From: John Browning <listguy@...>
Date: 2007-02-27T04:48:36+09:00
Subject: Re: [QUIZ] Mailing List Files (#115)

--Apple-Mail-2-938571758
Content-Transfer-Encoding: 7bit
Content-Type: text/plain;
	charset=US-ASCII;
	delsp=yes;
	format=flowed

#!/usr/bin/env ruby
#

require 'net/http'
require 'strscan'
require 'cgi'

class GetAttachments
   def initialize(id)
     @id = id
     @url = "blade.nagaokaut.ac.jp"
     @params = "/cgi-bin/scat.rb/ruby/ruby-talk/" + @id
     @attachments = Array.new
   end

   def store_attachments
     # get the attachment, then store it.
     self.fetch_attachments
     self.save_attachments
   end

   def fetch_attachments
     # get the page and extract email from pre tags
     @page = Net::HTTP.get(@url, @params)
     @page =~ /\<pre\>(.+)\<\/pre\>/im
     @email = $1
     # get rid of everything before the first part separator
     # NB boundary separators assumed to start with -- No RFC  
guarantee this is always right.
     @email.sub!(/\A([^-]|-[^-])+/m, '')
     # create a scanner and grab header / body pairs
     @mime_scanner = StringScanner.new(@email)
     # this regex looks for a boundary line beginning -- then a line  
beginning Content then other header stuff then a blank line then body  
stuff
     # then either another of the same or a boundary then an empty  
line. Lookahead ?= prevents using part of next token.
     while @mime_scanner.scan(/(^--.+?\nContent.*?^\s*$)(.*?)(?=^--.+? 
\n(Content|^\s*$))/im) do
       attachment = Hash.new
       # translate html escapes and get rid of html mark-up that  
seems to creep into body, plus starting and trailing spaces
       attachment[:header] = CGI.unescapeHTML( @mime_scanner[1] )
       attachment[:body] = CGI.unescapeHTML( @mime_scanner[2].gsub(/\A 
\s+/,'').chomp.gsub(/\<[^\>]*\>/, '') )
       @attachments = @attachments << attachment
     end
   end

   def save_attachments
     @attachments.each do |a|
       # skip parts that aren't attachments
       next if !(a[:header] =~ /Content-Disposition:\s*attachment/i)
       # grab file name and encoding.
       # quit with error if no filename.
       if ( a[:header] =~ /filename\s*\=\s*\"?([a-z\-\_\ 0-9\.\%\$\@ 
\!]+)\"?\s*(\n|\;)/i || a[:header] =~ /name\s*\=\s*\"?([a-z\-\_\ 0-9\. 
\%\$]+)\"?\s*(\n|\;)/i )
         # do above as || to favor filename over name, which may be  
unnecessary
         # NB hasty assumptions about file name characters
         filename = $1
       else
         puts "Could not parse filename for attachment from #{a 
[:header]}"
         exit 1
       end
       if ( a[:header] =~ /Content-Transfer-Encoding:\s*\"?([a-z\- 
\_0-9]+)\"?\s*?(\n|\;)/i )
         encoding = $1
       end
       # if the filename specifies a directory and it exists, use it.  
Otherwise just put in pwd.
       # NB clobbers any files with same name as attachment.
       if ( File.exist?(File.dirname(filename)) )
         file = File.new(filename, "w+")
       else
         file = File.new(filename = File.basename(filename), "w+")
       end
       # decode if necessary
       case encoding
       when /base64/i
         file << a[:body].unpack("m").first
       when /quoted-printable/i
         file << a[:body].unpack("M").first
       else
         file << a[:body]
       end
       # notify what's been done, clean up and go home
       file.close
       puts "Stored attachment from message #{@id} at #{@url} in # 
{File.expand_path(filename)}"
       exit 0
     end
   end
end

ARGV.each do |arg|
   @ga = GetAttachments.new(arg)
   @ga.store_attachments
end



........................................................................ 
............................
John Browning





On 23 Feb 2007, at 14:00, Ruby Quiz wrote:

> The three rules of Ruby Quiz:
>
> 1.  Please do not post any solutions or spoiler discussion for this  
> quiz until
> 48 hours have passed from the time on this message.
>
> 2.  Support Ruby Quiz by submitting ideas as often as you can:
>
> http://www.rubyquiz.com/
>
> 3.  Enjoy!
>
> Suggestion:  A [QUIZ] in the subject of emails about the problem  
> helps everyone
> on Ruby Talk follow the discussion.  Please reply to the original  
> quiz message,
> if you can.
>
> -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 
> =-=-=-=-=-=-=
>
> The Ruby Talk mailing list archives will show files attached to  
> incoming
> messages.  However, it's not always easy to get at the data from  
> these files
> using the archives alone.  The attachments are sometimes displayed in
> not-too-readable formats:
>
> 	http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-talk/190780
>
> 	http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-talk/226884
>
> This is tough for those of us who like to play with Ruby Quiz  
> solutions.
>
> This week's quiz is to write a program that takes a message id  
> number as a
> command-line argument and "downloads" any attachments from that  
> message.  Assume
> message ids are for Ruby Talk posts by default, but you may want to  
> provide an
> option to override that so we can support lists like Ruby Core as  
> well.
>
> If no path is given, write the attachments to the working  
> directory.  When there
> is a path, your code should place the files there instead.
>
>


--Apple-Mail-2-938571758--