├── .project
├── .pydevproject
├── README
└── pptx-export-notes.py


/.project:
--------------------------------------------------------------------------------
 1 | <?xml version="1.0" encoding="UTF-8"?>
 2 | <projectDescription>
 3 | 	<name>pptx_export_speaker_notes</name>
 4 | 	<comment></comment>
 5 | 	<projects>
 6 | 	</projects>
 7 | 	<buildSpec>
 8 | 		<buildCommand>
 9 | 			<name>org.python.pydev.PyDevBuilder</name>
10 | 			<arguments>
11 | 			</arguments>
12 | 		</buildCommand>
13 | 	</buildSpec>
14 | 	<natures>
15 | 		<nature>org.python.pydev.pythonNature</nature>
16 | 	</natures>
17 | </projectDescription>
18 | 


--------------------------------------------------------------------------------
/.pydevproject:
--------------------------------------------------------------------------------
 1 | <?xml version="1.0" encoding="UTF-8" standalone="no"?>
 2 | <?eclipse-pydev version="1.0"?>
 3 | 
 4 | <pydev_project>
 5 | <pydev_pathproperty name="org.python.pydev.PROJECT_SOURCE_PATH">
 6 | <path>/pptx_export_speaker_notes</path>
 7 | </pydev_pathproperty>
 8 | <pydev_property name="org.python.pydev.PYTHON_PROJECT_VERSION">python 2.7</pydev_property>
 9 | <pydev_property name="org.python.pydev.PYTHON_PROJECT_INTERPRETER">Default</pydev_property>
10 | </pydev_project>
11 | 


--------------------------------------------------------------------------------
/README:
--------------------------------------------------------------------------------
 1 | pptx-export-notes
 2 | 
 3 | v1
 4 | by Eric Jang
 5 | 
 6 | a simple script to extract the presenter notes from a .pptx file and export them into a single plaintext (.txt) file (for printing/rehearsing).
 7 | 
 8 | Usage:
 9 | 
10 | pptx_export_speaker_notes.py -p /Users/Eric/Desktop/myppt.pptx
11 | 
12 | A .txt file containing all of the presenter notes will be exported to the same directory as the .pptx file.
13 | 
14 | This only works for .pptx files as they use Microsoft's OpenXML format (will not work for ppt files).
15 | 
16 | 


--------------------------------------------------------------------------------
/pptx-export-notes.py:
--------------------------------------------------------------------------------
 1 | #############################################################################
 2 | #############################################################################
 3 | ###                                                                       ###
 4 | ###        pptx notes exporter v1.0 copyright Eric Jang 2012              ###
 5 | ###        ericjang2004@gmail.com                                         ###
 6 | ###                                                                       ###
 7 | #############################################################################
 8 | #############################################################################
 9 | 
10 | #!/usr/bin/env python
11 | import argparse, os, glob
12 | from zipfile import ZipFile
13 | from xml.dom.minidom import parse
14 | 
15 | 
16 | def slide_number_from_xml_file(filename):
17 |     """
18 |     Integer slide number from filename
19 | 
20 |     Assumes /path/to/Slidefile/somekindofSlide36.something
21 |     """
22 |     return int(filename[filename.rfind("Slide") + 5:filename.rfind(".")])
23 | 
24 | #main function
25 | def run():
26 |     parser = argparse.ArgumentParser(description='exports speaker notes from pptx files by parsing the XML')
27 |     parser.add_argument('-v', action='version', version='%(prog)s 1.0')
28 |     parser.add_argument('-p', metavar='<path/to/pptx/file>', help='path to the Powerpoint 2007+ file', action='store',
29 |                         type=file, dest='pptxfile')
30 |     #add more arguments here in future if you wish to expand
31 |     args = parser.parse_args()
32 |     #extract the pptx file as a zip archive
33 |     #note: only extract from pptx files that you trust. they could potentially overwrite your important files.
34 |     ZipFile(args.pptxfile).extractall(path='/tmp/', pwd=None)
35 |     path = '/tmp/ppt/notesSlides/'
36 | 
37 |     notesDict = {}
38 |     #open up the file that you wish to write to
39 |     writepath = os.path.dirname(args.pptxfile.name) + '/' + os.path.basename(args.pptxfile.name).rsplit('.', 1)[
40 |         0] + '_presenter_notes.txt'
41 |     print writepath
42 | 
43 |     # Get the xml we extracted from the zip file
44 |     xmlfiles = glob.glob(os.path.join(path, '*.xml'))
45 | 
46 |     with open(writepath, 'w') as f:
47 |         for infile in sorted(xmlfiles, key=slide_number_from_xml_file):
48 |             #parse each XML notes file from the notes folder.
49 |             dom = parse(infile)
50 |             noteslist = dom.getElementsByTagName('a:t')
51 |             if len(noteslist) == 0:
52 |                 continue
53 | 
54 |             #separate last element of noteslist for use as the slide marking.
55 |             slideNumber = slide_number_from_xml_file(infile)
56 |             #start with this empty string to build the presenter note itself
57 |             tempstring = ''
58 | 
59 |             for node in noteslist:
60 |                 xmlTag = node.toxml()
61 |                 xmlData = xmlTag.replace('<a:t>', '').replace('</a:t>', '')
62 |                 #concatenate the xmlData to the tempstring for the particular slideNumber index.
63 |                 tempstring = tempstring + xmlData
64 | 
65 |             #store the tempstring in the dictionary under the slide number
66 |             notesDict[slideNumber] = tempstring
67 | 
68 |         #print/write the dictionary to file in sorted order by key value.
69 |         for x in [key for key in sorted(notesDict.keys(), key=int)]:
70 |             f.write('Slide ' + str(x) + '\n')
71 |             notes_string = notesDict[x]
72 |             f.write(notes_string.encode('utf-8', 'ignore') + '\n')
73 | 
74 |         print 'file successfully written to' + '\'' + writepath + '\''
75 | 
76 | 
77 | if __name__ == "__main__":
78 |     try:
79 |         run()
80 |     except (KeyboardInterrupt, SystemExit):
81 |         raise
82 | 
83 | 


--------------------------------------------------------------------------------