DZone Snippets: pdf code

Auto download pdf from www.estado.com.br

adr1an0 (Adr) — Fri, 28 Mar 2008 20:27:19 GMT

// This script downloads all pdfs from http://jpdf.estado.com.br
// Note, you must subscribe this newspaper in order to download the pdfs
// You must have wget installed



export http_proxy="http://10.1.1.1:8000"



cookie='sMkjwKA67H8FDcsZX5'

dd=`date +%d`

mm=`date +%m`

yyyy=`date +%Y`



index="http://jpdf.estado.com.br/menupdfi.php?E=SP&D=$dd/$mm/$yyyy&A=/estadopdf/sp/paginas/$yyyy/$mm/$dd/A01.pdf"



rm index.txt

./wget/wget -nc -k -S -U Mozilla --proxy --header "Cookie: User=$cookie " -O index.txt $index

if [ ! -f index.txt ]; then exit 1; fi



l=`gawk  'BEGIN {FS="\""} /option VALUE="\/estadopdf/ { print $2 }' index.txt`



for x in $l; do 



	# Ignora os classificados

	if [ ${x%01.pdf} -eq "Cl" ]; then continue; fi

	# Ignora o Guia

	if [ ${x%01.pdf} -eq "Q" ]; then continue; fi



	y=http://jpdf.estado.com.br${x%01.pdf}

	i=1

	flag=0

	

	while [ $i -lt 40 ]; do

		filename=`printf "%s%02d.pdf\n" $y $i`



		echo "=================================================================="

		echo $filename

		echo "=================================================================="

		./wget/wget -P estado -nc -k -S -U Mozilla --proxy --header "Cookie: User=$cookie " $filename

		if [ $? -eq 1 ]; then

			let flag=flag+1

			if [ $flag -gt 1 ]; then 

				flag=0

				echo "Proximo caderno..."; break;

			fi 

		fi

		

		sleep 1

		let i=i+1

	done

done

pman -- create, print, save, view PDF man pages

ntk () — Sat, 07 Jul 2007 10:54:01 GMT

pman -- create, print, save, view PDF man pages

Author: ntk
License: The MIT License, Copyright (c) 2007 ntk
Description: (batch) convert man pages into PDF documents and save them to a specified directory; (batch) print or view PDF man pages from the command line
Platform: Mac OS X 10.4.10; man bash
Installation: put pman() into ~/.bash_login (or alternatives)







# Usage:

   

pman ls; pman getopts                                 # convert a singel man page to a PDF file, save and open it

pman 8 sticky                                         # same with manual section number

pman m toe                                     

pman -b ls 'open(2)' dd "chmod(2)" curl 'open(n)'     # batch convert man pages into PDF files

pman -p rm srm open\(2\) 'toe(m)' 'ncurses(3)'        # print man pages using the default printer







pman() {



section="$1"    

manpage="$2"    



mandir="/Users/Shared/manpages"    #  save the created PDF man pages to the specified directory





# batch process man pages to PDF files with the "-b" switch and save them to $mandir

# example: pman -b ls 'open(2)' dd 'chmod(2)' 'open(n)' 'sticky(8)'

# cf. man -aW open for "man n open"



if [[ "$1" = "-b" ]]; then         



if [[ ! -d $mandir ]]; then        

   mkdir -p $mandir

   chmod 1777 $mandir

fi



shift   # remove "-b" from "$@"



for manfile in "$@"; do 



# example for $manfile: open(2)

manpage="`echo $manfile | grep -Eos '^[^\(]+'`"                              # extract name of man page

section="`echo $manfile | grep -Eos '\([^\)]+\)' | grep -Eos '[^\(\)]+'`"    # extract section of man page



if [[ ! "$section" ]]; then

   section="1"

fi



if [[ ! -f "`man ${section} -W ${manpage} 2>/dev/null`" ]]; then

#if [[ ! -f "`man -W ${section} ${manpage} 2>/dev/null `" ]]; then

   echo "No such man page: man ${section} ${manpage}"

   continue

fi



manfile="${mandir}/${manpage}(${section}).pdf"

echo "$manfile"



if [[ ! -f "$manfile" ]]; then

   man $section -t $manpage 2>/dev/null | pstopdf -i -o "$manfile" 2>/dev/null

   chmod 1755 "$manfile"

   # hide file extension .pdf

   if [[ -f /Developer/Tools/SetFile ]]; then /Developer/Tools/SetFile -a E "$manfile"; fi

fi



done



return 0

   

fi          # END of batch processing man pages to PDF files







# print PDF man pages using the default printer (see man lpr and man lpoptions)

# if necessary, create the specified PDF man pages and save them to $mandir

# example: pman -p rm srm



if [[ "$1" = "-p" ]]; then         



if [[ ! -d $mandir ]]; then        

   mkdir -p $mandir

   chmod 1777 $mandir

fi



shift   # remove "-p" from "$@"



for manfile in "$@"; do 



# example for $manfile: open(2)

manpage="`echo $manfile | grep -Eos '^[^\(]+'`"                              # extract name of man page

section="`echo $manfile | grep -Eos '\([^\)]+\)' | grep -Eos '[^\(\)]+'`"    # extract section of man page



if [[ ! "$section" ]]; then

   section="1"

fi



if [[ ! -f "`man ${section} -W ${manpage} 2>/dev/null`" ]]; then

   echo "No such man page: man ${section} ${manpage}"

   continue

fi



manfile="${mandir}/${manpage}(${section}).pdf"

echo "$manfile"



if [[ ! -f "$manfile" ]]; then

   man -t $section $manpage 2>/dev/null | pstopdf -i -o "$manfile" 2>/dev/null

   chmod 1755 "$manfile"

   # hide file extension .pdf

   if [[ -f /Developer/Tools/SetFile ]]; then /Developer/Tools/SetFile -a E "$manfile"; fi

   lpr "$manfile"

else

   lpr "$manfile"

fi



done



return 0

   

fi          # END of printing man pages using the default printer







# convert a single man page to a PDF file, save it to $mandir and then open it in a PDF viewer



if [[ -z "$1" ]] || [[ $# -gt 2 ]]; then       # check number of arguments

#if [[ -z "$1" || $# -gt 2 ]]; then  

#if [ -z "$1" -o $# -gt 2 ]; then

  echo "Wrong number of arguments!" 

  return 1

fi 



if [[ ! "$manpage" ]]; then     # turn "pman ls" into "pman 1 ls"

   manpage="$section"         # if $manpage is an empty string because there has been no "$2" then $manpage is set to "$section" and ...

   section="1"                # ... $section is set to "1"

fi                            



if [[ ! -f "`man ${section} -W ${manpage} 2>/dev/null`" ]]; then

   echo "No such man page: man ${section} ${manpage}"

   return 1

fi



if [[ ! -d $mandir ]]; then

   mkdir -p $mandir

   chmod 1777 $mandir

fi



manfile="${mandir}/${manpage}(${section}).pdf"



if [[ -f "$manfile" ]]; then

   open "$manfile"

else

   man $section -t $manpage 2>/dev/null | pstopdf -i -o "$manfile" 2>/dev/null

   chmod 1755 "$manfile"

   # hide file extension .pdf

   if [[ -f /Developer/Tools/SetFile ]]; then /Developer/Tools/SetFile -a E "$manfile"; fi

   open "$manfile"

fi



return 0



}

PDF Word Link

ldstudio (Larry Rivera) — Thu, 17 May 2007 22:21:15 GMT

// Find Word(s) on Current Page and add link



var numWords = this.getPageNumWords(this.pageNum);

p = this.pageNum;



for ( var i=0; i    var ckWord =  this.getPageNthWord(p,i,true);;



    if(ckWord == "Solo")

    {

        var q = this.getPageNthWordQuads(p,i);



        m = (new Matrix2D).fromRotated(this,p);

        mInv = m.invert();

        r = mInv.transform(q);

        r = r.toString();

        r = r.split(",");

        l = addLink(p, [r[4], r[5], r[2], r[3]]);

        l.borderColor = color.red;

        l.borderWidth = 1;

        l.setAction("this.getUrl('http://www.adobe.com/');");



    }





}

Simple % bar in a pdf using Ruby

abscond (James Darling) — Thu, 08 Mar 2007 12:01:19 GMT

Will create a bar, filled to the percentage provided, and draw it in a PDF.

Requires PDF Writer, call method after setting up PDF to @pdf



  def generate_pdf_bar(p = 50, x = 10, y = 'center', w = 200, h = 10)

     # adjustments

    if y == 'center'

      y = @pdf.page_height / 2 - h

    else

      y = @pdf.page_height - y - h

    end

    p = w / 100 * p



      # Empty

    @pdf.stroke_color  Color::RGB::Black

    @pdf.rectangle(x, y, w, h).close_stroke



     # Fill

    @pdf.fill_color    Color::RGB::Black

    @pdf.stroke_color  Color::RGB::Black

    @pdf.rectangle(x, y, p, h).close_fill_stroke

  end

Export Adobe FDF and XFDF from ActiveRecord

seancribbs (Sean Cribbs) — Sat, 10 Feb 2007 00:43:34 GMT

I needed to export XFDF from an application. This code is kind of untested, but is based on the solution I came up with. I would appreciate responses/modifications. It's very straightforward mixin stuff, for the most part.



# (X)FDF Export for ActiveRecord

# Based on Justin Koivisto's FDF library for PHP

# Author: Sean Cribbs, seancribbs_AT_gmail_DOT_com, http://seancribbs.com

module FDF

  def self.included(base)

    base.extend ClassMethods

  end

  

  module ClassMethods

    # Options:

    #  :filename - The filename of the associated PDF document.  REQUIRED!

    #  :indentation - How much to indent the resulting XFDF (XML)

    #  :include - Which associated models to include in the generated XFDF.

    #  :exclude_attributes - Which attributes of the current model should not be exported.  By default all non-internal attributes are exported (i.e. everything but _id fields).

    #  :include_attributes - Which attributes of the current model should be exported in addition to the default. By default all non-internal attributes are exported (i.e. everything but _id fields).

    #  :attributes - Override which attributes to export.

    def exports_xfdf(options = {})

      raise ArgumentError, "A :filename option must be specified." unless options[:filename]

      options[:indentation] ||= 2

      options[:include] = options[:include].is_a?(Array) ? options[:include] : [options[:include]].compact

      unless included_modules.include? XFDFMethods

        class_inheritable_accessor :xfdf_options

        extend ClassMethods

        include XFDFMethods

      end

      self.xfdf_options = options

    end

    

    # Options:

    #  :filename - The filename of the associated PDF document.  REQUIRED!

    #  :include - Which associated models to include in the generated FDF.

    #  :exclude_attributes - Which attributes of the current model should not be exported.  By default all non-internal attributes are exported (i.e. everything but _id fields).

    #  :include_attributes - Which attributes of the current model should be exported in addition to the default. By default all non-internal attributes are exported (i.e. everything but _id fields).

    #  :attributes - Override which attributes to export.

    def exports_fdf(options = {})

      raise ArgumentError, "A :filename option must be specified." unless options[:filename]

      options[:include] = options[:include].is_a?(Array) ? options[:include] : [options[:include]].compact

      unless included_modules.include? FDFMethods

        class_inheritable_accessor :fdf_options

        extend ClassMethods

        include FDFMethods

      end

      self.fdf_options = options

    end

  end



  module XFDFMethods

    def to_xfdf(options = {})

      options.reverse_merge! self.class.xfdf_options

      fields = Util.collect_values(self, self.class.content_columns.map(&:name), options)

      filename = options[:filename]

      xml = Builder::XmlMarkup.new :indentation => options[:indentation]

      xml.instruct!

      xml.xfdf("xmlns" => "http://ns.adobe.com/xfdf/", "xml:space" => "preserve") {

        xml.f :href => filename

        xml.fields {

          fields.each do |field, value|

            xml.field(:name => field) {

              if value.is_a? Array

                  value.each {|item| xml.value(item.to_s) }

              else

                xml.value(value.to_s)

              end

            }

          end

        }

      }

      xml.target!

    end    

  end

  

  module FDFMethods

    def to_fdf(options={})

      options.reverse_merge! self.class.fdf_options

      fields = Util.collect_values(self, self.class.content_columns.map(&:name), options)

      filename = options[:filename]

      data = "%FDF-1.2\n%âã�?Ó\n1 0 obj\n<< \n/FDF << /Fields [ "

      fields.each do |field, value|

        if value.is_a? Array

          data << "<          value.each {|v| data << "(#{v.strip})"}

          data << "]>>"

        else

          data << "<>"

        end

      end

    end

    data << "] \n/F (#{filename}) /ID [ <#{MD5.md5(Time.now).to_s}>\n ] >>" <<

            " \n>> \nendobj\ntrailer\n" << "<<\n/Root 1 0 R \n\n>>\n%%EOF\n"

  end

  

  module Util

    def self.collect_values(object, defaults, options = {})

      attrs = []

      if options[:attributes]

        attrs = stringify_all(options[:attributes]) rescue []

      else        

        [:include_attributes, :exclude_attributes].each do |opt|

          options[opt] = stringify_all(options[opt]) rescue []

        end

        attrs = stringify_all(defaults) + options[:include_attributes] - options[:exclude_attributes]

      end

      fields = attrs.inject({}) do |hash, key|

        value = object.send(key) rescue nil

        hash.merge key => value

      end

      fields.merge collect_association_values(object, options)

    end

    

    def self.collect_association_values(object, options = {})

      return {} if options[:include].blank?

      values = {}

      options[:include].each do |association|

        unless object.send(association).blank?

          models = object.send(association)

          unless models.is_a? Array

            columns = models.class.content_columns.map(&:name)

            values.merge! association_dump(association, models, columns)

          else

            models.each_with_index do |model, index|

              columns = model.class.content_columns.map(&:name)

              values.merge! association_dump("#{association.singularize}_#{index+1}", model, columns)

            end

          end

        end

      end

      values

    end

    

    def self.association_dump(prefix, object, attributes)

      attributes.inject({}) do |hash, attr|

        value = object.send(attr) rescue nil

        hash.merge "#{prefix}_#{attr}" => value

      end

    end

    

    def self.stringify_all(ary)

      ary.compact.map(&:to_s).uniq

    end

  end

end

ActiveRecord::Base.send :include, FDF

Also available from: http://pastie.caboo.se/38835

Add a watermark to a multi-page PDF (a-la Pragmatic Programmers)

julik () — Thu, 16 Mar 2006 05:50:22 GMT

This adds a text watermark to every page of a PDF document, as used by Pragmatic Programmers. Nothing secret here, more of a way to excercise "human" DRM. Used as:



   perl makepdf.pl "John Doe"



use PDF::Reuse;

use PDF::Reuse::Util;

use strict;



my ($name) = @ARGV;



prFile('book_for_someone.pdf');



my $sourcePdf = 'pdf_that_your_designer_made.pdf';

my $greeting = "This book is personalized for " . $name;



my $left = 1;

while ($left) {

   prFont('HO');

   prAdd("0 0 0 rg\n0 g\nf\n");

   prText( 38, 800, $greeting);

   $left = prSinglePage($sourcePdf);   

} 



prEnd;

Creating a PDF using iText and ColdFusion

jnunemaker () — Tue, 07 Mar 2006 01:54:50 GMT

// description of your code here





// create document

document 		= CreateObject("java", "com.lowagie.text.Document");

document.init();



// writer

fileIO 			= CreateObject("java", "java.io.FileOutputStream");

fileIO.init(pdf_path);

writer 			= CreateObject("java", "com.lowagie.text.pdf.PdfWriter");

writer.getInstance(document, fileIO);

document.open();



// newsinfo header image

Image 			= CreateObject("java", "com.lowagie.text.Image");

jpg 			= Image.getInstance(header_image);

jpg.setAbsolutePosition(28, 713);

jpg.setDpi(300,300);

document.add(jpg);



// top margin; dumb i know but i was in a hurry

paragraph = CreateObject("java", "com.lowagie.text.Paragraph");

paragraph.init(" ");

for (i=0; i lt 9; i=i+1) {

	document.add(paragraph);

}



// the fonts

FontFactory 	= createobject("java", "com.lowagie.text.FontFactory");

Font 			= createObject("java", "com.lowagie.text.Font");

TimesLargeBI 	= Font.init(Font.TIMES_ROMAN, 14.0, Font.BOLDITALIC);

TimesNormal 	= Font.init(Font.TIMES_ROMAN, 12.0);



// all the text

paragraph 		= CreateObject("java", "com.lowagie.text.Paragraph");



paragraph.init("Hello World!", TimesLargeBI);

paragraph.setIndentationLeft(indentation_left);

paragraph.setIndentationRight(indentation_right);

document.add(paragraph);



paragraph.init("#dateFormat(now(), 'long')#", TimesNormal);

paragraph.setIndentationLeft(indentation_left);

paragraph.setIndentationRight(indentation_right);

document.add(paragraph);



document.close();

Finding pdf paper from CiteULike

korakot (Korakot Chaovavanich) — Mon, 11 Apr 2005 04:03:36 GMT

I use CiteULike (http://citeulike.org) to manage papers a lot.
Unfortunately, I don't have access to paid site. But some authors
are generous enough to put pdf on his own site, which I find
using google search.



javascript:(function(){

var title = document.title.substring(11);

var query = '%22' + title + '%22 ' + 'filetype:pdf';

var url = 'http://www.google.com/search?q=' + encodeURI(query);

window.open(url);

})();

It simply takes the paper title from windows title. Then it searches the title(enclosed in quotation) for pdf files of the same name.