summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorMoshe Zadka <moshez@math.huji.ac.il>2001-03-01 08:40:42 (GMT)
committerMoshe Zadka <moshez@math.huji.ac.il>2001-03-01 08:40:42 (GMT)
commit8a18e99008c28156a7ba701ca8d6824a50fb0a9e (patch)
tree301cbec622d1abeaa992063babaaee5a6cfb540a
parent251083142fe4c114753cef12c37589bd55761912 (diff)
downloadcpython-8a18e99008c28156a7ba701ca8d6824a50fb0a9e.zip
cpython-8a18e99008c28156a7ba701ca8d6824a50fb0a9e.tar.gz
cpython-8a18e99008c28156a7ba701ca8d6824a50fb0a9e.tar.bz2
Checking in patch 404826 -- urllib2 enhancements and documentations.
(please not that the library reference does *not* include the urllib2 documnetation -- that will wiat for Fred)
-rw-r--r--Doc/lib/liburllib2.tex501
-rw-r--r--Lib/urllib2.py163
2 files changed, 616 insertions, 48 deletions
diff --git a/Doc/lib/liburllib2.tex b/Doc/lib/liburllib2.tex
new file mode 100644
index 0000000..90243a5
--- /dev/null
+++ b/Doc/lib/liburllib2.tex
@@ -0,0 +1,501 @@
+\section{\module{urllib2} ---
+ extensible library for opening URLs}
+
+\declaremodule{standard}{urllib2}
+
+\moduleauthor{Jeremy Hylton}{jhylton@users.sourceforge.net}
+\sectionauthor{Moshe Zadka}{moshez@users.sourceforge.net}
+
+\modulesynopsis{An extensible library for opening URLs using a variety of
+ protocols}
+
+The \module{urllib2} module defines functions and classes which help
+in opening URLs (mostly HTTP) in a complex world -- basic and digest
+authentication, redirections and more.
+
+The \module{urllib2} module defines the following functions:
+
+\begin{funcdesc}{urlopen}{url\optional{, data}}
+Open the url \var{url}, which can either a string or a \class{Request}
+object (currently the code checks that it really is a \class{Request}
+instance, or an instance of a subclass of \class{Request}.
+
+\var{data} should be a string, which specifies additional data to
+send to the server. In HTTP requests, which are the only ones that
+support \var{data}, it should be a buffer in the format of
+\code{application/x-www-form-urlencoded}, for example one returned
+from \function{urllib.urlencode}.
+
+This function returns a file-like object with two additional methods:
+
+\begin{itemize}
+
+ \item \code{geturl()} --- return the URL of the resource retrieved
+ \item \code{info()} --- return the meta-information of the page, as
+ a dictionary-like object
+\end{itemize}
+
+Raises \exception{URLError} on errors.
+\end{funcdesc}
+
+\begin{funcdesc}{install_opener}{opener}
+Install a \class{OpenerDirector} instance as the default opener.
+The code does not check for a real \class{OpenerDirector}, and any
+class with the appropriate interface will work.
+\end{funcdesc}
+
+\begin{funcdesc}{build_opener}{\optional{handler\optional{,
+ handler\optional{, ...}}}}
+Return an \class{OpenerDirector} instance, which chains the
+handlers in the order given. \var{handler}s can be either instances
+of \class{BaseHandler}, or subclasses of \class{BaseHandler} (in
+which case it must be possible to call the constructor without
+any parameters. Instances of the following classes will be in
+the front of the \var{handler}s, unless the \var{handler}s contain
+them, instances of them or subclasses of them:
+
+\code{ProxyHandler, UnknownHandler, HTTPHandler, HTTPDefaultErrorHandler,
+ HTTPRedirectHandler, FTPHandler, FileHandler}
+
+If the Python installation has SSL support (\code{socket.ssl} exists),
+\class{HTTPSHandler} will also be added.
+\end{funcdesc}
+
+\begin{excdesc}{URLError}
+The error handlers raise when they run into a problem. It is a subclass
+of \exception{IOError}.
+\end{excdesc}
+
+\begin{excdesc}{HTTPError}
+A subclass of \exception{URLError}, it can also function as a
+non-exceptional file-like return value (the same thing that \function{urlopen}
+returns). This is useful when handling exotic HTTP errors, such as
+requests for authentications.
+\end{excdesc}
+
+\begin{excdesc}{GopherError}
+A subclass of \exception{URLError}, this is the error raised by the
+Gopher handler.
+\end{excdesc}
+
+\begin{classdesc}{Request}{url\optional{data, \optional{, headers}}}
+This class is an abstraction of a URL request.
+
+\var{url} should be a string which is a valid URL. For descrtion
+of \var{data} see the \method{add_data} description.
+\var{headers} should be a dictionary, and will be treated as if
+\method{add_header} was called with each key and value as arguments.
+\end{classdesc}
+
+The following methods describe all of \class{Request}'s public interface,
+and so all must be overridden in subclasses.
+
+\begin{methoddesc}[Request]{add_data}{data}
+Set the \class{Request} data to \var{data} is ignored
+by all handlers except HTTP handlers --- and there it should be an
+\code{application/x-www-form-encoded} buffer, and will change the
+request to be \code{POST} rather then \code{GET}.
+\end{methoddesc}
+
+\begin{methoddesc}[Request]{has_data}{data}
+Return whether the instance has a non-\code{None} data.
+\end{methoddesc}
+
+\begin{methoddesc}[Request]{get_data}{data}
+Return the instance's data.
+\end{methoddesc}
+
+\begin{methoddesc}[Request]{add_header}{key, val}
+Add another header to the request. Headers
+are currently ignored by all handlers except HTTP handlers, where they
+are added to the list of headers sent to the server. Note that there
+cannot be more then one header with the same name, and later calls
+will overwrite previous calls in case the \var{key} collides. Currently,
+this is no loss of HTTP functionality, since all headers which have meaning
+when used more then once have a (header-specific) way of gaining the
+same functionality using only one header.
+\end{methoddesc}
+
+\begin{methoddesc}[Request]{get_full_url}{}
+Return the URL given in the constructor.
+\end{methoddesc}
+
+\begin{methoddesc}[Request]{get_type}{}
+Return the type of the URL --- also known as the schema.
+\end{methoddesc}
+
+\begin{methoddesc}[Request]{get_host}{}
+Return the host to which connection will be made.
+\end{methoddesc}
+
+\begin{methoddesc}[Request]{get_selector}{}
+Return the selector --- the part of the URL that is sent to
+the server.
+\end{methoddesc}
+
+\begin{methoddesc}[Request]{set_proxy}{host, type}
+Make the request by connecting to a proxy server. The \var{host} and \var{type}
+will replace those of the instance, and the instance's selector will be
+the original URL given in the constructor.
+\end{methoddesc}
+
+\begin{classdesc}{OpenerDirector}{}
+The \class{OpenerDirector} class opens URLs via \class{BaseHandler}s chained
+together. It manages the chaining of handlers, and recovery from errors.
+\end{classdesc}
+
+\begin{methoddesc}[OpenerDirector]{add_handler}{handler}
+\var{handler} should be an instance of \class{BaseHandler}. The following
+methods are searched, and added to the possible chains.
+
+\begin{itemize}
+ \item \code{{\em protocol}_open} --- signal that the handler knows how
+ to open {\em protocol} URLs.
+ \item \code{{\em protocol}_error_{\em type}} -- signal that the handler
+ knows how to handle {\em type}
+ errors from {\em protocol}.
+\end{itemize}
+
+\end{methoddesc}
+
+\begin{methoddesc}[OpenerDirector]{close}{}
+Explicitly break cycles, and delete all the handlers.
+Because the \class{OpenerDirector} needs to know the registered handlers,
+and a handler needs to know who the \class{OpenerDirector} who called
+it is, there is a reference cycles. Even though recent versions of Python
+have cycle-collection, it is sometimes preferable to explicitly break
+the cycles.
+\end{methoddesc}
+
+\begin{methoddesc}[OpenerDirector]{open}{url\optional{, data}}
+Open the given \var{url}. (which can be a request object or a string),
+optionally passing the given \var{data}.
+Arguments, return values and exceptions raised are the same as those
+of \function{urlopen} (which simply calls the \method{open()} method
+on the default installed \class{OpenerDirector}.
+\end{methoddesc}
+
+\begin{methoddesc}[OpenerDirector]{error}{proto\optional{, arg\optional{, ...}}}
+Handle an error in a given protocol. The HTTP protocol is special cased to
+use the code as the error. This will call the registered error handlers
+for the given protocol with the given arguments (which are protocol specific).
+
+Return values and exceptions raised are the same as those
+of \function{urlopen}.
+\end{methoddesc}
+
+\begin{classdesc}{BaseHandler}{}
+This is the base class for all registered handlers --- and handles only
+the simple mechanics of registration.
+\end{classdesc}
+
+\begin{methoddesc}[BaseHandler]{add_parent}{director}
+Add a director as parent.
+\end{methoddesc}
+
+\begin{methoddesc}[BaseHandler]{close}{}
+Remove any parents.
+\end{methoddesc}
+
+The following members and methods should be used only be classes derived
+from \class{BaseHandler}:
+
+\begin{memberdesc}[BaseHandler]{parent}
+A valid \class{OpenerDirector}, which can be used to open using a different
+protocol, or handle errors.
+\end{memberdesc}
+
+\begin{methoddesc}[BaseHandler]{default_open}{req}
+This method is {\em not} defined in \class{BaseHandler}, but subclasses
+should define it if they want to catch all URLs.
+
+This method, if exists, will be called by the \member{parent}
+\class{OpenerDirector}. It should return a file-like object as described
+in the return value of the \method{open} of \class{OpenerDirector} or
+\code{None}. It should raise \exception{URLError}, unless a truly exceptional
+thing happens (for example, \exception{MemoryError} should not be mapped
+to \exception{URLError}.
+
+This method will be called before any protocol-specific open method.
+\end{methoddesc}
+
+\begin{methoddesc}[BaseHandler]{{\em protocol}_open}{req}
+This method is {\em not} defined in \class{BaseHandler}, but subclasses
+should define it if they want to handle URLs with the given protocol.
+
+This method, if exists, will be called by the \member{parent}
+\class{OpenerDirector}. Return values should be the same as for
+\method{default_open}.
+\end{methoddesc}
+
+\begin{methoddesc}[BaseHandler]{unknown_open}{req}
+This method is {\em not} defined in \class{BaseHandler}, but subclasses
+should define it if they want to catch all URLs with no specific
+registerd handler to open it.
+
+This method, if exists, will be called by the \member{parent}
+\class{OpenerDirector}. Return values should be the same as for
+\method{default_open}.
+\end{methoddesc}
+
+\begin{methoddesc}[BaseHandler]{http_error_default}{req, fp, code, msg, hdrs}
+This method is {\em not} defined in \class{BaseHandler}, but subclasses
+should override it if they intend to provide a catch-all for otherwise
+unhandled HTTP errors. It will be called automatically by the
+\class{OpenerDirector} getting the error, and should not normally be called
+in other circumstances.
+
+\var{req} will be a \class{Request} object, \var{fp} will be a file-like
+object with the HTTP error body, \var{code} will be the three-digit code
+of the error, \var{msg} will be the user-visible explanation of the
+code and \var{hdrs} will be a dictionary-like object with the headers of
+the error.
+
+Return values and exceptions raised should be the same as those
+of \function{urlopen}.
+\end{methoddesc}
+
+\begin{methoddesc}[BaseHandler]{http_error_{\em nnn}}{req, fp, code, msg, hdrs}
+\code{nnn} should be a three-digit HTTP error code. This method is also
+not defined in \class{BaseHandler}, but will be called, if it exists, on
+an instance of a subclass, when an HTTP error with code \code{nnn} occurse.
+
+Subclasses should override this method to handle specific HTTP errors.
+
+Arguments, return values and exceptions raised shoudl be the same as for
+\method{http_error_default}
+\end{methoddesc}
+
+
+\begin{classdesc}{HTTPDefaultErrorHandler}{}
+A class which catches all HTTP errors.
+\end{classdesc}
+
+\begin{methoddesc}[HTTPDefaultErrorHandler]{http_error_default}{req, fp, code,
+ msg, hdrs}
+Raise an \exception{HTTPError}
+\end{methoddesc}
+
+\begin{classdesc}{HTTPRedirectHandler}{}
+A class to handle redirections.
+\end{classdesc}
+
+\begin{methoddesc}[HTTPRedirectHandler]{http_error_301}{req, fp, code,
+ msg, hdrs}
+Redirect to the \code{Location:} URL. This method gets called by
+the parent \class{OpenerDirector} when getting an HTTP permanent-redirect
+error.
+\end{methoddesc}
+
+\begin{methoddesc}[HTTPRedirectHandler]{http_error_302}{req, fp, code,
+ msg, hdrs}
+The same as \method{http_error_301}.
+\end{methoddesc}
+
+\strong{Note:} 303 redirection is not supported by this version of
+\module{urllib2}.
+
+\begin{classdesc}{ProxyHandler}{\optional{proxies}}
+Cause requests to go through a proxy.
+If \var{proxies} is given, it must be a dictionary mapping
+protocol names to URLs of proxies.
+The default is to read the list of proxies from the environment
+variables \code{{\em protocol}_proxy}.
+\end{classdesc}
+
+\begin{methoddesc}[ProxyHandler]{{\em protocol}_open}{request}
+The \class{ProxyHandler} will have a method \code{{\em protocol}_open} for
+every {\em protocol} which has a proxy in the \var{proxies} dictionary
+given in the constructor. The method will modify requests to go
+through the proxy, by calling \code{request.set_proxy()}, and call the next
+handler in the chain to actually execute the protocol.
+\end{methoddesc}
+
+\begin{classdesc}{HTTPPasswordMgr}{}
+Keep a database of
+\code{(\var{realm}, \var{uri}) -> (\var{user}, \var{password})} mapping.
+\end{classdesc}
+
+\begin{methoddesc}[HTTPPasswordMgr]{add_password}{realm, uri, user, passwd}
+\var{uri} can be either a single URI, or a sequene of URIs. \var{realm},
+\var{user} and \var{passwd} must be strings. This causes
+ \code{(\var{user}, \var{passwd})} to be used as authentication tokens
+when authentication for \var{realm} and a super-URI of any of the
+given URIs is given.
+\end{methoddesc}
+
+\begin{methoddesc}[HTTPPasswordMgr]{find_user_password}{realm, authuri}
+Get user/password for given realm and URI, if any. This method will
+return \code{(None, None)} if there is no user/password is known.
+\end{methoddesc}
+
+\begin{classdesc}{HTTPPasswordMgrWithDefaultRealm}{}
+Keep a database of
+\code{(\var{realm}, \var{uri}) -> (\var{user}, \var{password})} mapping.
+A realm of \code{None} is considered a catch-all realm, which is searched
+if no other realm fits.
+\end{classdesc}
+
+\begin{methoddesc}[HTTPPasswordMgrWithDefaultRealm]{add_password}
+ {realm, uri, user, passwd}
+\var{uri} can be either a single URI, or a sequene of URIs. \var{realm},
+\var{user} and \var{passwd} must be strings. This causes
+ \code{(\var{user}, \var{passwd})} to be used as authentication tokens
+when authentication for \var{realm} and a super-URI of any of the
+given URIs is given.
+\end{methoddesc}
+
+\begin{methoddesc}[HTTPPasswordMgr]{find_user_password}{realm, authuri}
+Get user/password for given realm and URI, if any. This method will
+return \code{(None, None)} if there is no user/password is known.
+If the given \var{realm} has no user/password, the realm \code{None}
+will be searched.
+\end{methoddesc}
+
+\begin{classdesc}[AbstractBasicAuthHandler]{\optional{password_mgr}}
+This is a mixin class, that helps with HTTP authentication, both
+to the remote host and to a proxy.
+
+\var{password_mgr} should be something that is compatible with
+\class{HTTPPasswordMgr} --- supplies the documented interface above.
+\end{classdesc}
+
+\begin{methoddesc}[AbstractBasicAuthHandler]{handle_authentication_request}
+ {authreq, host, req, headers}
+Handle an authentication request by getting user/password pair, and retrying.
+\var{authreq} should be the name of the header where the information about
+the realm, \var{host} is the host to authenticate too, \var{req} should be the
+(failed) \class{Request} object, and \var{headers} should be the error headers.
+\end{methoddesc}
+
+\begin{classdesc}{HTTPBasicAuthHandler}{\optional{password_mgr}}
+Handle authentication with the remote host.
+Valid \var{password_mgr}, if given, are the same as for
+\class{AbstractBasicAuthHandler}.
+\end{classdesc}
+
+\begin{methoddesc}[HTTPBasicAuthHandler]{http_error_401}{req, fp, code,
+ msg, hdrs}
+Retry the request with authentication info, if available.
+\end{methoddesc}
+
+\begin{classdesc}{ProxyBasicAuthHandler}{\optional{password_mgr}}
+Handle authentication with the proxy.
+Valid \var{password_mgr}, if given, are the same as for
+\class{AbstractBasicAuthHandler}.
+\end{classdesc}
+
+\begin{methoddesc}[ProxyBasicAuthHandler]{http_error_407}{req, fp, code,
+ msg, hdrs}
+Retry the request with authentication info, if available.
+\end{methoddesc}
+
+\begin{classdesc}{AbstractDigestAuthHandler}{\optional{password_mgr}}
+This is a mixin class, that helps with HTTP authentication, both
+to the remote host and to a proxy.
+
+\var{password_mgr} should be something that is compatible with
+\class{HTTPPasswordMgr} --- supplies the documented interface above.
+\end{classdesc}
+
+\begin{methoddesc}[AbstractBasicAuthHandler]{handle_authentication_request}
+ {authreq, host, req, headers}
+\var{authreq} should be the name of the header where the information about
+the realm, \var{host} should be the host to authenticate too, \var{req}
+should be the (failed) \class{Request} object, and \var{headers} should be the
+error headers.
+\end{methoddesc}
+
+\begin{classdesc}{HTTPDigestAuthHandler}{\optional{password_mgr}}
+Handle authentication with the remote host.
+Valid \var{password_mgr}, if given, are the same as for
+\class{AbstractBasicAuthHandler}.
+\end{classdesc}
+
+\begin{methoddesc}[HTTPDigestAuthHandler]{http_error_401}{req, fp, code,
+ msg, hdrs}
+Retry the request with authentication info, if available.
+\end{methoddesc}
+
+\begin{classdesc}{ProxyDigestAuthHandler}{\optional{password_mgr}}
+Handle authentication with the proxy.
+\var{password_mgr}, if given, shoudl be the same as for
+the constructor of \class{AbstractDigestAuthHandler}.
+\end{classdesc}
+
+\begin{methoddesc}[ProxyDigestAuthHandler]{http_error_407}{req, fp, code,
+ msg, hdrs}
+Retry the request with authentication info, if available.
+\end{methoddesc}
+
+\begin{classdesc}{HTTPHandler}{}
+A class to handle opening of HTTP URLs
+\end{classdesc}
+
+\begin{methoddesc}[HTTPHandler]{http_open}{req}
+Send an HTTP request (either GET or POST, depending on whether
+\code{req.has_data()}.
+\end{methoddesc}
+
+\begin{classdesc}{HTTPSHandler}{}
+A class to handle opening of HTTPS URLs
+\end{classdesc}
+
+\begin{methoddesc}[HTTPSHandler]{https_open}{req}
+Send an HTTPS request (either GET or POST, depending on whether
+\code{req.has_data()}.
+\end{methoddesc}
+
+\begin{classdesc}{UknownHandler}{}
+A catch-all class to handle unknown URLs.
+\end{classdesc}
+
+\begin{methoddesc}[UknownHandler]{unknown_open}
+Raise a \exception{URLError} exception
+\end{methoddesc}
+
+\begin{classdesc}{FileHandler}{}
+Open local files.
+\end{classdesc}
+
+\begin{methoddesc}[FileHandler]{file_open}{req}
+Open the file locally, if there is no host name, or
+the host name is \code{"localhost"}. Change the
+protocol to \code{ftp} otherwise, and retry opening
+it using \member{parent}.
+\end{methoddesc}
+
+\begin{classdesc}{FTPHandler}{}
+Open FTP URLs.
+\end{classdesc}
+
+\begin{methoddesc}[FTPHandler]{ftp_open}{req}
+Open the FTP file indicated by \var{req}.
+The login is always done with empty username and password.
+\end{methoddesc}
+
+\begin{classdesc}{CacheFTPHandler}{}
+Open FTP URLs, keeping a cache of open FTP connections to minimize
+delays.
+\end{classdesc}
+
+\begin{methoddesc}[CacheFTPHandler]{ftp_open}{req}
+Open the FTP file indicated by \var{req}.
+The login is always done with empty username and password.
+\end{methoddesc}
+
+\begin{methoddesc}[CacheFTPHandler]{setTimeout}{t}
+Set timeout of connections to \var{t} seconds.
+\end{methoddesc}
+
+\begin{methoddesc}[CacheFTPHandler]{setMaxConns}{m}
+Set maximum number of cached connections to \var{m}.
+\end{methoddesc}
+
+\begin{classdesc}{GopherHandler}{}
+Open gopher URLs.
+\end{classdesc}
+
+\begin{methoddesc}[GopherHandler]{gopher_open}{req}
+Open the gopher resource indicated by \var{req}.
+\end{methoddesc}
diff --git a/Lib/urllib2.py b/Lib/urllib2.py
index a3ff482..a1e157b 100644
--- a/Lib/urllib2.py
+++ b/Lib/urllib2.py
@@ -57,8 +57,10 @@ import urllib2
authinfo = urllib2.HTTPBasicAuthHandler()
authinfo.add_password('realm', 'host', 'username', 'password')
+proxy_support = urllib2.ProxyHandler({"http" : "http://ahad-haam:3128"})
+
# build a new opener that adds authentication and caching FTP handlers
-opener = urllib2.build_opener(authinfo, urllib2.CacheFTPHandler)
+opener = urllib2.build_opener(proxy_support, authinfo, urllib2.CacheFTPHandler)
# install it
urllib2.install_opener(opener)
@@ -92,7 +94,6 @@ import re
import base64
import types
import urlparse
-import os
import md5
import mimetypes
import mimetools
@@ -100,6 +101,7 @@ import ftplib
import sys
import time
import gopherlib
+import posixpath
try:
from cStringIO import StringIO
@@ -121,10 +123,7 @@ from urllib import unwrap, unquote, splittype, splithost, \
from urllib import getproxies
# support for FileHandler
-from urllib import localhost, thishost, url2pathname, pathname2url
-
-# support for GopherHandler
-from urllib import splitgophertype, splitquery
+from urllib import localhost, url2pathname
__version__ = "2.0a1"
@@ -177,7 +176,9 @@ class HTTPError(URLError, addinfourl):
class GopherError(URLError):
pass
+
class Request:
+
def __init__(self, url, data=None, headers={}):
# unwrap('<URL:type://host/path>') --> 'type://host/path'
self.__original = unwrap(url)
@@ -229,15 +230,8 @@ class Request:
def get_selector(self):
return self.__r_host
- def set_proxy(self, proxy):
- self.__proxy = proxy
- # XXX this code is based on urllib, but it doesn't seem
- # correct. specifically, if the proxy has a port number then
- # splittype will return the hostname as the type and the port
- # will be include with everything else
- self.type, self.__r_type = splittype(self.__proxy)
- self.host, XXX = splithost(self.__r_type)
- self.host = unquote(self.host)
+ def set_proxy(self, host, type):
+ self.host, self.type = host, type
self.__r_host = self.__original
def add_header(self, key, val):
@@ -329,9 +323,9 @@ class OpenerDirector:
'unknown_open', req)
def error(self, proto, *args):
- if proto == 'http':
- # XXX http protocol is special cased
- dict = self.handle_error[proto]
+ if proto in ['http', 'https']:
+ # XXX http[s] protocols are special cased
+ dict = self.handle_error['http'] # https is not different then http
proto = args[2] # YUCK!
meth_name = 'http_error_%d' % proto
http_err = 1
@@ -397,6 +391,8 @@ def build_opener(*handlers):
default_classes = [ProxyHandler, UnknownHandler, HTTPHandler,
HTTPDefaultErrorHandler, HTTPRedirectHandler,
FTPHandler, FileHandler]
+ if hasattr(httplib, 'HTTPS'):
+ default_classes.append(HTTPSHandler)
skip = []
for klass in default_classes:
for check in handlers:
@@ -451,7 +447,7 @@ class HTTPRedirectHandler(BaseHandler):
new = Request(newurl, req.get_data())
new.error_302_dict = {}
if hasattr(req, 'error_302_dict'):
- if req.error_302_dict.has_key(newurl):
+ if len(error_302_dict)>10 or req.error_302_dict.has_key(newurl):
raise HTTPError(req.get_full_url(), code,
self.inf_msg + msg, headers)
new.error_302_dict.update(req.error_302_dict)
@@ -477,7 +473,14 @@ class ProxyHandler(BaseHandler):
def proxy_open(self, req, proxy, type):
orig_type = req.get_type()
- req.set_proxy(proxy)
+ type, r_type = splittype(proxy)
+ host, XXX = splithost(r_type)
+ if '@' in host:
+ user_pass, host = host.split('@', 1)
+ user_pass = base64.encode_string(unquote(user_passw)).strip()
+ req.addheader('Proxy-Authorization', user_pass)
+ host = unquote(host)
+ req.set_proxy(host, type)
if orig_type == type:
# let other handlers take care of it
# XXX this only makes sense if the proxy is before the
@@ -569,21 +572,33 @@ class HTTPPasswordMgr:
return 1
if base[0] != test[0]:
return 0
- common = os.path.commonprefix((base[1], test[1]))
+ common = posixpath.commonprefix((base[1], test[1]))
if len(common) == len(base[1]):
return 1
return 0
-class HTTPBasicAuthHandler(BaseHandler):
+class HTTPPasswordMgrWithDefaultRealm(HTTPPasswordMgr):
+
+ def find_user_password(self, realm, authuri):
+ user, password = HTTPPasswordMgr.find_user_password(self,realm,authuri)
+ if user is not None:
+ return user, password
+ return HTTPPasswordMgr.find_user_password(self, None, authuri)
+
+
+class AbstractBasicAuthHandler:
+
rx = re.compile('[ \t]*([^ \t]+)[ \t]+realm="([^"]*)"')
# XXX there can actually be multiple auth-schemes in a
# www-authenticate header. should probably be a lot more careful
# in parsing them to extract multiple alternatives
- def __init__(self):
- self.passwd = HTTPPasswordMgr()
+ def __init__(self, password_mgr=None):
+ if password_mgr is None:
+ password_mgr = HTTPPasswordMgr()
+ self.passwd = password_mgr
self.add_password = self.passwd.add_password
self.__current_realm = None
# if __current_realm is not None, then the server must have
@@ -591,29 +606,27 @@ class HTTPBasicAuthHandler(BaseHandler):
# again. must be careful to set it to None on successful
# return.
- def http_error_401(self, req, fp, code, msg, headers):
- # XXX could be mult. headers
- authreq = headers.get('www-authenticate', None)
+ def http_error_auth_reqed(self, authreq, host, req, headers):
+ # XXX could be multiple headers
+ authreq = headers.get(authreq, None)
if authreq:
- mo = HTTPBasicAuthHandler.rx.match(authreq)
+ mo = AbstractBasicAuthHandler.rx.match(authreq)
if mo:
scheme, realm = mo.groups()
if scheme.lower() == 'basic':
- return self.retry_http_basic_auth(req, realm)
+ return self.retry_http_basic_auth(host, req, realm)
- def retry_http_basic_auth(self, req, realm):
+ def retry_http_basic_auth(self, host, req, realm):
if self.__current_realm is None:
self.__current_realm = realm
else:
self.__current_realm = realm
return None
- # XXX host isn't really the correct URI?
- host = req.get_host()
user,pw = self.passwd.find_user_password(realm, host)
if pw:
raw = "%s:%s" % (user, pw)
auth = base64.encodestring(raw).strip()
- req.add_header('Authorization', 'Basic %s' % auth)
+ req.add_header(self.header, 'Basic %s' % auth)
resp = self.parent.open(req)
self.__current_realm = None
return resp
@@ -621,21 +634,37 @@ class HTTPBasicAuthHandler(BaseHandler):
self.__current_realm = None
return None
-class HTTPDigestAuthHandler(BaseHandler):
- """An authentication protocol defined by RFC 2069
+class HTTPBasicAuthHandler(AbstractBasicAuthHandler, BaseHandler):
- Digest authentication improves on basic authentication because it
- does not transmit passwords in the clear.
- """
+ header = 'Authorization'
- def __init__(self):
- self.passwd = HTTPPasswordMgr()
+ def http_error_401(self, req, fp, code, msg, headers):
+ host = urlparse.urlparse(req.get_full_url())[1]
+ return self.http_error_auth_reqed('www-authenticate',
+ host, req, headers)
+
+
+class ProxyBasicAuthHandler(AbstractBasicAuthHandler, BaseHandler):
+
+ header = 'Proxy-Authorization'
+
+ def http_error_407(self, req, fp, code, msg, headers):
+ host = req.get_host()
+ return self.http_error_auth_reqed('proxy-authenticate',
+ host, req, headers)
+
+
+class AbstractDigestAuthHandler:
+
+ def __init__(self, passwd=None):
+ if passwd is None:
+ passwd = HTTPPassowrdMgr()
+ self.passwd = passwd
self.add_password = self.passwd.add_password
self.__current_realm = None
- def http_error_401(self, req, fp, code, msg, headers):
- # XXX could be mult. headers
- authreq = headers.get('www-authenticate', None)
+ def http_error_auth_reqed(self, authreq, host, req, headers):
+ authreq = headers.get(self.header, None)
if authreq:
kind = authreq.split()[0]
if kind == 'Digest':
@@ -646,7 +675,7 @@ class HTTPDigestAuthHandler(BaseHandler):
chal = parse_keqv_list(parse_http_list(challenge))
auth = self.get_authorization(req, chal)
if auth:
- req.add_header('Authorization', 'Digest %s' % auth)
+ req.add_header(self.header, 'Digest %s' % auth)
resp = self.parent.open(req)
self.__current_realm = None
return resp
@@ -715,6 +744,30 @@ class HTTPDigestAuthHandler(BaseHandler):
# XXX not implemented yet
return None
+
+class HTTPDigestAuthHandler(BaseHandler, AbstractDigestAuthHandler):
+ """An authentication protocol defined by RFC 2069
+
+ Digest authentication improves on basic authentication because it
+ does not transmit passwords in the clear.
+ """
+
+ header = 'Authorization'
+
+ def http_error_401(self, req, fp, code, msg, headers):
+ host = urlparse.urlparse(req.get_full_url())[1]
+ self.http_error_auth_reqed('www-authenticate', host, req, headers)
+
+
+class ProxyDigestAuthHandler(BaseHandler, AbstractDigestAuthHandler):
+
+ header = 'Proxy-Authorization'
+
+ def http_error_407(self, req, fp, code, msg, headers):
+ host = req.get_host()
+ self.http_error_auth_reqed('proxy-authenticate', host, req, headers)
+
+
def encode_digest(digest):
hexrep = []
for c in digest:
@@ -725,15 +778,15 @@ def encode_digest(digest):
return ''.join(hexrep)
-class HTTPHandler(BaseHandler):
- def http_open(self, req):
- # XXX devise a new mechanism to specify user/password
+class AbstractHTTPHandler(BaseHandler):
+
+ def do_open(self, http_class, req):
host = req.get_host()
if not host:
raise URLError('no host given')
try:
- h = httplib.HTTP(host) # will parse host:port
+ h = http_class(host) # will parse host:port
if req.has_data():
data = req.get_data()
h.putrequest('POST', req.get_selector())
@@ -762,6 +815,20 @@ class HTTPHandler(BaseHandler):
else:
return self.parent.error('http', req, fp, code, msg, hdrs)
+
+class HTTPHandler(AbstractHTTPHandler):
+
+ def http_open(self, req):
+ return self.do_open(httplib.HTTP, req)
+
+
+if hasattr(httplib, 'HTTPS'):
+ class HTTPSHandler(AbstractHTTPHandler):
+
+ def https_open(self, req):
+ return self.do_open(httplib.HTTPS, req)
+
+
class UnknownHandler(BaseHandler):
def unknown_open(self, req):
type = req.get_type()