import unicodedata
from html.parser import HTMLParser

class MyHTMLParser(HTMLParser):
	CDATA_CONTENT_ELEMENTS = ("script", "style", "code")
	def __init__(self, strict=False):
		super(MyHTMLParser, self).__init__()
		self.laststarttag = None
		self.secondtolaststarttag = None
		self.codeblocks = []
		self.textblock = ""
	def remove_accents(self, input_str):
		nkfd_form = unicodedata.normalize('NFKD', input_str)
		return u"".join([c for c in nkfd_form if not unicodedata.combining(c)])
	def get_code(self):
		rcodeblocks = []
		for codeblock in self.codeblocks:
			codeblock = codeblock.replace("<br>", "\n").replace("&gt;", ">").replace("&lt;", "<")
			codeblock = self.remove_accents(codeblock)
			codeblock = codeblock.encode('ascii', 'ignore')
			rcodeblocks.append(codeblock.decode())
		self.codeblocks = []
		return rcodeblocks
	def get_text(self):
		textblock = self.remove_accents(self.textblock)
		textblock = textblock.encode('ascii', 'ignore').decode()
		self.textblock = ""
		return textblock
	def handle_starttag(self, tag, attrs):
		self.secondtolaststarttag = self.laststarttag
		self.laststarttag = tag
	def handle_endtag(self, tag):
		self.secondtolaststarttag = None
		self.laststarttag = None
	def handle_data(self, data):
		if self.secondtolaststarttag == "pre" and self.laststarttag == "code":
			self.codeblocks.append(data)
		else:
			if not self.textblock:
				self.textblock = data
			else:
				self.textblock += "\n\n" + data