wget.1

Wget很好的处理了http和ftp的下载,很值得学习的经典代码

.\" Automatically generated by Pod::Man v1.37, Pod::Parser v1.32
.\"
.\" Standard preamble:
.\" ========================================================================
.de Sh \" Subsection heading
.br
.if t .Sp
.ne 5
.PP
\fB\\$1\fR
.PP
..
.de Sp \" Vertical space (when we can't use .PP)
.if t .sp .5v
.if n .sp
..
.de Vb \" Begin verbatim text
.ft CW
.nf
.ne \\$1
..
.de Ve \" End verbatim text
.ft R
.fi
..
.\" Set up some character translations and predefined strings.  \*(-- will
.\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
.\" double quote, and \*(R" will give a right double quote.  | will give a
.\" real vertical bar.  \*(C+ will give a nicer C++.  Capital omega is used to
.\" do unbreakable dashes and therefore won't be available.  \*(C` and \*(C'
.\" expand to `' in nroff, nothing in troff, for use with C<>.
.tr \(*W-|\(bv\*(Tr
.ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
.ie n \{\
.    ds -- \(*W-
.    ds PI pi
.    if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
.    if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\"  diablo 12 pitch
.    ds L" ""
.    ds R" ""
.    ds C` ""
.    ds C' ""
'br\}
.el\{\
.    ds -- \|\(em\|
.    ds PI \(*p
.    ds L" ``
.    ds R" ''
'br\}
.\"
.\" If the F register is turned on, we'll generate index entries on stderr for
.\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index
.\" entries marked with X<> in POD.  Of course, you'll have to process the
.\" output yourself in some meaningful fashion.
.if \nF \{\
.    de IX
.    tm Index:\\$1\t\\n%\t"\\$2"
..
.    nr % 0
.    rr F
.\}
.\"
.\" For nroff, turn off justification.  Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents.
.hy 0
.if n .na
.\"
.\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
.\" Fear.  Run.  Save yourself.  No user-serviceable parts.
.    \" fudge factors for nroff and troff
.if n \{\
.    ds #H 0
.    ds #V .8m
.    ds #F .3m
.    ds #[ \f1
.    ds #] \fP
.\}
.if t \{\
.    ds #H ((1u-(\\\\n(.fu%2u))*.13m)
.    ds #V .6m
.    ds #F 0
.    ds #[ \&
.    ds #] \&
.\}
.    \" simple accents for nroff and troff
.if n \{\
.    ds ' \&
.    ds ` \&
.    ds ^ \&
.    ds , \&
.    ds ~ ~
.    ds /
.\}
.if t \{\
.    ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
.    ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
.    ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
.    ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
.    ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
.    ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
.\}
.    \" troff and (daisy-wheel) nroff accents
.ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
.ds 8 \h'\*(#H'\(*b\h'-\*(#H'
.ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
.ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
.ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
.ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
.ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
.ds ae a\h'-(\w'a'u*4/10)'e
.ds Ae A\h'-(\w'A'u*4/10)'E
.    \" corrections for vroff
.if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
.if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
.    \" for low resolution devices (crt and lpr)
.if \n(.H>23 .if \n(.V>19 \
\{\
.    ds : e
.    ds 8 ss
.    ds o a
.    ds d- d\h'-1'\(ga
.    ds D- D\h'-1'\(hy
.    ds th \o'bp'
.    ds Th \o'LP'
.    ds ae ae
.    ds Ae AE
.\}
.rm #[ #] #H #V #F C
.\" ========================================================================
.\"
.IX Title "WGET 1"
.TH WGET 1 "2008-03-24" "GNU Wget 1.11.1" "GNU Wget"
.SH "NAME"
Wget \- The non\-interactive network downloader.
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
wget [\fIoption\fR]... [\fI\s-1URL\s0\fR]...
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
\&\s-1GNU\s0 Wget is a free utility for non-interactive download of files from
the Web.  It supports \s-1HTTP\s0, \s-1HTTPS\s0, and \s-1FTP\s0 protocols, as
well as retrieval through \s-1HTTP\s0 proxies.
.PP
Wget is non\-interactive, meaning that it can work in the background,
while the user is not logged on.  This allows you to start a retrieval
and disconnect from the system, letting Wget finish the work.  By
contrast, most of the Web browsers require constant user's presence,
which can be a great hindrance when transferring a lot of data.
.PP
Wget can follow links in \s-1HTML\s0 and \s-1XHTML\s0 pages and create local 
versions of remote web sites, fully recreating the directory structure of 
the original site.  This is sometimes referred to as \*(L"recursive
downloading.\*(R"  While doing that, Wget respects the Robot Exclusion
Standard (\fI/robots.txt\fR).  Wget can be instructed to convert the
links in downloaded \s-1HTML\s0 files to the local files for offline
viewing.
.PP
Wget has been designed for robustness over slow or unstable network
connections; if a download fails due to a network problem, it will
keep retrying until the whole file has been retrieved.  If the server
supports regetting, it will instruct the server to continue the
download from where it left off.
.SH "OPTIONS"
.IX Header "OPTIONS"
.Sh "Option Syntax"
.IX Subsection "Option Syntax"
Since Wget uses \s-1GNU\s0 getopt to process command-line arguments, every
option has a long form along with the short one.  Long options are
more convenient to remember, but take time to type.  You may freely
mix different option styles, or specify options after the command-line
arguments.  Thus you may write:
.PP
.Vb 1
\&        wget -r --tries=10 http://fly.srk.fer.hr/ -o log
.Ve
.PP
The space between the option accepting an argument and the argument may
be omitted.  Instead of \fB\-o log\fR you can write \fB\-olog\fR.
.PP
You may put several options that do not require arguments together,
like:
.PP
.Vb 1
\&        wget -drc <URL>
.Ve
.PP
This is a complete equivalent of:
.PP
.Vb 1
\&        wget -d -r -c <URL>
.Ve
.PP
Since the options can be specified after the arguments, you may
terminate them with \fB\-\-\fR.  So the following will try to download
\&\s-1URL\s0 \fB\-x\fR, reporting failure to \fIlog\fR:
.PP
.Vb 1
\&        wget -o log -- -x
.Ve
.PP
The options that accept comma-separated lists all respect the convention
that specifying an empty list clears its value.  This can be useful to
clear the \fI.wgetrc\fR settings.  For instance, if your \fI.wgetrc\fR
sets \f(CW\*(C`exclude_directories\*(C'\fR to \fI/cgi\-bin\fR, the following
example will first reset it, and then set it to exclude \fI/~nobody\fR
and \fI/~somebody\fR.  You can also clear the lists in \fI.wgetrc\fR.
.PP
.Vb 1
\&        wget -X " -X /~nobody,/~somebody
.Ve
.PP
Most options that do not accept arguments are \fIboolean\fR options,
so named because their state can be captured with a yes-or-no
(\*(L"boolean\*(R") variable.  For example, \fB\-\-follow\-ftp\fR tells Wget
to follow \s-1FTP\s0 links from \s-1HTML\s0 files and, on the other hand,
\&\fB\-\-no\-glob\fR tells it not to perform file globbing on \s-1FTP\s0 URLs.  A
boolean option is either \fIaffirmative\fR or \fInegative\fR
(beginning with \fB\-\-no\fR).  All such options share several
properties.
.PP
Unless stated otherwise, it is assumed that the default behavior is
the opposite of what the option accomplishes.  For example, the
documented existence of \fB\-\-follow\-ftp\fR assumes that the default
is to \fInot\fR follow \s-1FTP\s0 links from \s-1HTML\s0 pages.
.PP
Affirmative options can be negated by prepending the \fB\-\-no\-\fR to
the option name; negative options can be negated by omitting the
\&\fB\-\-no\-\fR prefix.  This might seem superfluous\-\-\-if the default for
an affirmative option is to not do something, then why provide a way
to explicitly turn it off?  But the startup file may in fact change
the default.  For instance, using \f(CW\*(C`follow_ftp = off\*(C'\fR in
\&\fI.wgetrc\fR makes Wget \fInot\fR follow \s-1FTP\s0 links by default, and
using \fB\-\-no\-follow\-ftp\fR is the only way to restore the factory
default from the command line.
.Sh "Basic Startup Options"
.IX Subsection "Basic Startup Options"
.IP "\fB\-V\fR" 4
.IX Item "-V"
.PD 0
.IP "\fB\-\-version\fR" 4
.IX Item "--version"
.PD
Display the version of Wget.
.IP "\fB\-h\fR" 4
.IX Item "-h"
.PD 0
.IP "\fB\-\-help\fR" 4
.IX Item "--help"
.PD
Print a help message describing all of Wget's command-line options.
.IP "\fB\-b\fR" 4
.IX Item "-b"
.PD 0
.IP "\fB\-\-background\fR" 4
.IX Item "--background"
.PD
Go to background immediately after startup.  If no output file is
specified via the \fB\-o\fR, output is redirected to \fIwget-log\fR.
.IP "\fB\-e\fR \fIcommand\fR" 4
.IX Item "-e command"
.PD 0
.IP "\fB\-\-execute\fR \fIcommand\fR" 4
.IX Item "--execute command"
.PD
Execute \fIcommand\fR as if it were a part of \fI.wgetrc\fR.  A command thus invoked will be executed
\&\fIafter\fR the commands in \fI.wgetrc\fR, thus taking precedence over
them.  If you need to specify more than one wgetrc command, use multiple
instances of \fB\-e\fR.
.Sh "Logging and Input File Options"
.IX Subsection "Logging and Input File Options"
.IP "\fB\-o\fR \fIlogfile\fR" 4
.IX Item "-o logfile"
.PD 0
.IP "\fB\-\-output\-file=\fR\fIlogfile\fR" 4
.IX Item "--output-file=logfile"
.PD
Log all messages to \fIlogfile\fR.  The messages are normally reported
to standard error.
.IP "\fB\-a\fR \fIlogfile\fR" 4
.IX Item "-a logfile"
.PD 0
.IP "\fB\-\-append\-output=\fR\fIlogfile\fR" 4
.IX Item "--append-output=logfile"
.PD
Append to \fIlogfile\fR.  This is the same as \fB\-o\fR, only it appends
to \fIlogfile\fR instead of overwriting the old log file.  If
\&\fIlogfile\fR does not exist, a new file is created.
.IP "\fB\-d\fR" 4
.IX Item "-d"
.PD 0
.IP "\fB\-\-debug\fR" 4
.IX Item "--debug"
.PD
Turn on debug output, meaning various information important to the
developers of Wget if it does not work properly.  Your system