sebastien/enextractor.py

## enextractor.py
#!/usr/bin/env python
# encoding=utf8 ---------------------------------------------------------------
# Project           : Enextrcator
# -----------------------------------------------------------------------------
# Author            : Sébastien Pierre
# License           : BSD License
# -----------------------------------------------------------------------------
# Creation date     : 2015-06-22
# Last modification : 2015-06-22
# -----------------------------------------------------------------------------

VERSION = "0.0.0"
LICENSE = "http://ffctn.com/doc/licenses/bsd"

import os, sys, re, json, base64, logging, datetime, dateutil.parser, mimetypes

__doc__ = """
A converter that parses Evernote's .enex data dump and outputs its content
as HTML, JSON, binaries and Markdown (if Pandoc is installed).
"""

RE_KEY      =re.compile("([^\w\d]|[_])+")
RE_SPACES   =re.compile("\s+")

try:
	from wwwclient import *
except ImportError, e:
	print ("Enextractor requires wwwclient: type `pip install -u wwwclient` or `easy_install wwwclient`")
	sys.exit(-1)

def save( data, path ):
	"""Saves the given data to the given path, if the data is not null."""
	if data:
		d = os.path.dirname(os.path.abspath(path))
		if not os.path.isdir(d): os.mkdir(d)
		with open(path, "wb") as f:
			logging.info("Writing: {0}".format(path))
			try:
				f.write(data)
			except Exception, e:
				logging.error("Cannot write: {0}".format(e))
		return path
	else:
		return None

def process_note( xml ):
	title      = xml.first("title").text()
	created    = xml.first("created").text()
	updated    = xml.first("updated").text()
	attributes = [{e.name:e.text()} for e in xml.first("note-attributes").children]
	created    = created or datetime.datetime.now()
	created    = tuple(dateutil.parser.parse(created).timetuple())
	updated    = tuple(dateutil.parser.parse(updated).timetuple()) if updated else created
	# The content is stored as HTML CDATA
	content    = xml.first("content").html().split("<![CDATA[",1)[-1].rsplit("]]>",1)[0]
	content  = "<html><body>" + content + "</body></html>"
	rsrc       = []
	for r in xml.query("resource"):
		data = r.first("date")
		mime = r.first("mime")
		if data and data.get("encoding"):
			enc  = data.get("encoding")
			assert enc == "base64", "Unsupported encoding: {0}".format(enc)
			data = base64.decodestring(data)
			# We take tha last extension (it's the most complete)
			ext  = mimetypes.guess_all_extensions(mime)[-1]
			rsrc.append(dict(
				data = data,
				mime = mime,
				ext  = ext,
			))
	return dict(
		title      = title,
		created    = created,
		updated    = updated,
		attributes = attributes,
		content    = content,
		resources  = rsrc,
	)

def write_note( note, path="notes", use_pandoc=True ):
	"""Writes the note in the given directory."""
	name   = RE_SPACES.sub("_", RE_KEY.sub("-", note["title"]).lower()).strip()
	logging.info("Writing note {0} in {1}".format(name, path))
	date   = note["updated"] or note["created"]
	prefix = os.path.join(path, "{0:04d}-{1:02d}-{2:02d}-{3}".format(date[0], date[1], date[2], name))
	save(json.dumps(note), "{0}.json".format(prefix))
	save(note["content"],  "{0}.html".format(prefix))
	if use_pandoc: os.system("pandoc -f html -t markdown {0}.html > {0}.md".format(prefix))
	for i,r in enumerate(note["resources"]):
		save(r["data"],  "{0}-{1}.{2}".format(i, r["ext"]))

def process_enex( path ):
	assert os.path.exists(path), "Given path does not exist: {0}".format(path)
	logging.info("Processing note at {0}".format(path))
	with open(path) as f: t = f.read()
	xml = HTML.tree(t, asXML=True)
	for note in xml.query("note"):
		write_note(process_note(note))


# -----------------------------------------------------------------------------
#
# SECTION
#
# -----------------------------------------------------------------------------

def run( args ):
	if not args:
		logging.error("run(): At least one .enex file path required")
	else:
		for p in args:
			process_enex(p)

# -----------------------------------------------------------------------------
#
# MAIN
#
# -----------------------------------------------------------------------------

if __name__ == "__main__":
	logging.basicConfig(level=logging.DEBUG,stream=sys.stderr)
	run(sys.argv[1:])

# EOF - vim: ts=4 sw=4 noet
	#!/usr/bin/env python
	# encoding=utf8 ---------------------------------------------------------------
	# Project : Enextrcator
	# -----------------------------------------------------------------------------
	# Author : Sébastien Pierre
	# License : BSD License
	# -----------------------------------------------------------------------------
	# Creation date : 2015-06-22
	# Last modification : 2015-06-22
	# -----------------------------------------------------------------------------

	VERSION = "0.0.0"
	LICENSE = "http://ffctn.com/doc/licenses/bsd"

	import os, sys, re, json, base64, logging, datetime, dateutil.parser, mimetypes

	__doc__ = """
	A converter that parses Evernote's .enex data dump and outputs its content
	as HTML, JSON, binaries and Markdown (if Pandoc is installed).
	"""

	RE_KEY =re.compile("([^\w\d]\|[_])+")
	RE_SPACES =re.compile("\s+")

	try:
	from wwwclient import *
	except ImportError, e:
	print ("Enextractor requires wwwclient: type `pip install -u wwwclient` or `easy_install wwwclient`")
	sys.exit(-1)

	def save( data, path ):
	"""Saves the given data to the given path, if the data is not null."""
	if data:
	d = os.path.dirname(os.path.abspath(path))
	if not os.path.isdir(d): os.mkdir(d)
	with open(path, "wb") as f:
	logging.info("Writing: {0}".format(path))
	try:
	f.write(data)
	except Exception, e:
	logging.error("Cannot write: {0}".format(e))
	return path
	else:
	return None

	def process_note( xml ):
	title = xml.first("title").text()
	created = xml.first("created").text()
	updated = xml.first("updated").text()
	attributes = [{e.name:e.text()} for e in xml.first("note-attributes").children]
	created = created or datetime.datetime.now()
	created = tuple(dateutil.parser.parse(created).timetuple())
	updated = tuple(dateutil.parser.parse(updated).timetuple()) if updated else created
	# The content is stored as HTML CDATA
	content = xml.first("content").html().split("<![CDATA[",1)[-1].rsplit("]]>",1)[0]
	content = "<html><body>" + content + "</body></html>"
	rsrc = []
	for r in xml.query("resource"):
	data = r.first("date")
	mime = r.first("mime")
	if data and data.get("encoding"):
	enc = data.get("encoding")
	assert enc == "base64", "Unsupported encoding: {0}".format(enc)
	data = base64.decodestring(data)
	# We take tha last extension (it's the most complete)
	ext = mimetypes.guess_all_extensions(mime)[-1]
	rsrc.append(dict(
	data = data,
	mime = mime,
	ext = ext,
	))
	return dict(
	title = title,
	created = created,
	updated = updated,
	attributes = attributes,
	content = content,
	resources = rsrc,
	)

	def write_note( note, path="notes", use_pandoc=True ):
	"""Writes the note in the given directory."""
	name = RE_SPACES.sub("_", RE_KEY.sub("-", note["title"]).lower()).strip()
	logging.info("Writing note {0} in {1}".format(name, path))
	date = note["updated"] or note["created"]
	prefix = os.path.join(path, "{0:04d}-{1:02d}-{2:02d}-{3}".format(date[0], date[1], date[2], name))
	save(json.dumps(note), "{0}.json".format(prefix))
	save(note["content"], "{0}.html".format(prefix))
	if use_pandoc: os.system("pandoc -f html -t markdown {0}.html > {0}.md".format(prefix))
	for i,r in enumerate(note["resources"]):
	save(r["data"], "{0}-{1}.{2}".format(i, r["ext"]))

	def process_enex( path ):
	assert os.path.exists(path), "Given path does not exist: {0}".format(path)
	logging.info("Processing note at {0}".format(path))
	with open(path) as f: t = f.read()
	xml = HTML.tree(t, asXML=True)
	for note in xml.query("note"):
	write_note(process_note(note))


	# -----------------------------------------------------------------------------
	#
	# SECTION
	#
	# -----------------------------------------------------------------------------

	def run( args ):
	if not args:
	logging.error("run(): At least one .enex file path required")
	else:
	for p in args:
	process_enex(p)

	# -----------------------------------------------------------------------------
	#
	# MAIN
	#
	# -----------------------------------------------------------------------------

	if __name__ == "__main__":
	logging.basicConfig(level=logging.DEBUG,stream=sys.stderr)
	run(sys.argv[1:])

	# EOF - vim: ts=4 sw=4 noet