FM / library

/usr/share/doc/python2-docs/html/_sources/library/

/usr/share/doc/python2-docs/html/_sources/library

Name	Size	Mode	Actions
2to3.rst.txt	14647	0644	edit dl rm
abc.rst.txt	7219	0644	edit dl rm
aepack.rst.txt	4257	0644	edit dl rm
aetools.rst.txt	3532	0644	edit dl rm
aetypes.rst.txt	4257	0644	edit dl rm
aifc.rst.txt	7086	0644	edit dl rm
al.rst.txt	5309	0644	edit dl rm
allos.rst.txt	695	0644	edit dl rm
anydbm.rst.txt	4111	0644	edit dl rm
archiving.rst.txt	424	0644	edit dl rm
argparse.rst.txt	74685	0644	edit dl rm
array.rst.txt	10524	0644	edit dl rm
ast.rst.txt	10111	0644	edit dl rm
asynchat.rst.txt	9206	0644	edit dl rm
asyncore.rst.txt	12937	0644	edit dl rm
atexit.rst.txt	3910	0644	edit dl rm
audioop.rst.txt	10395	0644	edit dl rm
autogil.rst.txt	1015	0644	edit dl rm
base64.rst.txt	6252	0644	edit dl rm
basehttpserver.rst.txt	10404	0644	edit dl rm
bastion.rst.txt	2611	0644	edit dl rm
bdb.rst.txt	12456	0644	edit dl rm
binascii.rst.txt	6508	0644	edit dl rm
binhex.rst.txt	1910	0644	edit dl rm
bisect.rst.txt	5415	0644	edit dl rm
bsddb.rst.txt	7575	0644	edit dl rm
bz2.rst.txt	8064	0644	edit dl rm
calendar.rst.txt	11282	0644	edit dl rm
carbon.rst.txt	15956	0644	edit dl rm
cd.rst.txt	11974	0644	edit dl rm
cgi.rst.txt	22853	0644	edit dl rm
cgihttpserver.rst.txt	2788	0644	edit dl rm
cgitb.rst.txt	2874	0644	edit dl rm
chunk.rst.txt	4955	0644	edit dl rm
cmath.rst.txt	7647	0644	edit dl rm
cmd.rst.txt	8565	0644	edit dl rm
code.rst.txt	7115	0644	edit dl rm
codecs.rst.txt	66966	0644	edit dl rm
codeop.rst.txt	3774	0644	edit dl rm
collections.rst.txt	41448	0644	edit dl rm
colorpicker.rst.txt	913	0644	edit dl rm
colorsys.rst.txt	1819	0644	edit dl rm
commands.rst.txt	2595	0644	edit dl rm
compileall.rst.txt	4678	0644	edit dl rm
compiler.rst.txt	37464	0644	edit dl rm
configparser.rst.txt	19607	0644	edit dl rm
constants.rst.txt	2328	0644	edit dl rm
contextlib.rst.txt	6012	0644	edit dl rm
cookie.rst.txt	9543	0644	edit dl rm
cookielib.rst.txt	27875	0644	edit dl rm
copy.rst.txt	3351	0644	edit dl rm
copy_reg.rst.txt	2329	0644	edit dl rm
crypt.rst.txt	2292	0644	edit dl rm
crypto.rst.txt	355	0644	edit dl rm
csv.rst.txt	22757	0644	edit dl rm
ctypes.rst.txt	90513	0644	edit dl rm
curses.ascii.rst.txt	9046	0644	edit dl rm
curses.panel.rst.txt	2740	0644	edit dl rm
curses.rst.txt	74877	0644	edit dl rm
custominterp.rst.txt	570	0644	edit dl rm
datatypes.rst.txt	864	0644	edit dl rm
datetime.rst.txt	74679	0644	edit dl rm
dbhash.rst.txt	3865	0644	edit dl rm
dbm.rst.txt	3117	0644	edit dl rm
debug.rst.txt	446	0644	edit dl rm
decimal.rst.txt	70926	0644	edit dl rm
development.rst.txt	640	0644	edit dl rm
difflib.rst.txt	30716	0644	edit dl rm
dircache.rst.txt	1813	0644	edit dl rm
dis.rst.txt	23248	0644	edit dl rm
distribution.rst.txt	426	0644	edit dl rm
distutils.rst.txt	1958	0644	edit dl rm
dl.rst.txt	3392	0644	edit dl rm
doctest.rst.txt	73985	0644	edit dl rm
docxmlrpcserver.rst.txt	3802	0644	edit dl rm
dumbdbm.rst.txt	2841	0644	edit dl rm
dummy_thread.rst.txt	1058	0644	edit dl rm
dummy_threading.rst.txt	799	0644	edit dl rm
easydialogs.rst.txt	10346	0644	edit dl rm
email-examples.rst.txt	1271	0644	edit dl rm
email.charset.rst.txt	9654	0644	edit dl rm
email.encoders.rst.txt	2376	0644	edit dl rm
email.errors.rst.txt	4006	0644	edit dl rm
email.generator.rst.txt	6132	0644	edit dl rm
email.header.rst.txt	7531	0644	edit dl rm
email.iterators.rst.txt	2421	0644	edit dl rm
email.message.rst.txt	25217	0644	edit dl rm
email.mime.rst.txt	9917	0644	edit dl rm
email.parser.rst.txt	10327	0644	edit dl rm
email.rst.txt	16111	0644	edit dl rm
email.utils.rst.txt	6475	0644	edit dl rm
ensurepip.rst.txt	5022	0644	edit dl rm
errno.rst.txt	6708	0644	edit dl rm
exceptions.rst.txt	18343	0644	edit dl rm
fcntl.rst.txt	7361	0644	edit dl rm
filecmp.rst.txt	5348	0644	edit dl rm
fileformats.rst.txt	302	0644	edit dl rm
fileinput.rst.txt	7417	0644	edit dl rm
filesys.rst.txt	806	0644	edit dl rm
fl.rst.txt	17646	0644	edit dl rm
fm.rst.txt	2699	0644	edit dl rm
fnmatch.rst.txt	3104	0644	edit dl rm
formatter.rst.txt	13245	0644	edit dl rm
fpectl.rst.txt	4171	0644	edit dl rm
fpformat.rst.txt	1747	0644	edit dl rm
fractions.rst.txt	5297	0644	edit dl rm
framework.rst.txt	11444	0644	edit dl rm
frameworks.rst.txt	378	0644	edit dl rm
ftplib.rst.txt	15720	0644	edit dl rm
functions.rst.txt	75554	0644	edit dl rm
functools.rst.txt	7448	0644	edit dl rm
future_builtins.rst.txt	2010	0644	edit dl rm
gc.rst.txt	9014	0644	edit dl rm
gdbm.rst.txt	4882	0644	edit dl rm
gensuitemodule.rst.txt	3113	0644	edit dl rm
getopt.rst.txt	6670	0644	edit dl rm
getpass.rst.txt	1876	0644	edit dl rm
gettext.rst.txt	29040	0644	edit dl rm
gl.rst.txt	6009	0644	edit dl rm
glob.rst.txt	2414	0644	edit dl rm
grp.rst.txt	2256	0644	edit dl rm
gzip.rst.txt	4828	0644	edit dl rm
hashlib.rst.txt	7379	0644	edit dl rm
heapq.rst.txt	13185	0644	edit dl rm
hmac.rst.txt	3073	0644	edit dl rm
hotshot.rst.txt	4289	0644	edit dl rm
htmllib.rst.txt	7379	0644	edit dl rm
htmlparser.rst.txt	11640	0644	edit dl rm
httplib.rst.txt	37454	0644	edit dl rm
i18n.rst.txt	409	0644	edit dl rm
ic.rst.txt	5005	0644	edit dl rm
idle.rst.txt	22182	0644	edit dl rm
imageop.rst.txt	4001	0644	edit dl rm
imaplib.rst.txt	17221	0644	edit dl rm
imgfile.rst.txt	2765	0644	edit dl rm
imghdr.rst.txt	2635	0644	edit dl rm
imp.rst.txt	12593	0644	edit dl rm
importlib.rst.txt	1126	0644	edit dl rm
imputil.rst.txt	7023	0644	edit dl rm
index.rst.txt	2287	0644	edit dl rm
inspect.rst.txt	28151	0644	edit dl rm
internet.rst.txt	950	0644	edit dl rm
intro.rst.txt	2803	0644	edit dl rm
io.rst.txt	39015	0644	edit dl rm
ipc.rst.txt	630	0644	edit dl rm
itertools.rst.txt	36324	0644	edit dl rm
jpeg.rst.txt	3858	0644	edit dl rm
json.rst.txt	25545	0644	edit dl rm
keyword.rst.txt	617	0644	edit dl rm
language.rst.txt	523	0644	edit dl rm
linecache.rst.txt	1887	0644	edit dl rm
locale.rst.txt	24975	0644	edit dl rm
logging.config.rst.txt	31560	0644	edit dl rm
logging.handlers.rst.txt	28153	0644	edit dl rm
logging.rst.txt	46882	0644	edit dl rm
mac.rst.txt	791	0644	edit dl rm
macos.rst.txt	3824	0644	edit dl rm
macosa.rst.txt	3964	0644	edit dl rm
macostools.rst.txt	4017	0644	edit dl rm
macpath.rst.txt	650	0644	edit dl rm
mailbox.rst.txt	68129	0644	edit dl rm
mailcap.rst.txt	3675	0644	edit dl rm
markup.rst.txt	1249	0644	edit dl rm
marshal.rst.txt	5689	0644	edit dl rm
math.rst.txt	10920	0644	edit dl rm
md5.rst.txt	2815	0644	edit dl rm
mhlib.rst.txt	3966	0644	edit dl rm
mimetools.rst.txt	4504	0644	edit dl rm
mimetypes.rst.txt	9839	0644	edit dl rm
mimewriter.rst.txt	3360	0644	edit dl rm
mimify.rst.txt	3519	0644	edit dl rm
miniaeframe.rst.txt	2564	0644	edit dl rm
misc.rst.txt	248	0644	edit dl rm
mm.rst.txt	447	0644	edit dl rm
mmap.rst.txt	10481	0644	edit dl rm
modulefinder.rst.txt	3380	0644	edit dl rm
modules.rst.txt	382	0644	edit dl rm
msilib.rst.txt	19062	0644	edit dl rm
msvcrt.rst.txt	4346	0644	edit dl rm
multifile.rst.txt	6613	0644	edit dl rm
multiprocessing.rst.txt	92621	0644	edit dl rm
mutex.rst.txt	1939	0644	edit dl rm
netdata.rst.txt	432	0644	edit dl rm
netrc.rst.txt	3119	0644	edit dl rm
new.rst.txt	2653	0644	edit dl rm
nis.rst.txt	2108	0644	edit dl rm
nntplib.rst.txt	14531	0644	edit dl rm
numbers.rst.txt	8007	0644	edit dl rm
numeric.rst.txt	751	0644	edit dl rm
operator.rst.txt	22092	0644	edit dl rm
optparse.rst.txt	77101	0644	edit dl rm
os.path.rst.txt	13094	0644	edit dl rm
os.rst.txt	82580	0644	edit dl rm
ossaudiodev.rst.txt	17309	0644	edit dl rm
othergui.rst.txt	2721	0644	edit dl rm
parser.rst.txt	15385	0644	edit dl rm
pdb.rst.txt	16043	0644	edit dl rm
persistence.rst.txt	826	0644	edit dl rm
pickle.rst.txt	37262	0644	edit dl rm
pickletools.rst.txt	1997	0644	edit dl rm
pipes.rst.txt	3786	0644	edit dl rm
pkgutil.rst.txt	7714	0644	edit dl rm
platform.rst.txt	9554	0644	edit dl rm
plistlib.rst.txt	4134	0644	edit dl rm
popen2.rst.txt	7022	0644	edit dl rm
poplib.rst.txt	6220	0644	edit dl rm
posix.rst.txt	3630	0644	edit dl rm
posixfile.rst.txt	7200	0644	edit dl rm
pprint.rst.txt	9071	0644	edit dl rm
profile.rst.txt	28666	0644	edit dl rm
pty.rst.txt	1762	0644	edit dl rm
pwd.rst.txt	2725	0644	edit dl rm
pyclbr.rst.txt	3296	0644	edit dl rm
pydoc.rst.txt	4083	0644	edit dl rm
pyexpat.rst.txt	28891	0644	edit dl rm
python.rst.txt	514	0644	edit dl rm
py_compile.rst.txt	2479	0644	edit dl rm
queue.rst.txt	7034	0644	edit dl rm
quopri.rst.txt	2670	0644	edit dl rm
random.rst.txt	13319	0644	edit dl rm
re.rst.txt	55102	0644	edit dl rm
readline.rst.txt	10513	0644	edit dl rm
repr.rst.txt	4718	0644	edit dl rm
resource.rst.txt	9595	0644	edit dl rm
restricted.rst.txt	3327	0644	edit dl rm
rexec.rst.txt	11742	0644	edit dl rm
rfc822.rst.txt	14037	0644	edit dl rm
rlcompleter.rst.txt	2494	0644	edit dl rm
robotparser.rst.txt	2190	0644	edit dl rm
runpy.rst.txt	6938	0644	edit dl rm
sched.rst.txt	4644	0644	edit dl rm
scrolledtext.rst.txt	1379	0644	edit dl rm
select.rst.txt	20705	0644	edit dl rm
sets.rst.txt	14973	0644	edit dl rm
sgi.rst.txt	322	0644	edit dl rm
sgmllib.rst.txt	10664	0644	edit dl rm
sha.rst.txt	2807	0644	edit dl rm
shelve.rst.txt	8319	0644	edit dl rm
shlex.rst.txt	11313	0644	edit dl rm
shutil.rst.txt	13491	0644	edit dl rm
signal.rst.txt	10719	0644	edit dl rm
simplehttpserver.rst.txt	4559	0644	edit dl rm
simplexmlrpcserver.rst.txt	10881	0644	edit dl rm
site.rst.txt	7880	0644	edit dl rm
smtpd.rst.txt	2464	0644	edit dl rm
smtplib.rst.txt	14906	0644	edit dl rm
sndhdr.rst.txt	1759	0644	edit dl rm
socket.rst.txt	40765	0644	edit dl rm
socketserver.rst.txt	22512	0644	edit dl rm
someos.rst.txt	599	0644	edit dl rm
spwd.rst.txt	2825	0644	edit dl rm
sqlite3.rst.txt	35448	0644	edit dl rm
ssl.rst.txt	76554	0644	edit dl rm
stat.rst.txt	7778	0644	edit dl rm
statvfs.rst.txt	1300	0644	edit dl rm
stdtypes.rst.txt	122668	0644	edit dl rm
string.rst.txt	44085	0644	edit dl rm
stringio.rst.txt	4166	0644	edit dl rm
stringprep.rst.txt	4238	0644	edit dl rm
strings.rst.txt	746	0644	edit dl rm
struct.rst.txt	17100	0644	edit dl rm
subprocess.rst.txt	33648	0644	edit dl rm
sun.rst.txt	249	0644	edit dl rm
sunau.rst.txt	7124	0644	edit dl rm
sunaudio.rst.txt	5849	0644	edit dl rm
symbol.rst.txt	975	0644	edit dl rm
symtable.rst.txt	5064	0644	edit dl rm
sys.rst.txt	47520	0644	edit dl rm
sysconfig.rst.txt	7639	0644	edit dl rm
syslog.rst.txt	3931	0644	edit dl rm
tabnanny.rst.txt	1999	0644	edit dl rm
tarfile.rst.txt	28214	0644	edit dl rm
telnetlib.rst.txt	7482	0644	edit dl rm
tempfile.rst.txt	10504	0644	edit dl rm
termios.rst.txt	3733	0644	edit dl rm
test.rst.txt	17659	0644	edit dl rm
textwrap.rst.txt	8552	0644	edit dl rm
thread.rst.txt	6588	0644	edit dl rm
threading.rst.txt	32468	0644	edit dl rm
time.rst.txt	26020	0644	edit dl rm
timeit.rst.txt	11598	0644	edit dl rm
tix.rst.txt	22693	0644	edit dl rm
tk.rst.txt	1612	0644	edit dl rm
tkinter.rst.txt	33456	0644	edit dl rm
token.rst.txt	2451	0644	edit dl rm
tokenize.rst.txt	5570	0644	edit dl rm
trace.rst.txt	6724	0644	edit dl rm
traceback.rst.txt	10711	0644	edit dl rm
ttk.rst.txt	57411	0644	edit dl rm
tty.rst.txt	1011	0644	edit dl rm
turtle.rst.txt	64097	0644	edit dl rm
types.rst.txt	6200	0644	edit dl rm
undoc.rst.txt	6550	0644	edit dl rm
unicodedata.rst.txt	5736	0644	edit dl rm
unittest.rst.txt	82952	0644	edit dl rm
unix.rst.txt	490	0644	edit dl rm
urllib.rst.txt	24960	0644	edit dl rm
urllib2.rst.txt	35211	0644	edit dl rm
urlparse.rst.txt	16071	0644	edit dl rm
user.rst.txt	2748	0644	edit dl rm
userdict.rst.txt	9290	0644	edit dl rm
uu.rst.txt	2369	0644	edit dl rm
uuid.rst.txt	8378	0644	edit dl rm
warnings.rst.txt	19815	0644	edit dl rm
wave.rst.txt	5047	0644	edit dl rm
weakref.rst.txt	12926	0644	edit dl rm
webbrowser.rst.txt	9863	0644	edit dl rm
whichdb.rst.txt	931	0644	edit dl rm
windows.rst.txt	273	0644	edit dl rm
winsound.rst.txt	5066	0644	edit dl rm
wsgiref.rst.txt	30567	0644	edit dl rm
xdrlib.rst.txt	8077	0644	edit dl rm
xml.dom.minidom.rst.txt	11208	0644	edit dl rm
xml.dom.pulldom.rst.txt	1571	0644	edit dl rm
xml.dom.rst.txt	40182	0644	edit dl rm
xml.etree.elementtree.rst.txt	35707	0644	edit dl rm
xml.rst.txt	6090	0644	edit dl rm
xml.sax.handler.rst.txt	15371	0644	edit dl rm
xml.sax.reader.rst.txt	12257	0644	edit dl rm
xml.sax.rst.txt	6460	0644	edit dl rm
xml.sax.utils.rst.txt	3560	0644	edit dl rm
xmlrpclib.rst.txt	22559	0644	edit dl rm
zipfile.rst.txt	18871	0644	edit dl rm
zipimport.rst.txt	5957	0644	edit dl rm
zlib.rst.txt	12766	0644	edit dl rm
_winreg.rst.txt	23305	0644	edit dl rm
__builtin__.rst.txt	1494	0644	edit dl rm
__future__.rst.txt	4952	0644	edit dl rm
__main__.rst.txt	535	0644	edit dl rm

Edit: /usr/share/doc/python2-docs/html/_sources/library/urllib2.rst.txt (35211B)

:mod:`urllib2` --- extensible library for opening URLs
======================================================

.. module:: urllib2
   :synopsis: Next generation URL opening library.
.. moduleauthor:: Jeremy Hylton <jhylton@users.sourceforge.net>
.. sectionauthor:: Moshe Zadka <moshez@users.sourceforge.net>

.. note::
   The :mod:`urllib2` module has been split across several modules in
   Python 3 named :mod:`urllib.request` and :mod:`urllib.error`.
   The :term:`2to3` tool will automatically adapt imports when converting
   your sources to Python 3.

The :mod:`urllib2` module defines functions and classes which help in opening
URLs (mostly HTTP) in a complex world --- basic and digest authentication,
redirections, cookies and more.

.. seealso::

The `Requests package <http://requests.readthedocs.org/>`_
    is recommended for a higher-level HTTP client interface.

The :mod:`urllib2` module defines the following functions:

.. function:: urlopen(url[, data[, timeout[, cafile[, capath[, cadefault[, context]]]]])

Open the URL *url*, which can be either a string or a :class:`Request` object.

*data* may be a string specifying additional data to send to the server, or
   ``None`` if no such data is needed.  Currently HTTP requests are the only ones
   that use *data*; the HTTP request will be a POST instead of a GET when the
   *data* parameter is provided.  *data* should be a buffer in the standard
   :mimetype:`application/x-www-form-urlencoded` format.  The
   :func:`urllib.urlencode` function takes a mapping or sequence of 2-tuples and
   returns a string in this format. urllib2 module sends HTTP/1.1 requests with
   ``Connection:close`` header included.

The optional *timeout* parameter specifies a timeout in seconds for blocking
   operations like the connection attempt (if not specified, the global default
   timeout setting will be used).  This actually only works for HTTP, HTTPS and
   FTP connections.

If *context* is specified, it must be a :class:`ssl.SSLContext` instance
   describing the various SSL options. See :class:`~httplib.HTTPSConnection` for
   more details.

The optional *cafile* and *capath* parameters specify a set of trusted CA
   certificates for HTTPS requests.  *cafile* should point to a single file
   containing a bundle of CA certificates, whereas *capath* should point to a
   directory of hashed certificate files.  More information can be found in
   :meth:`ssl.SSLContext.load_verify_locations`.

The *cadefault* parameter is ignored.

This function returns a file-like object with three additional methods:

* :meth:`geturl` --- return the URL of the resource retrieved, commonly used to
     determine if a redirect was followed

* :meth:`info` --- return the meta-information of the page, such as headers,
     in the form of an :class:`mimetools.Message` instance
     (see `Quick Reference to HTTP Headers <https://www.cs.tut.fi/~jkorpela/http.html>`_)

* :meth:`getcode` --- return the HTTP status code of the response.

Raises :exc:`URLError` on errors.

Note that ``None`` may be returned if no handler handles the request (though the
   default installed global :class:`OpenerDirector` uses :class:`UnknownHandler` to
   ensure this never happens).

In addition, if proxy settings are detected (for example, when a ``*_proxy``
   environment variable like :envvar:`http_proxy` is set),
   :class:`ProxyHandler` is default installed and makes sure the requests are
   handled through the proxy.

.. versionchanged:: 2.6
     *timeout* was added.

.. versionchanged:: 2.7.9
      *cafile*, *capath*, *cadefault*, and *context* were added.

.. function:: install_opener(opener)

Install an :class:`OpenerDirector` instance as the default global opener.
   Installing an opener is only necessary if you want urlopen to use that opener;
   otherwise, simply call :meth:`OpenerDirector.open` instead of :func:`urlopen`.
   The code does not check for a real :class:`OpenerDirector`, and any class with
   the appropriate interface will work.

.. function:: build_opener([handler, ...])

Return an :class:`OpenerDirector` instance, which chains the handlers in the
   order given. *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 front of the *handler*\s, unless the *handler*\s contain them,
   instances of them or subclasses of them: :class:`ProxyHandler` (if proxy
   settings are detected),
   :class:`UnknownHandler`, :class:`HTTPHandler`, :class:`HTTPDefaultErrorHandler`,
   :class:`HTTPRedirectHandler`, :class:`FTPHandler`, :class:`FileHandler`,
   :class:`HTTPErrorProcessor`.

If the Python installation has SSL support (i.e., if the :mod:`ssl` module can be imported),
   :class:`HTTPSHandler` will also be added.

Beginning in Python 2.3, a :class:`BaseHandler` subclass may also change its
   :attr:`handler_order` attribute to modify its position in the handlers
   list.

The following exceptions are raised as appropriate:

.. exception:: URLError

The handlers raise this exception (or derived exceptions) when they run into a
   problem.  It is a subclass of :exc:`IOError`.

.. attribute:: reason

The reason for this error.  It can be a message string or another exception
      instance (:exc:`socket.error` for remote URLs, :exc:`OSError` for local
      URLs).

.. exception:: HTTPError

Though being an exception (a subclass of :exc:`URLError`), an :exc:`HTTPError`
   can also function as a non-exceptional file-like return value (the same thing
   that :func:`urlopen` returns).  This is useful when handling exotic HTTP
   errors, such as requests for authentication.

.. attribute:: code

An HTTP status code as defined in `RFC 2616 <http://www.faqs.org/rfcs/rfc2616.html>`_.
      This numeric value corresponds to a value found in the dictionary of
      codes as found in :attr:`BaseHTTPServer.BaseHTTPRequestHandler.responses`.

.. attribute:: reason

The reason for this error.  It can be a message string or another exception
      instance.

The following classes are provided:

.. class:: Request(url[, data][, headers][, origin_req_host][, unverifiable])

This class is an abstraction of a URL request.

*url* should be a string containing a valid URL.

*headers* should be a dictionary, and will be treated as if :meth:`add_header`
   was called with each key and value as arguments.  This is often used to "spoof"
   the ``User-Agent`` header value, which is used by a browser to identify itself --
   some HTTP servers only allow requests coming from common browsers as opposed
   to scripts.  For example, Mozilla Firefox may identify itself as ``"Mozilla/5.0
   (X11; U; Linux i686) Gecko/20071127 Firefox/2.0.0.11"``, while :mod:`urllib2`'s
   default user agent string is ``"Python-urllib/2.6"`` (on Python 2.6).

The final two arguments are only of interest for correct handling of third-party
   HTTP cookies:

*origin_req_host* should be the request-host of the origin transaction, as
   defined by :rfc:`2965`.  It defaults to ``cookielib.request_host(self)``.  This
   is the host name or IP address of the original request that was initiated by the
   user.  For example, if the request is for an image in an HTML document, this
   should be the request-host of the request for the page containing the image.

*unverifiable* should indicate whether the request is unverifiable, as defined
   by RFC 2965.  It defaults to ``False``.  An unverifiable request is one whose URL
   the user did not have the option to approve.  For example, if the request is for
   an image in an HTML document, and the user had no option to approve the
   automatic fetching of the image, this should be true.

.. class:: OpenerDirector()

The :class:`OpenerDirector` class opens URLs via :class:`BaseHandler`\ s chained
   together. It manages the chaining of handlers, and recovery from errors.

.. class:: BaseHandler()

This is the base class for all registered handlers --- and handles only the
   simple mechanics of registration.

.. class:: HTTPDefaultErrorHandler()

A class which defines a default handler for HTTP error responses; all responses
   are turned into :exc:`HTTPError` exceptions.

.. class:: HTTPRedirectHandler()

A class to handle redirections.

.. class:: HTTPCookieProcessor([cookiejar])

A class to handle HTTP Cookies.

.. class:: ProxyHandler([proxies])

Cause requests to go through a proxy. If *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
   :envvar:`<protocol>_proxy`.  If no proxy environment variables are set, then
   in a Windows environment proxy settings are obtained from the registry's
   Internet Settings section, and in a Mac OS X environment proxy information
   is retrieved from the OS X System Configuration Framework.

To disable autodetected proxy pass an empty dictionary.

.. note::

``HTTP_PROXY`` will be ignored if a variable ``REQUEST_METHOD`` is set;
       see the documentation on :func:`~urllib.getproxies`.

.. class:: HTTPPasswordMgr()

Keep a database of  ``(realm, uri) -> (user, password)`` mappings.

.. class:: HTTPPasswordMgrWithDefaultRealm()

Keep a database of  ``(realm, uri) -> (user, password)`` mappings. A realm of
   ``None`` is considered a catch-all realm, which is searched if no other realm
   fits.

.. class:: AbstractBasicAuthHandler([password_mgr])

This is a mixin class that helps with HTTP authentication, both to the remote
   host and to a proxy. *password_mgr*, if given, should be something that is
   compatible with :class:`HTTPPasswordMgr`; refer to section
   :ref:`http-password-mgr` for information on the interface that must be
   supported.

.. class:: HTTPBasicAuthHandler([password_mgr])

Handle authentication with the remote host. *password_mgr*, if given, should be
   something that is compatible with :class:`HTTPPasswordMgr`; refer to section
   :ref:`http-password-mgr` for information on the interface that must be
   supported.

.. class:: ProxyBasicAuthHandler([password_mgr])

Handle authentication with the proxy. *password_mgr*, if given, should be
   something that is compatible with :class:`HTTPPasswordMgr`; refer to section
   :ref:`http-password-mgr` for information on the interface that must be
   supported.

.. class:: AbstractDigestAuthHandler([password_mgr])

.. class:: HTTPDigestAuthHandler([password_mgr])

.. class:: ProxyDigestAuthHandler([password_mgr])

.. class:: HTTPHandler()

A class to handle opening of HTTP URLs.

.. class:: HTTPSHandler([debuglevel[, context]])

A class to handle opening of HTTPS URLs. *context* has the same meaning as
   for :class:`httplib.HTTPSConnection`.

.. versionchanged:: 2.7.9
      *context* added.

.. class:: FileHandler()

Open local files.

.. class:: FTPHandler()

Open FTP URLs.

.. class:: CacheFTPHandler()

Open FTP URLs, keeping a cache of open FTP connections to minimize delays.

.. class:: UnknownHandler()

A catch-all class to handle unknown URLs.

.. class:: HTTPErrorProcessor()

Process HTTP error responses.

.. _request-objects:

Request Objects
---------------

The following methods describe all of :class:`Request`'s public interface, and
so all must be overridden in subclasses.

.. method:: Request.add_data(data)

Set the :class:`Request` data to *data*.  This is ignored by all handlers except
   HTTP handlers --- and there it should be a byte string, and will change the
   request to be ``POST`` rather than ``GET``.

.. method:: Request.get_method()

Return a string indicating the HTTP request method.  This is only meaningful for
   HTTP requests, and currently always returns ``'GET'`` or ``'POST'``.

.. method:: Request.has_data()

Return whether the instance has a non-\ ``None`` data.

.. method:: Request.get_data()

Return the instance's data.

.. method:: 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 than one header with the same
   name, and later calls will overwrite previous calls in case the *key* collides.
   Currently, this is no loss of HTTP functionality, since all headers which have
   meaning when used more than once have a (header-specific) way of gaining the
   same functionality using only one header.

.. method:: Request.add_unredirected_header(key, header)

Add a header that will not be added to a redirected request.

.. versionadded:: 2.4

.. method:: Request.has_header(header)

Return whether the instance has the named header (checks both regular and
   unredirected).

.. versionadded:: 2.4

.. method:: Request.get_full_url()

Return the URL given in the constructor.

.. method:: Request.get_type()

Return the type of the URL --- also known as the scheme.

.. method:: Request.get_host()

Return the host to which a connection will be made.

.. method:: Request.get_selector()

Return the selector --- the part of the URL that is sent to the server.

.. method:: Request.get_header(header_name, default=None)

Return the value of the given header. If the header is not present, return
   the default value.

.. method:: Request.header_items()

Return a list of tuples (header_name, header_value) of the Request headers.

.. method:: Request.set_proxy(host, type)

Prepare the request by connecting to a proxy server. The *host* and *type* will
   replace those of the instance, and the instance's selector will be the original
   URL given in the constructor.

.. method:: Request.get_origin_req_host()

Return the request-host of the origin transaction, as defined by :rfc:`2965`.
   See the documentation for the :class:`Request` constructor.

.. method:: Request.is_unverifiable()

Return whether the request is unverifiable, as defined by RFC 2965. See the
   documentation for the :class:`Request` constructor.

.. _opener-director-objects:

OpenerDirector Objects
----------------------

:class:`OpenerDirector` instances have the following methods:

.. method:: OpenerDirector.add_handler(handler)

*handler* should be an instance of :class:`BaseHandler`.  The following
   methods are searched, and added to the possible chains (note that HTTP errors
   are a special case).

* :samp:`{protocol}_open` --- signal that the handler knows how to open
     *protocol* URLs.

* :samp:`http_error_{type}` --- signal that the handler knows how to handle
     HTTP errors with HTTP error code *type*.

* :samp:`{protocol}_error` --- signal that the handler knows how to handle
     errors from (non-\ ``http``) *protocol*.

* :samp:`{protocol}_request` --- signal that the handler knows how to
     pre-process *protocol* requests.

* :samp:`{protocol}_response` --- signal that the handler knows how to
     post-process *protocol* responses.

.. method:: OpenerDirector.open(url[, data][, timeout])

Open the given *url* (which can be a request object or a string), optionally
   passing the given *data*. Arguments, return values and exceptions raised are
   the same as those of :func:`urlopen` (which simply calls the :meth:`open`
   method on the currently installed global :class:`OpenerDirector`).  The
   optional *timeout* parameter specifies a timeout in seconds for blocking
   operations like the connection attempt (if not specified, the global default
   timeout setting will be used). The timeout feature actually works only for
   HTTP, HTTPS and FTP connections).

.. versionchanged:: 2.6
      *timeout* was added.

.. method:: OpenerDirector.error(proto[, arg[, ...]])

Handle an error of the given protocol.  This will call the registered error
   handlers for the given protocol with the given arguments (which are protocol
   specific).  The HTTP protocol is a special case which uses the HTTP response
   code to determine the specific error handler; refer to the :meth:`http_error_\*`
   methods of the handler classes.

Return values and exceptions raised are the same as those of :func:`urlopen`.

OpenerDirector objects open URLs in three stages:

The order in which these methods are called within each stage is determined by
sorting the handler instances.

#. Every handler with a method named like :samp:`{protocol}_request` has that
   method called to pre-process the request.

#. Handlers with a method named like :samp:`{protocol}_open` are called to handle
   the request. This stage ends when a handler either returns a non-\ :const:`None`
   value (ie. a response), or raises an exception (usually :exc:`URLError`).
   Exceptions are allowed to propagate.

In fact, the above algorithm is first tried for methods named
   :meth:`default_open`.  If all such methods return :const:`None`, the
   algorithm is repeated for methods named like :samp:`{protocol}_open`.  If all
   such methods return :const:`None`, the algorithm is repeated for methods
   named :meth:`unknown_open`.

Note that the implementation of these methods may involve calls of the parent
   :class:`OpenerDirector` instance's :meth:`~OpenerDirector.open` and
   :meth:`~OpenerDirector.error` methods.

#. Every handler with a method named like :samp:`{protocol}_response` has that
   method called to post-process the response.

.. _base-handler-objects:

BaseHandler Objects
-------------------

:class:`BaseHandler` objects provide a couple of methods that are directly
useful, and others that are meant to be used by derived classes.  These are
intended for direct use:

.. method:: BaseHandler.add_parent(director)

Add a director as parent.

.. method:: BaseHandler.close()

Remove any parents.

The following attributes and methods should only be used by classes derived from
:class:`BaseHandler`.

.. note::

The convention has been adopted that subclasses defining
   :meth:`protocol_request` or :meth:`protocol_response` methods are named
   :class:`\*Processor`; all others are named :class:`\*Handler`.

.. attribute:: BaseHandler.parent

A valid :class:`OpenerDirector`, which can be used to open using a different
   protocol, or handle errors.

.. method:: BaseHandler.default_open(req)

This method is *not* defined in :class:`BaseHandler`, but subclasses should
   define it if they want to catch all URLs.

This method, if implemented, will be called by the parent
   :class:`OpenerDirector`.  It should return a file-like object as described in
   the return value of the :meth:`open` of :class:`OpenerDirector`, or ``None``.
   It should raise :exc:`URLError`, unless a truly exceptional thing happens (for
   example, :exc:`MemoryError` should not be mapped to :exc:`URLError`).

This method will be called before any protocol-specific open method.

.. method:: BaseHandler.protocol_open(req)
   :noindex:

("protocol" is to be replaced by the protocol name.)

This method is *not* defined in :class:`BaseHandler`, but subclasses should
   define it if they want to handle URLs with the given *protocol*.

This method, if defined, will be called by the parent :class:`OpenerDirector`.
   Return values should be the same as for  :meth:`default_open`.

.. method:: BaseHandler.unknown_open(req)

This method is *not* defined in :class:`BaseHandler`, but subclasses should
   define it if they want to catch all URLs with no specific registered handler to
   open it.

This method, if implemented, will be called by the :attr:`parent`
   :class:`OpenerDirector`.  Return values should be the same as for
   :meth:`default_open`.

.. method:: BaseHandler.http_error_default(req, fp, code, msg, hdrs)

This method is *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.

*req* will be a :class:`Request` object, *fp* will be a file-like object with
   the HTTP error body, *code* will be the three-digit code of the error, *msg*
   will be the user-visible explanation of the code and *hdrs* will be a mapping
   object with the headers of the error.

Return values and exceptions raised should be the same as those of
   :func:`urlopen`.

.. method:: BaseHandler.http_error_nnn(req, fp, code, msg, hdrs)

*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 *nnn* occurs.

Subclasses should override this method to handle specific HTTP errors.

Arguments, return values and exceptions raised should be the same as for
   :meth:`http_error_default`.

.. method:: BaseHandler.protocol_request(req)
   :noindex:

("protocol" is to be replaced by the protocol name.)

This method is *not* defined in :class:`BaseHandler`, but subclasses should
   define it if they want to pre-process requests of the given *protocol*.

This method, if defined, will be called by the parent :class:`OpenerDirector`.
   *req* will be a :class:`Request` object. The return value should be a
   :class:`Request` object.

.. method:: BaseHandler.protocol_response(req, response)
   :noindex:

("protocol" is to be replaced by the protocol name.)

This method is *not* defined in :class:`BaseHandler`, but subclasses should
   define it if they want to post-process responses of the given *protocol*.

This method, if defined, will be called by the parent :class:`OpenerDirector`.
   *req* will be a :class:`Request` object. *response* will be an object
   implementing the same interface as the return value of :func:`urlopen`.  The
   return value should implement the same interface as the return value of
   :func:`urlopen`.

.. _http-redirect-handler:

HTTPRedirectHandler Objects
---------------------------

.. note::

Some HTTP redirections require action from this module's client code.  If this
   is the case, :exc:`HTTPError` is raised.  See :rfc:`2616` for details of the
   precise meanings of the various redirection codes.

.. method:: HTTPRedirectHandler.redirect_request(req, fp, code, msg, hdrs, newurl)

Return a :class:`Request` or ``None`` in response to a redirect. This is called
   by the default implementations of the :meth:`http_error_30\*` methods when a
   redirection is received from the server.  If a redirection should take place,
   return a new :class:`Request` to allow :meth:`http_error_30\*` to perform the
   redirect to *newurl*.  Otherwise, raise :exc:`HTTPError` if no other handler
   should try to handle this URL, or return ``None`` if you can't but another
   handler might.

.. note::

The default implementation of this method does not strictly follow :rfc:`2616`,
      which says that 301 and 302 responses to ``POST`` requests must not be
      automatically redirected without confirmation by the user.  In reality, browsers
      do allow automatic redirection of these responses, changing the POST to a
      ``GET``, and the default implementation reproduces this behavior.

.. method:: HTTPRedirectHandler.http_error_301(req, fp, code, msg, hdrs)

Redirect to the ``Location:`` or ``URI:`` URL.  This method is called by the
   parent :class:`OpenerDirector` when getting an HTTP 'moved permanently' response.

.. method:: HTTPRedirectHandler.http_error_302(req, fp, code, msg, hdrs)

The same as :meth:`http_error_301`, but called for the 'found' response.

.. method:: HTTPRedirectHandler.http_error_303(req, fp, code, msg, hdrs)

The same as :meth:`http_error_301`, but called for the 'see other' response.

.. method:: HTTPRedirectHandler.http_error_307(req, fp, code, msg, hdrs)

The same as :meth:`http_error_301`, but called for the 'temporary redirect'
   response.

.. _http-cookie-processor:

HTTPCookieProcessor Objects
---------------------------

.. versionadded:: 2.4

:class:`HTTPCookieProcessor` instances have one attribute:

.. attribute:: HTTPCookieProcessor.cookiejar

The :class:`cookielib.CookieJar` in which cookies are stored.

.. _proxy-handler:

ProxyHandler Objects
--------------------

.. method:: ProxyHandler.protocol_open(request)
   :noindex:

("protocol" is to be replaced by the protocol name.)

The :class:`ProxyHandler` will have a method :samp:`{protocol}_open` for every
   *protocol* which has a proxy in the *proxies* dictionary given in the
   constructor.  The method will modify requests to go through the proxy, by
   calling ``request.set_proxy()``, and call the next handler in the chain to
   actually execute the protocol.

.. _http-password-mgr:

HTTPPasswordMgr Objects
-----------------------

These methods are available on :class:`HTTPPasswordMgr` and
:class:`HTTPPasswordMgrWithDefaultRealm` objects.

.. method:: HTTPPasswordMgr.add_password(realm, uri, user, passwd)

*uri* can be either a single URI, or a sequence of URIs. *realm*, *user* and
   *passwd* must be strings. This causes ``(user, passwd)`` to be used as
   authentication tokens when authentication for *realm* and a super-URI of any of
   the given URIs is given.

.. method:: HTTPPasswordMgr.find_user_password(realm, authuri)

Get user/password for given realm and URI, if any.  This method will return
   ``(None, None)`` if there is no matching user/password.

For :class:`HTTPPasswordMgrWithDefaultRealm` objects, the realm ``None`` will be
   searched if the given *realm* has no matching user/password.

.. _abstract-basic-auth-handler:

AbstractBasicAuthHandler Objects
--------------------------------

.. method:: AbstractBasicAuthHandler.http_error_auth_reqed(authreq, host, req, headers)

Handle an authentication request by getting a user/password pair, and re-trying
   the request.  *authreq* should be the name of the header where the information
   about the realm is included in the request, *host* specifies the URL and path to
   authenticate for, *req* should be the (failed) :class:`Request` object, and
   *headers* should be the error headers.

*host* is either an authority (e.g. ``"python.org"``) or a URL containing an
   authority component (e.g. ``"http://python.org/"``). In either case, the
   authority must not contain a userinfo component (so, ``"python.org"`` and
   ``"python.org:80"`` are fine, ``"joe:password@python.org"`` is not).

.. _http-basic-auth-handler:

HTTPBasicAuthHandler Objects
----------------------------

.. method:: HTTPBasicAuthHandler.http_error_401(req, fp, code,  msg, hdrs)

Retry the request with authentication information, if available.

.. _proxy-basic-auth-handler:

ProxyBasicAuthHandler Objects
-----------------------------

.. method:: ProxyBasicAuthHandler.http_error_407(req, fp, code,  msg, hdrs)

Retry the request with authentication information, if available.

.. _abstract-digest-auth-handler:

AbstractDigestAuthHandler Objects
---------------------------------

.. method:: AbstractDigestAuthHandler.http_error_auth_reqed(authreq, host, req, headers)

*authreq* should be the name of the header where the information about the realm
   is included in the request, *host* should be the host to authenticate to, *req*
   should be the (failed) :class:`Request` object, and *headers* should be the
   error headers.

.. _http-digest-auth-handler:

HTTPDigestAuthHandler Objects
-----------------------------

.. method:: HTTPDigestAuthHandler.http_error_401(req, fp, code,  msg, hdrs)

Retry the request with authentication information, if available.

.. _proxy-digest-auth-handler:

ProxyDigestAuthHandler Objects
------------------------------

.. method:: ProxyDigestAuthHandler.http_error_407(req, fp, code,  msg, hdrs)

Retry the request with authentication information, if available.

.. _http-handler-objects:

HTTPHandler Objects
-------------------

.. method:: HTTPHandler.http_open(req)

Send an HTTP request, which can be either GET or POST, depending on
   ``req.has_data()``.

.. _https-handler-objects:

HTTPSHandler Objects
--------------------

.. method:: HTTPSHandler.https_open(req)

Send an HTTPS request, which can be either GET or POST, depending on
   ``req.has_data()``.

.. _file-handler-objects:

FileHandler Objects
-------------------

.. method:: FileHandler.file_open(req)

Open the file locally, if there is no host name, or the host name is
   ``'localhost'``. Change the protocol to ``ftp`` otherwise, and retry opening it
   using :attr:`parent`.

.. _ftp-handler-objects:

FTPHandler Objects
------------------

.. method:: FTPHandler.ftp_open(req)

Open the FTP file indicated by *req*. The login is always done with empty
   username and password.

.. _cacheftp-handler-objects:

CacheFTPHandler Objects
-----------------------

:class:`CacheFTPHandler` objects are :class:`FTPHandler` objects with the
following additional methods:

.. method:: CacheFTPHandler.setTimeout(t)

Set timeout of connections to *t* seconds.

.. method:: CacheFTPHandler.setMaxConns(m)

Set maximum number of cached connections to *m*.

.. _unknown-handler-objects:

UnknownHandler Objects
----------------------

.. method:: UnknownHandler.unknown_open()

Raise a :exc:`URLError` exception.

.. _http-error-processor-objects:

HTTPErrorProcessor Objects
--------------------------

.. versionadded:: 2.4

.. method:: HTTPErrorProcessor.http_response()

Process HTTP error responses.

For 200 error codes, the response object is returned immediately.

For non-200 error codes, this simply passes the job on to the
   :samp:`{protocol}_error_code` handler methods, via
   :meth:`OpenerDirector.error`.  Eventually,
   :class:`urllib2.HTTPDefaultErrorHandler` will raise an :exc:`HTTPError` if no
   other handler handles the error.

.. method:: HTTPErrorProcessor.https_response()

Process HTTPS error responses.

The behavior is same as :meth:`http_response`.

.. _urllib2-examples:

Examples
--------

In addition to the examples below, more examples are given in
:ref:`urllib-howto`.

This example gets the python.org main page and displays the first 100 bytes of
it::

>>> import urllib2
   >>> f = urllib2.urlopen('http://www.python.org/')
   >>> print f.read(100)
   <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
   <?xml-stylesheet href="./css/ht2html

Here we are sending a data-stream to the stdin of a CGI and reading the data it
returns to us. Note that this example will only work when the Python
installation supports SSL. ::

>>> import urllib2
   >>> req = urllib2.Request(url='https://localhost/cgi-bin/test.cgi',
   ...                       data='This data is passed to stdin of the CGI')
   >>> f = urllib2.urlopen(req)
   >>> print f.read()
   Got Data: "This data is passed to stdin of the CGI"

The code for the sample CGI used in the above example is::

#!/usr/bin/env python
   import sys
   data = sys.stdin.read()
   print 'Content-type: text-plain\n\nGot Data: "%s"' % data

Use of Basic HTTP Authentication::

import urllib2
   # Create an OpenerDirector with support for Basic HTTP Authentication...
   auth_handler = urllib2.HTTPBasicAuthHandler()
   auth_handler.add_password(realm='PDQ Application',
                             uri='https://mahler:8092/site-updates.py',
                             user='klem',
                             passwd='kadidd!ehopper')
   opener = urllib2.build_opener(auth_handler)
   # ...and install it globally so it can be used with urlopen.
   urllib2.install_opener(opener)
   urllib2.urlopen('http://www.example.com/login.html')

:func:`build_opener` provides many handlers by default, including a
:class:`ProxyHandler`.  By default, :class:`ProxyHandler` uses the environment
variables named ``<scheme>_proxy``, where ``<scheme>`` is the URL scheme
involved.  For example, the :envvar:`http_proxy` environment variable is read to
obtain the HTTP proxy's URL.

This example replaces the default :class:`ProxyHandler` with one that uses
programmatically-supplied proxy URLs, and adds proxy authorization support with
:class:`ProxyBasicAuthHandler`. ::

proxy_handler = urllib2.ProxyHandler({'http': 'http://www.example.com:3128/'})
   proxy_auth_handler = urllib2.ProxyBasicAuthHandler()
   proxy_auth_handler.add_password('realm', 'host', 'username', 'password')

opener = urllib2.build_opener(proxy_handler, proxy_auth_handler)
   # This time, rather than install the OpenerDirector, we use it directly:
   opener.open('http://www.example.com/login.html')

Adding HTTP headers:

Use the *headers* argument to the :class:`Request` constructor, or::

import urllib2
   req = urllib2.Request('http://www.example.com/')
   req.add_header('Referer', 'http://www.python.org/')
   # Customize the default User-Agent header value:
   req.add_header('User-Agent', 'urllib-example/0.1 (Contact: . . .)')
   r = urllib2.urlopen(req)

:class:`OpenerDirector` automatically adds a :mailheader:`User-Agent` header to
every :class:`Request`.  To change this::

import urllib2
   opener = urllib2.build_opener()
   opener.addheaders = [('User-agent', 'Mozilla/5.0')]
   opener.open('http://www.example.com/')

Also, remember that a few standard headers (:mailheader:`Content-Length`,
:mailheader:`Content-Type` and :mailheader:`Host`) are added when the
:class:`Request` is passed to :func:`urlopen` (or :meth:`OpenerDirector.open`).

:mod:`urllib2` --- extensible library for opening URLs ====================================================== .. module:: urllib2 :synopsis: Next generation URL opening library. .. moduleauthor:: Jeremy Hylton .. sectionauthor:: Moshe Zadka .. note:: The :mod:`urllib2` module has been split across several modules in Python 3 named :mod:`urllib.request` and :mod:`urllib.error`. The :term:`2to3` tool will automatically adapt imports when converting your sources to Python 3. The :mod:`urllib2` module defines functions and classes which help in opening URLs (mostly HTTP) in a complex world --- basic and digest authentication, redirections, cookies and more. .. seealso:: The `Requests package `_ is recommended for a higher-level HTTP client interface. The :mod:`urllib2` module defines the following functions: .. function:: urlopen(url[, data[, timeout[, cafile[, capath[, cadefault[, context]]]]]) Open the URL *url*, which can be either a string or a :class:`Request` object. *data* may be a string specifying additional data to send to the server, or ``None`` if no such data is needed. Currently HTTP requests are the only ones that use *data*; the HTTP request will be a POST instead of a GET when the *data* parameter is provided. *data* should be a buffer in the standard :mimetype:`application/x-www-form-urlencoded` format. The :func:`urllib.urlencode` function takes a mapping or sequence of 2-tuples and returns a string in this format. urllib2 module sends HTTP/1.1 requests with ``Connection:close`` header included. The optional *timeout* parameter specifies a timeout in seconds for blocking operations like the connection attempt (if not specified, the global default timeout setting will be used). This actually only works for HTTP, HTTPS and FTP connections. If *context* is specified, it must be a :class:`ssl.SSLContext` instance describing the various SSL options. See :class:`~httplib.HTTPSConnection` for more details. The optional *cafile* and *capath* parameters specify a set of trusted CA certificates for HTTPS requests. *cafile* should point to a single file containing a bundle of CA certificates, whereas *capath* should point to a directory of hashed certificate files. More information can be found in :meth:`ssl.SSLContext.load_verify_locations`. The *cadefault* parameter is ignored. This function returns a file-like object with three additional methods: * :meth:`geturl` --- return the URL of the resource retrieved, commonly used to determine if a redirect was followed * :meth:`info` --- return the meta-information of the page, such as headers, in the form of an :class:`mimetools.Message` instance (see `Quick Reference to HTTP Headers `_) * :meth:`getcode` --- return the HTTP status code of the response. Raises :exc:`URLError` on errors. Note that ``None`` may be returned if no handler handles the request (though the default installed global :class:`OpenerDirector` uses :class:`UnknownHandler` to ensure this never happens). In addition, if proxy settings are detected (for example, when a ``*_proxy`` environment variable like :envvar:`http_proxy` is set), :class:`ProxyHandler` is default installed and makes sure the requests are handled through the proxy. .. versionchanged:: 2.6 *timeout* was added. .. versionchanged:: 2.7.9 *cafile*, *capath*, *cadefault*, and *context* were added. .. function:: install_opener(opener) Install an :class:`OpenerDirector` instance as the default global opener. Installing an opener is only necessary if you want urlopen to use that opener; otherwise, simply call :meth:`OpenerDirector.open` instead of :func:`urlopen`. The code does not check for a real :class:`OpenerDirector`, and any class with the appropriate interface will work. .. function:: build_opener([handler, ...]) Return an :class:`OpenerDirector` instance, which chains the handlers in the order given. *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 front of the *handler*\s, unless the *handler*\s contain them, instances of them or subclasses of them: :class:`ProxyHandler` (if proxy settings are detected), :class:`UnknownHandler`, :class:`HTTPHandler`, :class:`HTTPDefaultErrorHandler`, :class:`HTTPRedirectHandler`, :class:`FTPHandler`, :class:`FileHandler`, :class:`HTTPErrorProcessor`. If the Python installation has SSL support (i.e., if the :mod:`ssl` module can be imported), :class:`HTTPSHandler` will also be added. Beginning in Python 2.3, a :class:`BaseHandler` subclass may also change its :attr:`handler_order` attribute to modify its position in the handlers list. The following exceptions are raised as appropriate: .. exception:: URLError The handlers raise this exception (or derived exceptions) when they run into a problem. It is a subclass of :exc:`IOError`. .. attribute:: reason The reason for this error. It can be a message string or another exception instance (:exc:`socket.error` for remote URLs, :exc:`OSError` for local URLs). .. exception:: HTTPError Though being an exception (a subclass of :exc:`URLError`), an :exc:`HTTPError` can also function as a non-exceptional file-like return value (the same thing that :func:`urlopen` returns). This is useful when handling exotic HTTP errors, such as requests for authentication. .. attribute:: code An HTTP status code as defined in `RFC 2616 `_. This numeric value corresponds to a value found in the dictionary of codes as found in :attr:`BaseHTTPServer.BaseHTTPRequestHandler.responses`. .. attribute:: reason The reason for this error. It can be a message string or another exception instance. The following classes are provided: .. class:: Request(url[, data][, headers][, origin_req_host][, unverifiable]) This class is an abstraction of a URL request. *url* should be a string containing a valid URL. *data* may be a string specifying additional data to send to the server, or ``None`` if no such data is needed. Currently HTTP requests are the only ones that use *data*; the HTTP request will be a POST instead of a GET when the *data* parameter is provided. *data* should be a buffer in the standard :mimetype:`application/x-www-form-urlencoded` format. The :func:`urllib.urlencode` function takes a mapping or sequence of 2-tuples and returns a string in this format. *headers* should be a dictionary, and will be treated as if :meth:`add_header` was called with each key and value as arguments. This is often used to "spoof" the ``User-Agent`` header value, which is used by a browser to identify itself -- some HTTP servers only allow requests coming from common browsers as opposed to scripts. For example, Mozilla Firefox may identify itself as ``"Mozilla/5.0 (X11; U; Linux i686) Gecko/20071127 Firefox/2.0.0.11"``, while :mod:`urllib2`'s default user agent string is ``"Python-urllib/2.6"`` (on Python 2.6). The final two arguments are only of interest for correct handling of third-party HTTP cookies: *origin_req_host* should be the request-host of the origin transaction, as defined by :rfc:`2965`. It defaults to ``cookielib.request_host(self)``. This is the host name or IP address of the original request that was initiated by the user. For example, if the request is for an image in an HTML document, this should be the request-host of the request for the page containing the image. *unverifiable* should indicate whether the request is unverifiable, as defined by RFC 2965. It defaults to ``False``. An unverifiable request is one whose URL the user did not have the option to approve. For example, if the request is for an image in an HTML document, and the user had no option to approve the automatic fetching of the image, this should be true. .. class:: OpenerDirector() The :class:`OpenerDirector` class opens URLs via :class:`BaseHandler`\ s chained together. It manages the chaining of handlers, and recovery from errors. .. class:: BaseHandler() This is the base class for all registered handlers --- and handles only the simple mechanics of registration. .. class:: HTTPDefaultErrorHandler() A class which defines a default handler for HTTP error responses; all responses are turned into :exc:`HTTPError` exceptions. .. class:: HTTPRedirectHandler() A class to handle redirections. .. class:: HTTPCookieProcessor([cookiejar]) A class to handle HTTP Cookies. .. class:: ProxyHandler([proxies]) Cause requests to go through a proxy. If *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 :envvar:`_proxy`. If no proxy environment variables are set, then in a Windows environment proxy settings are obtained from the registry's Internet Settings section, and in a Mac OS X environment proxy information is retrieved from the OS X System Configuration Framework. To disable autodetected proxy pass an empty dictionary. .. note:: ``HTTP_PROXY`` will be ignored if a variable ``REQUEST_METHOD`` is set; see the documentation on :func:`~urllib.getproxies`. .. class:: HTTPPasswordMgr() Keep a database of ``(realm, uri) -> (user, password)`` mappings. .. class:: HTTPPasswordMgrWithDefaultRealm() Keep a database of ``(realm, uri) -> (user, password)`` mappings. A realm of ``None`` is considered a catch-all realm, which is searched if no other realm fits. .. class:: AbstractBasicAuthHandler([password_mgr]) This is a mixin class that helps with HTTP authentication, both to the remote host and to a proxy. *password_mgr*, if given, should be something that is compatible with :class:`HTTPPasswordMgr`; refer to section :ref:`http-password-mgr` for information on the interface that must be supported. .. class:: HTTPBasicAuthHandler([password_mgr]) Handle authentication with the remote host. *password_mgr*, if given, should be something that is compatible with :class:`HTTPPasswordMgr`; refer to section :ref:`http-password-mgr` for information on the interface that must be supported. .. class:: ProxyBasicAuthHandler([password_mgr]) Handle authentication with the proxy. *password_mgr*, if given, should be something that is compatible with :class:`HTTPPasswordMgr`; refer to section :ref:`http-password-mgr` for information on the interface that must be supported. .. class:: AbstractDigestAuthHandler([password_mgr]) This is a mixin class that helps with HTTP authentication, both to the remote host and to a proxy. *password_mgr*, if given, should be something that is compatible with :class:`HTTPPasswordMgr`; refer to section :ref:`http-password-mgr` for information on the interface that must be supported. .. class:: HTTPDigestAuthHandler([password_mgr]) Handle authentication with the remote host. *password_mgr*, if given, should be something that is compatible with :class:`HTTPPasswordMgr`; refer to section :ref:`http-password-mgr` for information on the interface that must be supported. .. class:: ProxyDigestAuthHandler([password_mgr]) Handle authentication with the proxy. *password_mgr*, if given, should be something that is compatible with :class:`HTTPPasswordMgr`; refer to section :ref:`http-password-mgr` for information on the interface that must be supported. .. class:: HTTPHandler() A class to handle opening of HTTP URLs. .. class:: HTTPSHandler([debuglevel[, context]]) A class to handle opening of HTTPS URLs. *context* has the same meaning as for :class:`httplib.HTTPSConnection`. .. versionchanged:: 2.7.9 *context* added. .. class:: FileHandler() Open local files. .. class:: FTPHandler() Open FTP URLs. .. class:: CacheFTPHandler() Open FTP URLs, keeping a cache of open FTP connections to minimize delays. .. class:: UnknownHandler() A catch-all class to handle unknown URLs. .. class:: HTTPErrorProcessor() Process HTTP error responses. .. _request-objects: Request Objects --------------- The following methods describe all of :class:`Request`'s public interface, and so all must be overridden in subclasses. .. method:: Request.add_data(data) Set the :class:`Request` data to *data*. This is ignored by all handlers except HTTP handlers --- and there it should be a byte string, and will change the request to be ``POST`` rather than ``GET``. .. method:: Request.get_method() Return a string indicating the HTTP request method. This is only meaningful for HTTP requests, and currently always returns ``'GET'`` or ``'POST'``. .. method:: Request.has_data() Return whether the instance has a non-\ ``None`` data. .. method:: Request.get_data() Return the instance's data. .. method:: 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 than one header with the same name, and later calls will overwrite previous calls in case the *key* collides. Currently, this is no loss of HTTP functionality, since all headers which have meaning when used more than once have a (header-specific) way of gaining the same functionality using only one header. .. method:: Request.add_unredirected_header(key, header) Add a header that will not be added to a redirected request. .. versionadded:: 2.4 .. method:: Request.has_header(header) Return whether the instance has the named header (checks both regular and unredirected). .. versionadded:: 2.4 .. method:: Request.get_full_url() Return the URL given in the constructor. .. method:: Request.get_type() Return the type of the URL --- also known as the scheme. .. method:: Request.get_host() Return the host to which a connection will be made. .. method:: Request.get_selector() Return the selector --- the part of the URL that is sent to the server. .. method:: Request.get_header(header_name, default=None) Return the value of the given header. If the header is not present, return the default value. .. method:: Request.header_items() Return a list of tuples (header_name, header_value) of the Request headers. .. method:: Request.set_proxy(host, type) Prepare the request by connecting to a proxy server. The *host* and *type* will replace those of the instance, and the instance's selector will be the original URL given in the constructor. .. method:: Request.get_origin_req_host() Return the request-host of the origin transaction, as defined by :rfc:`2965`. See the documentation for the :class:`Request` constructor. .. method:: Request.is_unverifiable() Return whether the request is unverifiable, as defined by RFC 2965. See the documentation for the :class:`Request` constructor. .. _opener-director-objects: OpenerDirector Objects ---------------------- :class:`OpenerDirector` instances have the following methods: .. method:: OpenerDirector.add_handler(handler) *handler* should be an instance of :class:`BaseHandler`. The following methods are searched, and added to the possible chains (note that HTTP errors are a special case). * :samp:`{protocol}_open` --- signal that the handler knows how to open *protocol* URLs. * :samp:`http_error_{type}` --- signal that the handler knows how to handle HTTP errors with HTTP error code *type*. * :samp:`{protocol}_error` --- signal that the handler knows how to handle errors from (non-\ ``http``) *protocol*. * :samp:`{protocol}_request` --- signal that the handler knows how to pre-process *protocol* requests. * :samp:`{protocol}_response` --- signal that the handler knows how to post-process *protocol* responses. .. method:: OpenerDirector.open(url[, data][, timeout]) Open the given *url* (which can be a request object or a string), optionally passing the given *data*. Arguments, return values and exceptions raised are the same as those of :func:`urlopen` (which simply calls the :meth:`open` method on the currently installed global :class:`OpenerDirector`). The optional *timeout* parameter specifies a timeout in seconds for blocking operations like the connection attempt (if not specified, the global default timeout setting will be used). The timeout feature actually works only for HTTP, HTTPS and FTP connections). .. versionchanged:: 2.6 *timeout* was added. .. method:: OpenerDirector.error(proto[, arg[, ...]]) Handle an error of the given protocol. This will call the registered error handlers for the given protocol with the given arguments (which are protocol specific). The HTTP protocol is a special case which uses the HTTP response code to determine the specific error handler; refer to the :meth:`http_error_\*` methods of the handler classes. Return values and exceptions raised are the same as those of :func:`urlopen`. OpenerDirector objects open URLs in three stages: The order in which these methods are called within each stage is determined by sorting the handler instances. #. Every handler with a method named like :samp:`{protocol}_request` has that method called to pre-process the request. #. Handlers with a method named like :samp:`{protocol}_open` are called to handle the request. This stage ends when a handler either returns a non-\ :const:`None` value (ie. a response), or raises an exception (usually :exc:`URLError`). Exceptions are allowed to propagate. In fact, the above algorithm is first tried for methods named :meth:`default_open`. If all such methods return :const:`None`, the algorithm is repeated for methods named like :samp:`{protocol}_open`. If all such methods return :const:`None`, the algorithm is repeated for methods named :meth:`unknown_open`. Note that the implementation of these methods may involve calls of the parent :class:`OpenerDirector` instance's :meth:`~OpenerDirector.open` and :meth:`~OpenerDirector.error` methods. #. Every handler with a method named like :samp:`{protocol}_response` has that method called to post-process the response. .. _base-handler-objects: BaseHandler Objects ------------------- :class:`BaseHandler` objects provide a couple of methods that are directly useful, and others that are meant to be used by derived classes. These are intended for direct use: .. method:: BaseHandler.add_parent(director) Add a director as parent. .. method:: BaseHandler.close() Remove any parents. The following attributes and methods should only be used by classes derived from :class:`BaseHandler`. .. note:: The convention has been adopted that subclasses defining :meth:`protocol_request` or :meth:`protocol_response` methods are named :class:`\*Processor`; all others are named :class:`\*Handler`. .. attribute:: BaseHandler.parent A valid :class:`OpenerDirector`, which can be used to open using a different protocol, or handle errors. .. method:: BaseHandler.default_open(req) This method is *not* defined in :class:`BaseHandler`, but subclasses should define it if they want to catch all URLs. This method, if implemented, will be called by the parent :class:`OpenerDirector`. It should return a file-like object as described in the return value of the :meth:`open` of :class:`OpenerDirector`, or ``None``. It should raise :exc:`URLError`, unless a truly exceptional thing happens (for example, :exc:`MemoryError` should not be mapped to :exc:`URLError`). This method will be called before any protocol-specific open method. .. method:: BaseHandler.protocol_open(req) :noindex: ("protocol" is to be replaced by the protocol name.) This method is *not* defined in :class:`BaseHandler`, but subclasses should define it if they want to handle URLs with the given *protocol*. This method, if defined, will be called by the parent :class:`OpenerDirector`. Return values should be the same as for :meth:`default_open`. .. method:: BaseHandler.unknown_open(req) This method is *not* defined in :class:`BaseHandler`, but subclasses should define it if they want to catch all URLs with no specific registered handler to open it. This method, if implemented, will be called by the :attr:`parent` :class:`OpenerDirector`. Return values should be the same as for :meth:`default_open`. .. method:: BaseHandler.http_error_default(req, fp, code, msg, hdrs) This method is *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. *req* will be a :class:`Request` object, *fp* will be a file-like object with the HTTP error body, *code* will be the three-digit code of the error, *msg* will be the user-visible explanation of the code and *hdrs* will be a mapping object with the headers of the error. Return values and exceptions raised should be the same as those of :func:`urlopen`. .. method:: BaseHandler.http_error_nnn(req, fp, code, msg, hdrs) *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 *nnn* occurs. Subclasses should override this method to handle specific HTTP errors. Arguments, return values and exceptions raised should be the same as for :meth:`http_error_default`. .. method:: BaseHandler.protocol_request(req) :noindex: ("protocol" is to be replaced by the protocol name.) This method is *not* defined in :class:`BaseHandler`, but subclasses should define it if they want to pre-process requests of the given *protocol*. This method, if defined, will be called by the parent :class:`OpenerDirector`. *req* will be a :class:`Request` object. The return value should be a :class:`Request` object. .. method:: BaseHandler.protocol_response(req, response) :noindex: ("protocol" is to be replaced by the protocol name.) This method is *not* defined in :class:`BaseHandler`, but subclasses should define it if they want to post-process responses of the given *protocol*. This method, if defined, will be called by the parent :class:`OpenerDirector`. *req* will be a :class:`Request` object. *response* will be an object implementing the same interface as the return value of :func:`urlopen`. The return value should implement the same interface as the return value of :func:`urlopen`. .. _http-redirect-handler: HTTPRedirectHandler Objects --------------------------- .. note:: Some HTTP redirections require action from this module's client code. If this is the case, :exc:`HTTPError` is raised. See :rfc:`2616` for details of the precise meanings of the various redirection codes. .. method:: HTTPRedirectHandler.redirect_request(req, fp, code, msg, hdrs, newurl) Return a :class:`Request` or ``None`` in response to a redirect. This is called by the default implementations of the :meth:`http_error_30\*` methods when a redirection is received from the server. If a redirection should take place, return a new :class:`Request` to allow :meth:`http_error_30\*` to perform the redirect to *newurl*. Otherwise, raise :exc:`HTTPError` if no other handler should try to handle this URL, or return ``None`` if you can't but another handler might. .. note:: The default implementation of this method does not strictly follow :rfc:`2616`, which says that 301 and 302 responses to ``POST`` requests must not be automatically redirected without confirmation by the user. In reality, browsers do allow automatic redirection of these responses, changing the POST to a ``GET``, and the default implementation reproduces this behavior. .. method:: HTTPRedirectHandler.http_error_301(req, fp, code, msg, hdrs) Redirect to the ``Location:`` or ``URI:`` URL. This method is called by the parent :class:`OpenerDirector` when getting an HTTP 'moved permanently' response. .. method:: HTTPRedirectHandler.http_error_302(req, fp, code, msg, hdrs) The same as :meth:`http_error_301`, but called for the 'found' response. .. method:: HTTPRedirectHandler.http_error_303(req, fp, code, msg, hdrs) The same as :meth:`http_error_301`, but called for the 'see other' response. .. method:: HTTPRedirectHandler.http_error_307(req, fp, code, msg, hdrs) The same as :meth:`http_error_301`, but called for the 'temporary redirect' response. .. _http-cookie-processor: HTTPCookieProcessor Objects --------------------------- .. versionadded:: 2.4 :class:`HTTPCookieProcessor` instances have one attribute: .. attribute:: HTTPCookieProcessor.cookiejar The :class:`cookielib.CookieJar` in which cookies are stored. .. _proxy-handler: ProxyHandler Objects -------------------- .. method:: ProxyHandler.protocol_open(request) :noindex: ("protocol" is to be replaced by the protocol name.) The :class:`ProxyHandler` will have a method :samp:`{protocol}_open` for every *protocol* which has a proxy in the *proxies* dictionary given in the constructor. The method will modify requests to go through the proxy, by calling ``request.set_proxy()``, and call the next handler in the chain to actually execute the protocol. .. _http-password-mgr: HTTPPasswordMgr Objects ----------------------- These methods are available on :class:`HTTPPasswordMgr` and :class:`HTTPPasswordMgrWithDefaultRealm` objects. .. method:: HTTPPasswordMgr.add_password(realm, uri, user, passwd) *uri* can be either a single URI, or a sequence of URIs. *realm*, *user* and *passwd* must be strings. This causes ``(user, passwd)`` to be used as authentication tokens when authentication for *realm* and a super-URI of any of the given URIs is given. .. method:: HTTPPasswordMgr.find_user_password(realm, authuri) Get user/password for given realm and URI, if any. This method will return ``(None, None)`` if there is no matching user/password. For :class:`HTTPPasswordMgrWithDefaultRealm` objects, the realm ``None`` will be searched if the given *realm* has no matching user/password. .. _abstract-basic-auth-handler: AbstractBasicAuthHandler Objects -------------------------------- .. method:: AbstractBasicAuthHandler.http_error_auth_reqed(authreq, host, req, headers) Handle an authentication request by getting a user/password pair, and re-trying the request. *authreq* should be the name of the header where the information about the realm is included in the request, *host* specifies the URL and path to authenticate for, *req* should be the (failed) :class:`Request` object, and *headers* should be the error headers. *host* is either an authority (e.g. ``"python.org"``) or a URL containing an authority component (e.g. ``"http://python.org/"``). In either case, the authority must not contain a userinfo component (so, ``"python.org"`` and ``"python.org:80"`` are fine, ``"joe:password@python.org"`` is not). .. _http-basic-auth-handler: HTTPBasicAuthHandler Objects ---------------------------- .. method:: HTTPBasicAuthHandler.http_error_401(req, fp, code, msg, hdrs) Retry the request with authentication information, if available. .. _proxy-basic-auth-handler: ProxyBasicAuthHandler Objects ----------------------------- .. method:: ProxyBasicAuthHandler.http_error_407(req, fp, code, msg, hdrs) Retry the request with authentication information, if available. .. _abstract-digest-auth-handler: AbstractDigestAuthHandler Objects --------------------------------- .. method:: AbstractDigestAuthHandler.http_error_auth_reqed(authreq, host, req, headers) *authreq* should be the name of the header where the information about the realm is included in the request, *host* should be the host to authenticate to, *req* should be the (failed) :class:`Request` object, and *headers* should be the error headers. .. _http-digest-auth-handler: HTTPDigestAuthHandler Objects ----------------------------- .. method:: HTTPDigestAuthHandler.http_error_401(req, fp, code, msg, hdrs) Retry the request with authentication information, if available. .. _proxy-digest-auth-handler: ProxyDigestAuthHandler Objects ------------------------------ .. method:: ProxyDigestAuthHandler.http_error_407(req, fp, code, msg, hdrs) Retry the request with authentication information, if available. .. _http-handler-objects: HTTPHandler Objects ------------------- .. method:: HTTPHandler.http_open(req) Send an HTTP request, which can be either GET or POST, depending on ``req.has_data()``. .. _https-handler-objects: HTTPSHandler Objects -------------------- .. method:: HTTPSHandler.https_open(req) Send an HTTPS request, which can be either GET or POST, depending on ``req.has_data()``. .. _file-handler-objects: FileHandler Objects ------------------- .. method:: FileHandler.file_open(req) Open the file locally, if there is no host name, or the host name is ``'localhost'``. Change the protocol to ``ftp`` otherwise, and retry opening it using :attr:`parent`. .. _ftp-handler-objects: FTPHandler Objects ------------------ .. method:: FTPHandler.ftp_open(req) Open the FTP file indicated by *req*. The login is always done with empty username and password. .. _cacheftp-handler-objects: CacheFTPHandler Objects ----------------------- :class:`CacheFTPHandler` objects are :class:`FTPHandler` objects with the following additional methods: .. method:: CacheFTPHandler.setTimeout(t) Set timeout of connections to *t* seconds. .. method:: CacheFTPHandler.setMaxConns(m) Set maximum number of cached connections to *m*. .. _unknown-handler-objects: UnknownHandler Objects ---------------------- .. method:: UnknownHandler.unknown_open() Raise a :exc:`URLError` exception. .. _http-error-processor-objects: HTTPErrorProcessor Objects -------------------------- .. versionadded:: 2.4 .. method:: HTTPErrorProcessor.http_response() Process HTTP error responses. For 200 error codes, the response object is returned immediately. For non-200 error codes, this simply passes the job on to the :samp:`{protocol}_error_code` handler methods, via :meth:`OpenerDirector.error`. Eventually, :class:`urllib2.HTTPDefaultErrorHandler` will raise an :exc:`HTTPError` if no other handler handles the error. .. method:: HTTPErrorProcessor.https_response() Process HTTPS error responses. The behavior is same as :meth:`http_response`. .. _urllib2-examples: Examples -------- In addition to the examples below, more examples are given in :ref:`urllib-howto`. This example gets the python.org main page and displays the first 100 bytes of it:: >>> import urllib2 >>> f = urllib2.urlopen('http://www.python.org/') >>> print f.read(100) >> import urllib2 >>> req = urllib2.Request(url='https://localhost/cgi-bin/test.cgi', ... data='This data is passed to stdin of the CGI') >>> f = urllib2.urlopen(req) >>> print f.read() Got Data: "This data is passed to stdin of the CGI" The code for the sample CGI used in the above example is:: #!/usr/bin/env python import sys data = sys.stdin.read() print 'Content-type: text-plain\n\nGot Data: "%s"' % data Use of Basic HTTP Authentication:: import urllib2 # Create an OpenerDirector with support for Basic HTTP Authentication... auth_handler = urllib2.HTTPBasicAuthHandler() auth_handler.add_password(realm='PDQ Application', uri='https://mahler:8092/site-updates.py', user='klem', passwd='kadidd!ehopper') opener = urllib2.build_opener(auth_handler) # ...and install it globally so it can be used with urlopen. urllib2.install_opener(opener) urllib2.urlopen('http://www.example.com/login.html') :func:`build_opener` provides many handlers by default, including a :class:`ProxyHandler`. By default, :class:`ProxyHandler` uses the environment variables named ``_proxy``, where ```` is the URL scheme involved. For example, the :envvar:`http_proxy` environment variable is read to obtain the HTTP proxy's URL. This example replaces the default :class:`ProxyHandler` with one that uses programmatically-supplied proxy URLs, and adds proxy authorization support with :class:`ProxyBasicAuthHandler`. :: proxy_handler = urllib2.ProxyHandler({'http': 'http://www.example.com:3128/'}) proxy_auth_handler = urllib2.ProxyBasicAuthHandler() proxy_auth_handler.add_password('realm', 'host', 'username', 'password') opener = urllib2.build_opener(proxy_handler, proxy_auth_handler) # This time, rather than install the OpenerDirector, we use it directly: opener.open('http://www.example.com/login.html') Adding HTTP headers: Use the *headers* argument to the :class:`Request` constructor, or:: import urllib2 req = urllib2.Request('http://www.example.com/') req.add_header('Referer', 'http://www.python.org/') # Customize the default User-Agent header value: req.add_header('User-Agent', 'urllib-example/0.1 (Contact: . . .)') r = urllib2.urlopen(req) :class:`OpenerDirector` automatically adds a :mailheader:`User-Agent` header to every :class:`Request`. To change this:: import urllib2 opener = urllib2.build_opener() opener.addheaders = [('User-agent', 'Mozilla/5.0')] opener.open('http://www.example.com/') Also, remember that a few standard headers (:mailheader:`Content-Length`, :mailheader:`Content-Type` and :mailheader:`Host`) are added when the :class:`Request` is passed to :func:`urlopen` (or :meth:`OpenerDirector.open`).