path: root/Doc/lib/libhttplib.tex

\section{\module{httplib} ---
         HTTP protocol client}

\declaremodule{standard}{httplib}
\modulesynopsis{HTTP and HTTPS protocol client (requires sockets).}

\indexii{HTTP}{protocol}
\index{HTTP!\module{httplib} (standard module)}

This module defines classes which implement the client side of the
HTTP and HTTPS protocols.  It is normally not used directly --- the
module \refmodule{urllib}\refstmodindex{urllib} uses it to handle URLs
that use HTTP and HTTPS.

\begin{notice}
  HTTPS support is only available if the \refmodule{socket} module was
  compiled with SSL support.
\end{notice}

\begin{notice}
  The public interface for this module changed substantially in Python
  2.0.  The \class{HTTP} class is retained only for backward
  compatibility with 1.5.2.  It should not be used in new code.  Refer
  to the online docstrings for usage.
\end{notice}

The module provides the following classes:

\begin{classdesc}{HTTPConnection}{host\optional{, port\optional{,
		  strict\optional{, timeout}}}}
An \class{HTTPConnection} instance represents one transaction with an HTTP
server.  It should be instantiated passing it a host and optional port number.
If no port number is passed, the port is extracted from the host string if it
has the form \code{\var{host}:\var{port}}, else the default HTTP port (80) is
used.  
When True the optional parameter \var{strict}
causes \code{BadStatusLine} to be raised if the status line can't be parsed
as a valid HTTP/1.0 or 1.1 status line.  If the optional \var{timeout}
parameter is given, connection attempts will timeout after that many
seconds (if no timeout is passed, or is passed as None, the global default 
timeout setting is used).

For example, the following calls all create instances that connect to
the server at the same host and port:

\begin{verbatim}
>>> h1 = httplib.HTTPConnection('www.cwi.nl')
>>> h2 = httplib.HTTPConnection('www.cwi.nl:80')
>>> h3 = httplib.HTTPConnection('www.cwi.nl', 80)
>>> h3 = httplib.HTTPConnection('www.cwi.nl', 80, timeout=10)
\end{verbatim}
\versionadded{2.0}
\end{classdesc}

\begin{classdesc}{HTTPSConnection}{host\optional{, port, key_file, cert_file}}
A subclass of \class{HTTPConnection} that uses SSL for communication with
secure servers.  Default port is \code{443}.
\var{key_file} is
the name of a PEM formatted file that contains your private
key. \var{cert_file} is a PEM formatted certificate chain file.

\warning{This does not do any certificate verification!}

\versionadded{2.0}
\end{classdesc}

\begin{classdesc}{HTTPResponse}{sock\optional{, debuglevel=0}\optional{, strict=0}}
Class whose instances are returned upon successful connection.  Not
instantiated directly by user.
\versionadded{2.0}
\end{classdesc}

The following exceptions are raised as appropriate:

\begin{excdesc}{HTTPException}
The base class of the other exceptions in this module.  It is a
subclass of \exception{Exception}.
\versionadded{2.0}
\end{excdesc}

\begin{excdesc}{NotConnected}
A subclass of \exception{HTTPException}.
\versionadded{2.0}
\end{excdesc}

\begin{excdesc}{InvalidURL}
A subclass of \exception{HTTPException}, raised if a port is given and is
either non-numeric or empty.
\versionadded{2.3}
\end{excdesc}

\begin{excdesc}{UnknownProtocol}
A subclass of \exception{HTTPException}.
\versionadded{2.0}
\end{excdesc}

\begin{excdesc}{UnknownTransferEncoding}
A subclass of \exception{HTTPException}.
\versionadded{2.0}
\end{excdesc}

\begin{excdesc}{UnimplementedFileMode}
A subclass of \exception{HTTPException}.
\versionadded{2.0}
\end{excdesc}

\begin{excdesc}{IncompleteRead}
A subclass of \exception{HTTPException}.
\versionadded{2.0}
\end{excdesc}

\begin{excdesc}{ImproperConnectionState}
A subclass of \exception{HTTPException}.
\versionadded{2.0}
\end{excdesc}

\begin{excdesc}{CannotSendRequest}
A subclass of \exception{ImproperConnectionState}.
\versionadded{2.0}
\end{excdesc}

\begin{excdesc}{CannotSendHeader}
A subclass of \exception{ImproperConnectionState}.
\versionadded{2.0}
\end{excdesc}

\begin{excdesc}{ResponseNotReady}
A subclass of \exception{ImproperConnectionState}.
\versionadded{2.0}
\end{excdesc}

\begin{excdesc}{BadStatusLine}
A subclass of \exception{HTTPException}.  Raised if a server responds with a
HTTP status code that we don't understand.
\versionadded{2.0}
\end{excdesc}

The constants defined in this module are:

\begin{datadesc}{HTTP_PORT}
  The default port for the HTTP protocol (always \code{80}).
\end{datadesc}

\begin{datadesc}{HTTPS_PORT}
  The default port for the HTTPS protocol (always \code{443}).
\end{datadesc}

and also the following constants for integer status codes:

\begin{tableiii}{l|c|l}{constant}{Constant}{Value}{Definition}
  \lineiii{CONTINUE}{\code{100}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.1.1}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.1.1}}
  \lineiii{SWITCHING_PROTOCOLS}{\code{101}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.1.2}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.1.2}}
  \lineiii{PROCESSING}{\code{102}}
    {WEBDAV, \ulink{RFC 2518, Section 10.1}
      {http://www.webdav.org/specs/rfc2518.html#STATUS_102}}

  \lineiii{OK}{\code{200}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.2.1}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.2.1}}
  \lineiii{CREATED}{\code{201}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.2.2}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.2.2}}
  \lineiii{ACCEPTED}{\code{202}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.2.3}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.2.3}}
  \lineiii{NON_AUTHORITATIVE_INFORMATION}{\code{203}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.2.4}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.2.4}}
  \lineiii{NO_CONTENT}{\code{204}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.2.5}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.2.5}}
  \lineiii{RESET_CONTENT}{\code{205}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.2.6}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.2.6}}
  \lineiii{PARTIAL_CONTENT}{\code{206}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.2.7}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.2.7}}
  \lineiii{MULTI_STATUS}{\code{207}}
    {WEBDAV \ulink{RFC 2518, Section 10.2}
      {http://www.webdav.org/specs/rfc2518.html#STATUS_207}}
  \lineiii{IM_USED}{\code{226}}
    {Delta encoding in HTTP, \rfc{3229}, Section 10.4.1}

  \lineiii{MULTIPLE_CHOICES}{\code{300}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.3.1}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.3.1}}
  \lineiii{MOVED_PERMANENTLY}{\code{301}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.3.2}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.3.2}}
  \lineiii{FOUND}{\code{302}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.3.3}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.3.3}}
  \lineiii{SEE_OTHER}{\code{303}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.3.4}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.3.4}}
  \lineiii{NOT_MODIFIED}{\code{304}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.3.5}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.3.5}}
  \lineiii{USE_PROXY}{\code{305}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.3.6}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.3.6}}
  \lineiii{TEMPORARY_REDIRECT}{\code{307}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.3.8}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.3.8}}

  \lineiii{BAD_REQUEST}{\code{400}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.4.1}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.1}}
  \lineiii{UNAUTHORIZED}{\code{401}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.4.2}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.2}}
  \lineiii{PAYMENT_REQUIRED}{\code{402}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.4.3}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.3}}
  \lineiii{FORBIDDEN}{\code{403}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.4.4}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.4}}
  \lineiii{NOT_FOUND}{\code{404}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.4.5}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.5}}
  \lineiii{METHOD_NOT_ALLOWED}{\code{405}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.4.6}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.6}}
  \lineiii{NOT_ACCEPTABLE}{\code{406}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.4.7}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.7}}
  \lineiii{PROXY_AUTHENTICATION_REQUIRED}
    {\code{407}}{HTTP/1.1, \ulink{RFC 2616, Section 10.4.8}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.8}}
  \lineiii{REQUEST_TIMEOUT}{\code{408}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.4.9}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.9}}
  \lineiii{CONFLICT}{\code{409}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.4.10}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.10}}
  \lineiii{GONE}{\code{410}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.4.11}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.11}}
  \lineiii{LENGTH_REQUIRED}{\code{411}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.4.12}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.12}}
  \lineiii{PRECONDITION_FAILED}{\code{412}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.4.13}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.13}}
  \lineiii{REQUEST_ENTITY_TOO_LARGE}
    {\code{413}}{HTTP/1.1, \ulink{RFC 2616, Section 10.4.14}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.14}}
  \lineiii{REQUEST_URI_TOO_LONG}{\code{414}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.4.15}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.15}}
  \lineiii{UNSUPPORTED_MEDIA_TYPE}{\code{415}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.4.16}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.16}}
  \lineiii{REQUESTED_RANGE_NOT_SATISFIABLE}{\code{416}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.4.17}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.17}}
  \lineiii{EXPECTATION_FAILED}{\code{417}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.4.18}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.18}}
  \lineiii{UNPROCESSABLE_ENTITY}{\code{422}}
    {WEBDAV, \ulink{RFC 2518, Section 10.3}
      {http://www.webdav.org/specs/rfc2518.html#STATUS_422}}
  \lineiii{LOCKED}{\code{423}}
    {WEBDAV \ulink{RFC 2518, Section 10.4}
      {http://www.webdav.org/specs/rfc2518.html#STATUS_423}}
  \lineiii{FAILED_DEPENDENCY}{\code{424}}
    {WEBDAV, \ulink{RFC 2518, Section 10.5}
      {http://www.webdav.org/specs/rfc2518.html#STATUS_424}}
  \lineiii{UPGRADE_REQUIRED}{\code{426}}
    {HTTP Upgrade to TLS, \rfc{2817}, Section 6}

  \lineiii{INTERNAL_SERVER_ERROR}{\code{500}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.5.1}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.5.1}}
  \lineiii{NOT_IMPLEMENTED}{\code{501}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.5.2}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.5.2}}
  \lineiii{BAD_GATEWAY}{\code{502}}
    {HTTP/1.1 \ulink{RFC 2616, Section 10.5.3}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.5.3}}
  \lineiii{SERVICE_UNAVAILABLE}{\code{503}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.5.4}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.5.4}}
  \lineiii{GATEWAY_TIMEOUT}{\code{504}}
    {HTTP/1.1 \ulink{RFC 2616, Section 10.5.5}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.5.5}}
  \lineiii{HTTP_VERSION_NOT_SUPPORTED}{\code{505}}
    {HTTP/1.1, \ulink{RFC 2616, Section 10.5.6}
      {http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.5.6}}
  \lineiii{INSUFFICIENT_STORAGE}{\code{507}}
    {WEBDAV, \ulink{RFC 2518, Section 10.6}
      {http://www.webdav.org/specs/rfc2518.html#STATUS_507}}
  \lineiii{NOT_EXTENDED}{\code{510}}
    {An HTTP Extension Framework, \rfc{2774}, Section 7}
\end{tableiii}

\begin{datadesc}{responses}
This dictionary maps the HTTP 1.1 status codes to the W3C names.

Example: \code{httplib.responses[httplib.NOT_FOUND]} is \code{'Not Found'}.
\versionadded{2.5}
\end{datadesc}


\subsection{HTTPConnection Objects \label{httpconnection-objects}}

\class{HTTPConnection} instances have the following methods:

\begin{methoddesc}{request}{method, url\optional{, body\optional{, headers}}}
This will send a request to the server using the HTTP request method
\var{method} and the selector \var{url}.  If the \var{body} argument is
present, it should be a string of data to send after the headers are finished.
Alternatively, it may be an open file object, in which case the
contents of the file is sent; this file object should support
\code{fileno()} and \code{read()} methods.
The header Content-Length is automatically set to the correct value.
The \var{headers} argument should be a mapping of extra HTTP headers to send
with the request.

\versionchanged[\var{body} can be a file object]{2.6}
\end{methoddesc}

\begin{methoddesc}{getresponse}{}
Should be called after a request is sent to get the response from the server.
Returns an \class{HTTPResponse} instance.
\note{Note that you must have read the whole response before you can send a new
request to the server.}
\end{methoddesc}

\begin{methoddesc}{set_debuglevel}{level}
Set the debugging level (the amount of debugging output printed).
The default debug level is \code{0}, meaning no debugging output is
printed.
\end{methoddesc}

\begin{methoddesc}{connect}{}
Connect to the server specified when the object was created.
\end{methoddesc}

\begin{methoddesc}{close}{}
Close the connection to the server.
\end{methoddesc}

As an alternative to using the \method{request()} method described above,
you can also send your request step by step, by using the four functions
below.

\begin{methoddesc}{putrequest}{request, selector\optional{,
skip\_host\optional{, skip_accept_encoding}}}
This should be the first call after the connection to the server has
been made.  It sends a line to the server consisting of the
\var{request} string, the \var{selector} string, and the HTTP version
(\code{HTTP/1.1}).  To disable automatic sending of \code{Host:} or
\code{Accept-Encoding:} headers (for example to accept additional
content encodings), specify \var{skip_host} or \var{skip_accept_encoding}
with non-False values.
\versionchanged[\var{skip_accept_encoding} argument added]{2.4}
\end{methoddesc}

\begin{methoddesc}{putheader}{header, argument\optional{, ...}}
Send an \rfc{822}-style header to the server.  It sends a line to the
server consisting of the header, a colon and a space, and the first
argument.  If more arguments are given, continuation lines are sent,
each consisting of a tab and an argument.
\end{methoddesc}

\begin{methoddesc}{endheaders}{}
Send a blank line to the server, signalling the end of the headers.
\end{methoddesc}

\begin{methoddesc}{send}{data}
Send data to the server.  This should be used directly only after the
\method{endheaders()} method has been called and before
\method{getresponse()} is called.
\end{methoddesc}

\subsection{HTTPResponse Objects \label{httpresponse-objects}}

\class{HTTPResponse} instances have the following methods and attributes:

\begin{methoddesc}{read}{\optional{amt}}
Reads and returns the response body, or up to the next \var{amt} bytes.
\end{methoddesc}

\begin{methoddesc}{getheader}{name\optional{, default}}
Get the contents of the header \var{name}, or \var{default} if there is no
matching header.
\end{methoddesc}

\begin{methoddesc}{getheaders}{}
Return a list of (header, value) tuples. \versionadded{2.4}
\end{methoddesc}

\begin{datadesc}{msg}
  A \class{mimetools.Message} instance containing the response headers.
\end{datadesc}

\begin{datadesc}{version}
  HTTP protocol version used by server.  10 for HTTP/1.0, 11 for HTTP/1.1.
\end{datadesc}

\begin{datadesc}{status}
  Status code returned by server.
\end{datadesc}

\begin{datadesc}{reason}
  Reason phrase returned by server.
\end{datadesc}


\subsection{Examples \label{httplib-examples}}

Here is an example session that uses the \samp{GET} method:

\begin{verbatim}
>>> import httplib
>>> conn = httplib.HTTPConnection("www.python.org")
>>> conn.request("GET", "/index.html")
>>> r1 = conn.getresponse()
>>> print r1.status, r1.reason
200 OK
>>> data1 = r1.read()
>>> conn.request("GET", "/parrot.spam")
>>> r2 = conn.getresponse()
>>> print r2.status, r2.reason
404 Not Found
>>> data2 = r2.read()
>>> conn.close()
\end{verbatim}

Here is an example session that shows how to \samp{POST} requests:

\begin{verbatim}
>>> import httplib, urllib
>>> params = urllib.urlencode({'spam': 1, 'eggs': 2, 'bacon': 0})
>>> headers = {"Content-type": "application/x-www-form-urlencoded",
...            "Accept": "text/plain"}
>>> conn = httplib.HTTPConnection("musi-cal.mojam.com:80")
>>> conn.request("POST", "/cgi-bin/query", params, headers)
>>> response = conn.getresponse()
>>> print response.status, response.reason
200 OK
>>> data = response.read()
>>> conn.close()
\end{verbatim}