields inside the request 
 79          self.get_type() 
 80          self.get_host() 
 81   
 82   
 83      @property 
 84 -    def allheaders(self): 
 85          ''' 
 86          Property to return all the headers to be sent in a request 
 87   
 88          urllib2 distinguishes amongst normal headers and headers that will 
 89          not be used if the original request is redirected 
 90   
 91          Therefore it is impossible to request all headers in just one call 
 92   
 93          Although Request has a utility function, it returns a list of tuples 
 94          rather than a dictionary 
 95   
 96          This property returns a dictionary 
 97          ''' 
 98          hdrs = self.unredirected_hdrs.copy() 
 99          hdrs.update(self.headers) 
100          return hdrs 
101   
102   
103      @property 
104 -    def method(self): 
105          ''' 
106          Property to have a handy alias for Request.get_method 
107          ''' 
108          return self.get_method() 
109   
110   
111 -    def ispost(self): 
112          ''' 
113          Utility function to avoid cluttering external code with 
114          string comparisons 
115   
116          @return: if the request will be a POST request 
117          @rtype: bool 
118          ''' 
119          return self.get_method() == 'POST' 
120   
121   
122 -    def isget(self): 
123          ''' 
124          Utility function to avoid cluttering external code with 
125          string comparisons 
126   
127          @return: if the request will be a GET request 
128          @rtype: bool 
129          ''' 
130          return self.get_method() == 'GET' 
131   
132   
133      @property 
134 -    def scheme(self): 
135          ''' 
136          Property to have a handy alias for Request.get_type or 
137          parsed.scheme 
138          ''' 
139          # return self.get_type() 
140          return self.parsed.scheme 
141   
142   
143      @property 
144 -    def netloc(self): 
145          ''' 
146          Property to have a handy alias for Request.get_host or 
147          parsed.netloc 
148          ''' 
149          # return self.get_host() 
150          return self.parsed.netloc 
151   
152   
153      @property 
154 -    def body(self): 
155          ''' 
156          Property to have a handy alias for Request.get_data 
157          ''' 
158          return self.get_data() 
159   
160   
161 -    def clone(self, url=None): 
162          ''' 
163          Clone a request with a change of url to support redirection 
164   
165          By using the normal/unredirected header separation in Request it is 
166          easy to clone for a redirection by only supplying the new headers 
167          to the class 
168   
169          @param url: url to redirect to if needed. Default of None for no 
170                      redirection 
171          @type url: str|None 
172          @return: a cloned object 
173          @rtype: L{HttxRequest} 
174          ''' 
175   
176          # The only non-cloned thing: unredirected_headers and this is possibly how it has to be 
177          if not url: 
178              url = self.get_full_url() 
179              headers = self.allheaders 
180          else: 
181              headers = self.headers 
182   
183          return self.__class__(url, self.data, headers, self.origin_req_host, self.unverifiable) 
184   
185   
186 -    def __deepcopy__(self, memo): 
187          ''' 
188          Deepcopy support. 
189   
190          @param memo: standard __deepcopy__ parameter to avoid circular references 
191          @type memo: dict 
192          @return: a cloned object 
193          @rtype: L{HttxRequest} 
194          ''' 
195          return self.clone() 
196