Patch docx file with a tracking URL | www.docping.me

patch_docx.py

#!/usr/bin/env python
"""

Patch docx file with a tracking URL


Author: Roy Firestein (roy[at]firestein[dot]net)
Date: October 28, 2014

Based on code from https://docping.me

"""

from os import path
import os
from tempfile import mkstemp, mkdtemp
from xml.dom.minidom import parse, parseString
import zipfile
import logging
from lxml import etree



def patch(docx_file, tracking_url):
    logging.info('Patching document: %s' % docx_file)
    docx_file = path.abspath(docx_file)

    # Extract
    logging.info('Extracting docx')
    docx_path = extract(docx_file)
    if docx_path is None:
        raise "No such file"

    # Patch
    safe_id = get_safe_id(docx_path)
    rel = makeelement("Relationship", attributes={
        "Id": "rId%s" %safe_id,
        "Type": "http://schemas.openxmlformats.org/officeDocument/2006/relationships/image",
        "TargetMode": "External",
        "Target": tracking_url
    })
    update_relationships(docx_path, rel)
    update_document(docx_path, safe_id)

    # Compress
    logging.info('Compressing docx')
    docx_path = compress(docx_path, docx_file)

    return docx_path



def extract(docx_path):
    if not path.exists(docx_path):
        return None
    temp_dir = mkdtemp()
    logging.info('Creating temp dir: %s' % temp_dir)
    with zipfile.ZipFile(docx_path) as z:
        z.extractall(path.abspath(temp_dir))
    return temp_dir


def compress(docx_path, docx_file):
    assert path.isdir(docx_path)

    os.chdir(docx_path)
    docxfile = zipfile.ZipFile(docx_file, mode='w', compression=zipfile.ZIP_DEFLATED)

    for root, dirs, files in os.walk("."):
        for f in files:
            docxfile.write(path.join(root, f))

    docxfile.close()
    return docx_file


def get_safe_id(extracted_path):
    dom = parse(path.join(extracted_path, 'word', '_rels', 'document.xml.rels'))
    ids = []
    for r in dom.getElementsByTagName('Relationship'):
        ids.append(int(r.getAttribute('Id').replace("rId", "")))
    ids = sorted(ids)
    safe_id = ids[-1] + 1
    logging.info('Safe ID: %s' % safe_id)
    return safe_id


def update_relationships(extracted_path, new_rel):
    file_path = path.join(extracted_path, 'word', '_rels', 'document.xml.rels')
    xmlcontent = open(file_path, 'r').read()
    document = etree.fromstring(xmlcontent)
    document.append(new_rel)

    fh = open(file_path, 'w')
    treestring = etree.tostring(document.getroottree(), pretty_print=True)
    fh.write(u'<?xml version="1.0" encoding="UTF-8" standalone="yes"?>\n%s' %treestring)
    fh.close()
    return True


def update_document(extracted_path, safe_id):
    file_path = path.join(extracted_path, 'word', 'document.xml')
    xmlcontent = open(file_path, 'r').read()
    document = etree.fromstring(xmlcontent)

    body = document.xpath('/w:document/w:body', namespaces=nsprefixes)[0]

    ctx = {"id": safe_id, "uuid": uuid.uuid4()}
    tracking_image = etree.fromstring(make_tracking_code(ctx))
    body.append(tracking_image)

    fh = open(file_path, 'w')
    treestring = etree.tostring(document.getroottree(), pretty_print=True)
    fh.write(u'<?xml version="1.0" encoding="UTF-8" standalone="yes"?>\n%s' %treestring)
    fh.close()
    return True


def makeelement(tagname, tagtext=None, nsprefix='w', attributes=None, attrnsprefix=None):
    '''Create an element & return it'''
    newelement = etree.Element(tagname)
    # Add attributes with namespaces
    if attributes:
        for tagattribute in attributes:
            newelement.set(tagattribute, attributes[tagattribute])
    if tagtext:
        newelement.text = tagtext
    return newelement


def make_tracking_code(ctx):
    return """<w:drawing xmlns:wpc="http://schemas.microsoft.com/office/word/2010/wordprocessingCanvas" xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math" xmlns:v="urn:schemas-microsoft-com:vml" xmlns:wp14="http://schemas.microsoft.com/office/word/2010/wordprocessingDrawing" xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing" xmlns:w10="urn:schemas-microsoft-com:office:word" xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:w14="http://schemas.microsoft.com/office/word/2010/wordml" xmlns:wpg="http://schemas.microsoft.com/office/word/2010/wordprocessingGroup" xmlns:wpi="http://schemas.microsoft.com/office/word/2010/wordprocessingInk" xmlns:wne="http://schemas.microsoft.com/office/word/2006/wordml" xmlns:wps="http://schemas.microsoft.com/office/word/2010/wordprocessingShape" mc:Ignorable="w14 wp14">
	<wp:inline distT="0" distB="0" distL="0" distR="0">
		<wp:extent cx="1" cy="1"/>
		<wp:effectExtent l="0" t="0" r="0" b="0"/>
		<wp:docPr id="4" name="gh6RuSZpJaptfEulBXmWORNwPEUbgy"/>
		<wp:cNvGraphicFramePr>
			<a:graphicFrameLocks xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main" noChangeAspect="1"/>
		</wp:cNvGraphicFramePr>
		<a:graphic xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main">
			<a:graphicData uri="http://schemas.openxmlformats.org/drawingml/2006/picture">
				<pic:pic xmlns:pic="http://schemas.openxmlformats.org/drawingml/2006/picture">
					<pic:nvPicPr>
						<pic:cNvPr id="0" name="%s"/>
						<pic:cNvPicPr/>
					</pic:nvPicPr>
					<pic:blipFill>
						<a:blip r:link="rId%s"/>
						<a:stretch>
							<a:fillRect/>
						</a:stretch>
					</pic:blipFill>
					<pic:spPr>
						<a:xfrm>
							<a:off x="0" y="0"/>
							<a:ext cx="1" cy="1"/>
						</a:xfrm>
						<a:prstGeom prst="rect">
							<a:avLst/>
						</a:prstGeom>
					</pic:spPr>
				</pic:pic>
			</a:graphicData>
		</a:graphic>
	</wp:inline>
</w:drawing>""" %(ctx['uuid'], ctx['id'])


nsprefixes = {
    'mo': 'http://schemas.microsoft.com/office/mac/office/2008/main',
    'o':  'urn:schemas-microsoft-com:office:office',
    've': 'http://schemas.openxmlformats.org/markup-compatibility/2006',
    # Text Content
    'w':   'http://schemas.openxmlformats.org/wordprocessingml/2006/main',
    'w10': 'urn:schemas-microsoft-com:office:word',
    'wne': 'http://schemas.microsoft.com/office/word/2006/wordml',
    # Drawing
    'a':   'http://schemas.openxmlformats.org/drawingml/2006/main',
    'm':   'http://schemas.openxmlformats.org/officeDocument/2006/math',
    'mv':  'urn:schemas-microsoft-com:mac:vml',
    'pic': 'http://schemas.openxmlformats.org/drawingml/2006/picture',
    'v':   'urn:schemas-microsoft-com:vml',
    'wp':  ('http://schemas.openxmlformats.org/drawingml/2006/wordprocessing'
            'Drawing'),
    # Properties (core and extended)
    'cp':  ('http://schemas.openxmlformats.org/package/2006/metadata/core-pr'
            'operties'),
    'dc':  'http://purl.org/dc/elements/1.1/',
    'ep':  ('http://schemas.openxmlformats.org/officeDocument/2006/extended-'
            'properties'),
    'xsi': 'http://www.w3.org/2001/XMLSchema-instance',
    # Content Types
    'ct':  'http://schemas.openxmlformats.org/package/2006/content-types',
    # Package Relationships
    'r':  ('http://schemas.openxmlformats.org/officeDocument/2006/relationsh'
           'ips'),
    'pr':  'http://schemas.openxmlformats.org/package/2006/relationships',
    # Dublin Core document properties
    'dcmitype': 'http://purl.org/dc/dcmitype/',
    'dcterms':  'http://purl.org/dc/terms/'
}


def main():
    from optparse import OptionParser, OptionGroup
    usage_text = "usage: %prog <file.docx> <tracking URL>"
    parser = OptionParser(usage_text)
    (menu, args) = parser.parse_args()

    if len(args) != 2:
        parser.print_usage()
    else:
        res = patch(args[0], args[1])
        print "File patched (%s)" %res



if __name__ == "__main__":
    main()