cpython/Doc/lib/emailutil.tex

\declaremodule{standard}{email.Utils}
\modulesynopsis{Miscellaneous email package utilities.}

There are several useful utilities provided with the \module{email}
package.

\begin{funcdesc}{quote}{str}
Return a new string with backslashes in \var{str} replaced by two
backslashes and double quotes replaced by backslash-double quote.
\end{funcdesc}

\begin{funcdesc}{unquote}{str}
Return a new string which is an \emph{unquoted} version of \var{str}.
If \var{str} ends and begins with double quotes, they are stripped
off.  Likewise if \var{str} ends and begins with angle brackets, they
are stripped off.
\end{funcdesc}

\begin{funcdesc}{parseaddr}{address}
Parse address -- which should be the value of some address-containing
field such as \mailheader{To} or \mailheader{Cc} -- into its constituent
\emph{realname} and \emph{email address} parts.  Returns a tuple of that
information, unless the parse fails, in which case a 2-tuple of
\code{(None, None)} is returned.
\end{funcdesc}

\begin{funcdesc}{dump_address_pair}{pair}
The inverse of \method{parseaddr()}, this takes a 2-tuple of the form
\code{(realname, email_address)} and returns the string value suitable
for a \mailheader{To} or \mailheader{Cc} header.  If the first element of
\var{pair} is false, then the second element is returned unmodified.
\end{funcdesc}

\begin{funcdesc}{getaddresses}{fieldvalues}
This method returns a list of 2-tuples of the form returned by
\code{parseaddr()}.  \var{fieldvalues} is a sequence of header field
values as might be returned by \method{Message.get_all()}.  Here's a
simple example that gets all the recipients of a message:

\begin{verbatim}
from email.Utils import getaddresses

tos = msg.get_all('to', [])
ccs = msg.get_all('cc', [])
resent_tos = msg.get_all('resent-to', [])
resent_ccs = msg.get_all('resent-cc', [])
all_recipients = getaddresses(tos + ccs + resent_tos + resent_ccs)
\end{verbatim}
\end{funcdesc}

\begin{funcdesc}{decode}{s}
This method decodes a string according to the rules in \rfc{2047}.  It
returns the decoded string as a Python unicode string.
\end{funcdesc}

\begin{funcdesc}{encode}{s\optional{, charset\optional{, encoding}}}
This method encodes a string according to the rules in \rfc{2047}.  It
is not actually the inverse of \function{decode()} since it doesn't
handle multiple character sets or multiple string parts needing
encoding.  In fact, the input string \var{s} must already be encoded
in the \var{charset} character set (Python can't reliably guess what
character set a string might be encoded in).  The default
\var{charset} is \samp{iso-8859-1}.

\var{encoding} must be either the letter \character{q} for
Quoted-Printable or \character{b} for Base64 encoding.  If
neither, a \exception{ValueError} is raised.  Both the \var{charset} and
the \var{encoding} strings are case-insensitive, and coerced to lower
case in the returned string.
\end{funcdesc}

\begin{funcdesc}{parsedate}{date}
Attempts to parse a date according to the rules in \rfc{2822}.
however, some mailers don't follow that format as specified, so
\function{parsedate()} tries to guess correctly in such cases. 
\var{date} is a string containing an \rfc{2822} date, such as 
\code{"Mon, 20 Nov 1995 19:12:08 -0500"}.  If it succeeds in parsing
the date, \function{parsedate()} returns a 9-tuple that can be passed
directly to \function{time.mktime()}; otherwise \code{None} will be
returned.  Note that fields 6, 7, and 8 of the result tuple are not
usable.
\end{funcdesc}

\begin{funcdesc}{parsedate_tz}{date}
Performs the same function as \function{parsedate()}, but returns
either \code{None} or a 10-tuple; the first 9 elements make up a tuple
that can be passed directly to \function{time.mktime()}, and the tenth
is the offset of the date's timezone from UTC (which is the official
term for Greenwich Mean Time)\footnote{Note that the sign of the timezone
offset is the opposite of the sign of the \code{time.timezone}
variable for the same timezone; the latter variable follows the
\POSIX{} standard while this module follows \rfc{2822}.}.  If the input
string has no timezone, the last element of the tuple returned is
\code{None}.  Note that fields 6, 7, and 8 of the result tuple are not
usable.
\end{funcdesc}

\begin{funcdesc}{mktime_tz}{tuple}
Turn a 10-tuple as returned by \function{parsedate_tz()} into a UTC
timestamp.  It the timezone item in the tuple is \code{None}, assume
local time.  Minor deficiency: \function{mktime_tz()} interprets the
first 8 elements of \var{tuple} as a local time and then compensates
for the timezone difference.  This may yield a slight error around
changes in daylight savings time, though not worth worrying about for
common use.
\end{funcdesc}

\begin{funcdesc}{formatdate}{\optional{timeval\optional{, localtime}}}
Returns a date string as per Internet standard \rfc{2822}, e.g.:

\begin{verbatim}
Fri, 09 Nov 2001 01:08:47 -0000
\end{verbatim}

Optional \var{timeval} if given is a floating point time value as
accepted by \function{time.gmtime()} and \function{time.localtime()},
otherwise the current time is used.

Optional \var{localtime} is a flag that when true, interprets
\var{timeval}, and returns a date relative to the local timezone
instead of UTC, properly taking daylight savings time into account.
\end{funcdesc}