clean latex file remove all formatting and just keep the mathematical equations formatting active.

latex_cleaner.py

def get_all_data(datasource):
	#print "In get_all_data"
	#datasource = datasource.replace('\n','')
	start = datasource.find('\\textb')
	#import pdb; pdb.set_trace()
	#print start

	if start == -1:
		return None,0
	st_data = datasource.find('f', start)
	end_data = datasource.find('\\textbf',st_data+1)
	data = datasource[st_data+1: end_data]
	return data, end_data

def process_data(seed):
	#print "In process_data"
	while seed:
		data, end_data = get_all_data(seed)
		lists.append(data)
		seed = seed[end_data:]
		if not data:
			break
	return lists

#################### cleaning the \\ from the substrings ############################

def cleanup(lists):
	length = len(lists)
		
	for string in lists:
		if type(string) == str:
			string = string.replace("`\\textit{a}'","'a'")
			string = string.replace('\\begin{center}','')
			string = string.replace('{\uppercase','')
			string = string.replace('\\Large ','')
			string = string.replace('\\end{center}','')
			string = string.replace('\\hspace{15pt}','')
			string = string.replace('}}}','')
			string = string.replace('}}','')
			string = string.replace('{{','')
			string = string.replace('` extit{','')
			string = string.replace("}'", '')
			if r'{Q.' in string:
				index = string.find('{Q.')
				#print index, string[index]
				head = string[index+1:4] 
				body = string[index+5:]
				string = head + ' ' +body
			new_list.append(string)
		if type(string) == None:
			pass
		
	return new_list

	
# tex_file = open('rotatory_motion.txt','r')
# strnew = tex_file.read()
text_file = open('rotatory_motion.txt','r')
# text_file.write(strnew)
# text_file.close()
new_file = open('new_text_gen.txt', 'wb+')


strnew = text_file.read()
#print strnew
lists = []
lists = process_data(strnew)
#print lists
new_list = []
new_list=cleanup(lists)
for item in new_list:
	new_file.write(item)