dynamicguy · April 10, 2023 11:07
diff --git a/text_cleaner.py b/text_cleaner.py
 def text_cleaner(text):
    rules = [
        {r'>\s+': u'>'},  # remove spaces after a tag opens or closes
        {r'\s+': u' '},  # replace consecutive spaces
        {r'\s*<br\s*/?>\s*': u'\n'},  # newline after a <br>
        {r'</(div)\s*>\s*': u'\n'},  # newline after </p> and </div> and <h1/>...
        {r'</(p|h\d)\s*>\s*': u'\n\n'},  # newline after </p> and </div> and <h1/>...
        {r'<head>.*<\s*(/head|body)[^>]*>': u''},  # remove <head> to </head>
        {r'<a\s+href="([^"]+)"[^>]*>.*</a>': r'\1'},  # show links instead of texts
        {r'[ \t]*<[^<]*?/?>': u''},  # remove remaining tags
        {r'^\s+': u''}  # remove spaces at the beginning
    ]
    for rule in rules:
    for (k, v) in rule.items():
        regex = re.compile(k)
        text = regex.sub(v, text)
    text = text.rstrip()
    return text.lower()
	def text_cleaner(text):
	rules = [
	{r'>\s+': u'>'}, # remove spaces after a tag opens or closes
	{r'\s+': u' '}, # replace consecutive spaces
	{r'\s<br\s/?>\s*': u'\n'}, # newline after a <br>
	{r'</(div)\s>\s': u'\n'}, # newline after </p> and </div> and <h1/>...
	{r'</(p\|h\d)\s>\s': u'\n\n'}, # newline after </p> and </div> and <h1/>...
	{r'<head>.<\s(/head\|body)[^>]*>': u''}, # remove <head> to </head>
	{r'<a\s+href="([^"]+)"[^>]>.</a>': r'\1'}, # show links instead of texts
	{r'[ \t]<[^<]?/?>': u''}, # remove remaining tags
	{r'^\s+': u''} # remove spaces at the beginning
	]
	for rule in rules:
	for (k, v) in rule.items():
	regex = re.compile(k)
	text = regex.sub(v, text)
	text = text.rstrip()
	return text.lower()