From 28f75725628d45c11e23f128c9bfea441e8cae82 Mon Sep 17 00:00:00 2001
From: Castro0o <andre@andrecastro.info>
Date: Fri, 10 Nov 2017 20:15:32 +0100
Subject: [PATCH] imposition and wiki-download in da house

---
 README           | 30 +++++++++++++++-
 imgs2pdf.sh      |  2 +-
 imposition.py    | 93 ++++++++++++++++++++++++++++++++++++++++++++++++
 wiki-download.py | 83 ++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 206 insertions(+), 2 deletions(-)
 create mode 100755 imposition.py
 create mode 100755 wiki-download.py

diff --git a/README b/README
index 27a4d14..015f490 100644
--- a/README
+++ b/README
@@ -2,9 +2,37 @@
 
 
 ## Software dependencies:
-pdftk, imagemagick
+Packages: pdftk, imagemagick
+Install in Debian/Ubuntu: apt-get install pdftk imagemagick
+
+Install in Mac with brew (http://brew.sh/): brew install pdftk imagemagick
+
+Python libraries: mwclient
+
+Install in Debian/Ubuntu w/ pip: sudo pip install mwclient
+
 
 ## Scripts
+
+### wiki-download.py
+Dowloads media files from a wiki, according to a sematic ask query. 
+
+Usage:
+python wiki-download.py --help
+
+python wiki-download.py -d imgs -a [[Modification_date::+]]  
+
+
+### imposition.py
+Converts 8 images (jpg or png) from a given directory, into a single sheet 4x2 imposition.
+
+Usage:
+python wiki-download.py --help 
+
+python imposition.py --dir imgs/  --size a3 --order random
+
+
+
 ### imgs2pdf.sh
 Converts a directory of images onto a single PDF
 
diff --git a/imgs2pdf.sh b/imgs2pdf.sh
index 2d23e31..455e2ed 100755
--- a/imgs2pdf.sh
+++ b/imgs2pdf.sh
@@ -33,7 +33,7 @@ then
     echo "processing..."
     for IMG in $DIR* # convert imgs to tmp pdfs
     do PDF=${IMG%.*}.pdf 
-       convert -density 200 $IMG $PDF
+#       convert -density 200 $IMG $PDF
     done
     pdftk $DIR*.pdf cat output $FILENAME # concatonate single pdf into 1 pdf 
 
diff --git a/imposition.py b/imposition.py
new file mode 100755
index 0000000..ec435de
--- /dev/null
+++ b/imposition.py
@@ -0,0 +1,93 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+import os, tempfile, shlex, subprocess
+from argparse import ArgumentParser
+from random import shuffle
+
+####
+# Arguments
+# TODO: add example to description
+####
+p = ArgumentParser(description='Script converts 8 images (jpg or png) from a given directory into a single page 4x2 imposition. Example: python imposition.py --dir imgs/  --size a3 --order random ')
+p.add_argument("--dir", metavar='', default='', required=True, help="Image directory, which stores the source images for the imposition")
+p.add_argument("--size", metavar='', default="A4", choices=['A4','a4','A3','a3'], help="Size of the printing sheet: A4 or A3. Default:A4")
+p.add_argument("--order", metavar='', default="alphabet", choices=["alphabet", "reverse", "random"], help="Image distribution Order in the imposition. Possible Values: alphabet (alphabetically) , reverse (reverse alphabetically), random. Default: alphabet")
+p.add_argument("--output", metavar='' ,default="output.pdf", help="Output file. Can either be a pdf, jpg or png. Default: output.pdf")
+args = p.parse_args()
+
+temp_dir = tempfile.mkdtemp()
+
+# dimensions
+args.size = (args.size).upper()
+global size_sheet
+if args.size == 'A4':
+    size_sheet = (3508, 2480) #landscape: widthxheight in px
+elif args.size == 'A3':
+    size_sheet = (4960, 3508) #landscape: widthxheight in px
+size_pages =  (size_sheet[0]/4,size_sheet[1]/2 )# size of each of the pages which makes up the printing sheet
+
+# image selection
+listdir = os.listdir( os.path.abspath(args.dir))
+listdir = [f for f in listdir if any (x in f for x in ['.jpeg','.jpg','.png','.JPEG','.JPG','.PNG', '.Jpg', '.Jpeg','.Png']) ] #only bitmaps allowed
+
+# create list of 8 ordered images
+global listdir_order
+if args.order == 'alphabet':
+    listdir.sort()        
+    listdir_order = listdir
+elif args.order == 'reverse':
+    listdir.sort()
+    listdir.reverse()
+    listdir_order = listdir
+elif args.order == 'random':
+    shuffle(listdir)    
+    listdir_order = listdir
+
+print listdir_order
+listdir_order = listdir_order[0:8]
+pagenumbers = [2,5,4,3,1,6,7,0] # from from top left to bottom right ( order in imagemagick creates mosaic)
+listdir_order = [listdir_order[n] for n in pagenumbers] # reorder according to pagenumbers
+print 'selected files according to pagenumbers:', listdir_order
+
+# image conversion: -extent
+tmpfiles =  [ (temp_dir +'/'+ str(n)+'.jpg')  for n, img in enumerate(listdir_order) ]
+for n, img in enumerate(listdir_order):
+    template_convert = 'convert -background white "{targetimg}" -gravity Center -resize {w}x{h} -extent {w}x{h} {tmpfile}'
+    cmd_convert = template_convert.format(targetimg=(os.path.abspath(args.dir))+'/'+img,
+                                          w=size_pages[0],
+                                          h=size_pages[1],
+                                          tmpfile=tmpfiles[n])
+    cmd_convert_l = shlex.split(cmd_convert)
+    subprocess.call(cmd_convert_l)
+    
+# montage
+## order & rotation
+tmpfiles_top =  tmpfiles[0:4] # top row will be rotated in the mosaic
+tmpfiles_top = ' '.join(tmpfiles_top)
+tmpfiles_bottom = tmpfiles[4:8]
+tmpfiles_bottom = ' '.join(tmpfiles_bottom)
+tmp_output = (temp_dir +'/'+'output.jpg') 
+# command
+template_montage = "montage -geometry +1+1 -tile 4x2  \( -rotate 180 {topfiles} \) {bottomfiles}  {output}"
+cmd_montage = template_montage.format(topfiles=tmpfiles_top,
+                                      bottomfiles=tmpfiles_bottom,
+                                      output = tmp_output)
+cmd_montage_l = shlex.split(cmd_montage)
+subprocess.call(cmd_montage_l)
+
+# resize output
+output_f = os.path.abspath('./'+args.output)
+template_convert = "convert {input_f} -resize {w}x{h} -units PixelsPerInch -density 300x300 {output}"
+cmd_convert = template_convert.format(
+    input_f= tmp_output,
+    w=size_sheet[0],
+    h=size_sheet[1],
+    output=output_f)
+cmd_convert_l = shlex.split(cmd_convert)
+subprocess.call(cmd_convert_l)
+
+print '** imposition save in', output_f, '**'
+
+# garbage collection
+cmd_rm = shlex.split( ('rm -rf '+ temp_dir) )
+subprocess.call(cmd_rm ) # rm temp dir
diff --git a/wiki-download.py b/wiki-download.py
new file mode 100755
index 0000000..41d7fe4
--- /dev/null
+++ b/wiki-download.py
@@ -0,0 +1,83 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+
+from mwclient import Site, image
+from argparse import RawTextHelpFormatter
+from argparse import ArgumentParser
+import pprint, os, urllib2
+
+####
+# Arguments
+# todo add search query
+####
+p = ArgumentParser(description="""
+# Description: Script dowloads media files from a wiki, according to a sematic ask query. 
+
+# Examples: 
+Downloads files with property Modification_date: 
+python wiki-download.py -d imgs -a [[Modification_date::+]]  
+
+Downloads files semantically tagged as belonging to Year 2007 and having Document_Type Poster: 
+python wiki-download.py -d imgs -a [[Year::2007]][[Document_Type::Poster]]""", formatter_class=RawTextHelpFormatter)
+
+p.add_argument("--host",  metavar='', default="aa.xpub.nl")
+p.add_argument("--path", metavar='', default="/", help="Wiki path. Should end with /")
+p.add_argument("--ask", "-a", metavar='', default="", help="Ask query to be sent to the wiki API.")
+p.add_argument("--download", "-d", metavar='', default='', help="Local directory to store files from wiki. If no directory provided files wont be downloaded")
+p.add_argument("--verbose", "-v", action='store_true', help="Increase verbosity. If not given no files will be downloaded")
+
+args = p.parse_args()
+print args
+
+#########
+# defs
+#########
+def mwsite(host, path):
+    site = Site(('http',host), path)
+    return site
+
+
+site = mwsite(args.host, args.path)
+print site
+
+
+
+query= ('[[File:+]]'+ args.ask)
+
+# examples:
+# [[File:+]][[Year::+]][[Document_Type::Poster]]
+# [[File:+]][[Year::2007]][[Document_Type::Poster]]
+# same as: api.php?action=ask&query=[[File:%2B]][[Year::2007]][[Document_Type::Poster]]
+# can write compound query such as Year::2000 Medium::Flyer
+
+
+for answer in site.ask(query):
+
+    print answer
+    img = image.Image(site, answer)
+    img_name = answer.title()        
+    img_text = img.text()
+    img_info =  img.imageinfo # dict includes url and extensive metadata
+    # FILE DOWNLOAD        
+    if 'url' in img_info.keys() and len(args.download) > 0:
+        img_url =  (img_info['url']).replace('https','http')
+
+        if os.path.exists(args.download) is False:
+            os.makedirs(args.download)
+
+        img_data = urllib2.urlopen( img_url )
+        img_file = open('{}/{}'.format(args.download, img_name), 'wb')
+        img_file.write(img_data.read())
+        img_file.close()
+        print 'Saved to {}'.format(args.download + '/' + img_name)
+    if args.verbose:
+        print 'File text:',img_text            
+        pprint.pprint( img_info )
+
+    print
+
+
+
+        
+
+