Python:XML - Revision history

Hdridder at 14:42, 11 August 2022

2022-08-11T14:42:58Z

← Older revision		Revision as of 14:42, 11 August 2022
Line 1:		Line 1:
			[[Category:Python]]
	TODO:		TODO:
	* Check [http://effbot.org/zone/element-iterparse.htm interparse] for parsing large files.		* Check [http://effbot.org/zone/element-iterparse.htm interparse] for parsing large files.

Hdridder: /* Parse into dict */

2020-12-15T14:12:41Z

Parse into dict

← Older revision		Revision as of 14:12, 15 December 2020
Line 268:		Line 268:

	def get_node(block,tag):		def get_node(block,tag):
	taglist = re.findall('<\s'+tag+'[\s\>].?</'+tag,block,re.DOTALL)		taglist = re.findall('<\s'+tag+'[\s\>].?</'+tag+'\s*>',block,re.DOTALL)
	if len(taglist) == 0:		if len(taglist) == 0:
	taglist = re.findall('<\s'+tag+'.?/>',block,re.DOTALL)		taglist = re.findall('<\s'+tag+'.?/>',block,re.DOTALL)

Hdridder at 10:15, 1 December 2020

2020-12-01T10:15:07Z

← Older revision		Revision as of 10:15, 1 December 2020
Line 2:		Line 2:
	* Check [http://effbot.org/zone/element-iterparse.htm interparse] for parsing large files.		* Check [http://effbot.org/zone/element-iterparse.htm interparse] for parsing large files.
	* Check lxml.etree as, [https://lxml.de/1.3/compatibility.html according to the developers], it offers a lot more functionality, such as XPath, XSLT, Relax NG, and XML Schema support, which (c)ElementTree does not offer.		* Check lxml.etree as, [https://lxml.de/1.3/compatibility.html according to the developers], it offers a lot more functionality, such as XPath, XSLT, Relax NG, and XML Schema support, which (c)ElementTree does not offer.

			[[XML\|Generic page on XML]]

	;Convert XML to a dict		;Convert XML to a dict

Hdridder: /* Parse into dict */

2020-12-01T10:12:54Z

Parse into dict

← Older revision		Revision as of 10:12, 1 December 2020
Line 273:		Line 273:

	def get_content(block,tag):		def get_content(block,tag):
			content = None
	content_mo = re.search('<\s'+tag+'[\s\>].?>?(.?)</'+tag+'\s>',block,re.DOTALL)		content_mo = re.search('<\s'+tag+'[\s\>].?>?(.?)</'+tag+'\s>',block,re.DOTALL)
	if content_mo:		if content_mo:
Line 280:		Line 281:

	def get_attr(block,attr):		def get_attr(block,attr):
			attrvalue = None
	attribute_mo = re.search(r' '+attr+'\s=\s[\"\'](.*?)[\"\']',block,re.DOTALL)		attribute_mo = re.search(r' '+attr+'\s=\s[\"\'](.*?)[\"\']',block,re.DOTALL)
	if attribute_mo:		if attribute_mo:

Hdridder at 10:59, 28 October 2020

2020-10-28T10:59:09Z

← Older revision		Revision as of 10:59, 28 October 2020
Line 2:		Line 2:
	* Check [http://effbot.org/zone/element-iterparse.htm interparse] for parsing large files.		* Check [http://effbot.org/zone/element-iterparse.htm interparse] for parsing large files.
	* Check lxml.etree as, [https://lxml.de/1.3/compatibility.html according to the developers], it offers a lot more functionality, such as XPath, XSLT, Relax NG, and XML Schema support, which (c)ElementTree does not offer.		* Check lxml.etree as, [https://lxml.de/1.3/compatibility.html according to the developers], it offers a lot more functionality, such as XPath, XSLT, Relax NG, and XML Schema support, which (c)ElementTree does not offer.

			;Convert XML to a dict
			<syntaxhighlight lang=python>
			import xmltodict
			dict1 = xmltodict.parse(xml-string)
			</syntaxhighlight>

	;from xml.etree import ElementTree as ET		;from xml.etree import ElementTree as ET

Hdridder at 10:09, 23 April 2020

2020-04-23T10:09:35Z

← Older revision		Revision as of 10:09, 23 April 2020
Line 260:		Line 260:

	def get_node(block,tag):		def get_node(block,tag):
	taglist = re.findall('<\s'+tag+'[\s\>].?</'+tag',block,re.DOTALL)		taglist = re.findall('<\s'+tag+'[\s\>].?</'+tag,block,re.DOTALL)
	if len(taglist) == 0:		if len(taglist) == 0:
	taglist = re.findall('<\s'+tag+'.?/>',block,re.DOTALL)		taglist = re.findall('<\s'+tag+'.?/>',block,re.DOTALL)

Hdridder at 20:52, 27 January 2020

2020-01-27T20:52:48Z

← Older revision		Revision as of 20:52, 27 January 2020
Line 3:		Line 3:
	* Check lxml.etree as, [https://lxml.de/1.3/compatibility.html according to the developers], it offers a lot more functionality, such as XPath, XSLT, Relax NG, and XML Schema support, which (c)ElementTree does not offer.		* Check lxml.etree as, [https://lxml.de/1.3/compatibility.html according to the developers], it offers a lot more functionality, such as XPath, XSLT, Relax NG, and XML Schema support, which (c)ElementTree does not offer.

	;from xml.etree import ElementTree		;from xml.etree import ElementTree as ET
	:Load XML-support		:Load XML-support

	;tree = ~~get_tree~~(filename)		;tree = ET.parse(filename)
	:Read the file into an XML-tree		:Read the file or an xml-sting into an XML-tree

	;root = tree.getroot()		;root = tree.getroot()
			;root = ET.fromstring(xml-string)
	:Get the tree root element object		:Get the tree root element object

Line 19:		Line 20:
	;element.text		;element.text
	:<tag attribname=attrib>text</tag>		:<tag attribname=attrib>text</tag>

			;element.find(elementname)
			:Get first subelement by name (element can be root too)

	Code example:		Code example:
Line 32:		Line 36:
	import os		import os
	import sys		import sys
	from xml.etree import ElementTree		from xml.etree import ElementTree as ET

	def main():		def main():
Line 55:		Line 59:
	if os.path.isfile(filename):		if os.path.isfile(filename):
	#with open(filename, 'r') as f:		#with open(filename, 'r') as f:
	# tree = ~~ElementTree~~.parse(f)		# tree = ET.parse(f)
	tree = ~~ElementTree~~.parse(filename)		tree = ET.parse(filename)
	else:		else:
	usage()		usage()

Hdridder at 08:10, 26 April 2019

2019-04-26T08:10:57Z

← Older revision		Revision as of 08:10, 26 April 2019
Line 1:		Line 1:
	TODO: Check ~~out~~ [http://effbot.org/zone/element-iterparse.htm interparse] for parsing large files.		TODO:
			* Check [http://effbot.org/zone/element-iterparse.htm interparse] for parsing large files.
			* Check lxml.etree as, [https://lxml.de/1.3/compatibility.html according to the developers], it offers a lot more functionality, such as XPath, XSLT, Relax NG, and XML Schema support, which (c)ElementTree does not offer.

	;from xml.etree import ElementTree		;from xml.etree import ElementTree

Hdridder: /* Parse into dict */

2019-01-04T15:26:35Z

Parse into dict

← Older revision		Revision as of 15:26, 4 January 2019
Line 225:		Line 225:
	newblock = newblock[garbage_mo.end():]		newblock = newblock[garbage_mo.end():]
	while len(newblock) > 0:		while len(newblock) > 0:
	~~#Remove empty spaces and line endings (for formatted files)~~		block = blockrest+newblock)
	block = ~~re.sub('>\s[\n\r]+\s<','><',~~blockrest+newblock)
	blockrest,result = do_it(block,result)		blockrest,result = do_it(block,result)
	newblock = f1.read(blockl)		newblock = f1.read(blockl)
Line 235:		Line 234:
	tag1list = get_node(block,'TAG1')		tag1list = get_node(block,'TAG1')
	for tag1 in tag1list:		for tag1 in tag1list:
	block = block.replace(tag1,'',1)		#Remove processed part of block
			#block = block.replace(tag1,'',1)
			#or everything from the beginning
			dataend = block.find(mecontext)+len(mecontext)
			block = block[dataend:]

	tag1id = get_attr(tag1,'ID')		tag1id = get_attr(tag1,'ID')
	~~try~~:		if tag1id in result:
	~~result[tag1id]~~		pass
	~~except KeyError~~:		else:
	result[tag1id] = set()		result[tag1id] = set()
	tag2list = get_node(tag1,'TAG2')		tag2list = get_node(tag1,'TAG2')
Line 250:		Line 254:

	def get_node(block,tag):		def get_node(block,tag):
	taglist = re.findall('<\s'+tag+'[\s\>].?</'+tag',block)		taglist = re.findall('<\s'+tag+'[\s\>].?</'+tag',block,re.DOTALL)
	if len(taglist) == 0:		if len(taglist) == 0:
	taglist = re.findall('<\s'+tag+'.?/>',block)		taglist = re.findall('<\s'+tag+'.?/>',block,re.DOTALL)
	return taglist		return taglist


	def get_content(block,tag):		def get_content(block,tag):
	content_mo = re.search('<\s'+tag+'[\s\>].?>?(.?)</'+tag+'\s>',block)		content_mo = re.search('<\s'+tag+'[\s\>].?>?(.?)</'+tag+'\s>',block,re.DOTALL)
	if content_mo:		if content_mo:
	content = content_mo.group(1)		content = content_mo.group(1)
Line 264:		Line 268:

	def get_attr(block,attr):		def get_attr(block,attr):
	attribute_mo = re.search(r' '+attr+'\s=\s[\"\'](.*?)[\"\']',block)		attribute_mo = re.search(r' '+attr+'\s=\s[\"\'](.*?)[\"\']',block,re.DOTALL)
	if attribute_mo:		if attribute_mo:
	attrvalue = attribute_mo.group(1)		attrvalue = attribute_mo.group(1)

Hdridder: /* Parse into dict */

2019-01-04T14:47:30Z

Parse into dict

← Older revision		Revision as of 14:47, 4 January 2019
Line 250:		Line 250:

	def get_node(block,tag):		def get_node(block,tag):
	taglist = re.findall('<\s'+tag+'\s+.?</'+tag~~+'\s*>~~',block)		taglist = re.findall('<\s'+tag+'[\s\>].?</'+tag',block)
	if len(taglist) == 0:		if len(taglist) == 0:
	taglist = re.findall('<\s'+tag+'.?/>',block)		taglist = re.findall('<\s'+tag+'.?/>',block)
Line 257:		Line 257:

	def get_content(block,tag):		def get_content(block,tag):
	content_mo = re.search('<\s'+tag+'.?>(.?)</'+tag+'\s>',block)		content_mo = re.search('<\s'+tag+'[\s\>].?>?(.?)</'+tag+'\s>',block)
	if content_mo:		if content_mo:
	content = content_mo.group(1)		content = content_mo.group(1)