We use cookies to ensure you have the best browsing experience on our website. Please read our cookie policy for more information about how we use cookies.
  1. Prepare
  2. Python
  3. Regex and Parsing
  4. Detect HTML Tags, Attributes and Attribute Values
  5. Discussions

Detect HTML Tags, Attributes and Attribute Values

  • nehrusethuraman0
     + 0 comments
    import re
import sys

N = int(input())
text = sys.stdin.read()

text = """<head>
<title>HTML</title>
</head>
<object type="application/x-flash" 
  data="your-file.swf" 
  width="0" height="0">
  <!-- <param name="movie" value="your-file.swf" /> -->
  <param name="quality" value="high"/>
</object>"""

regex_endtag = r'(?<=<)([a-zA-Z0-9]+)([\s\S]*?)/?>'
regex_comment = r'\<!--.*?-\>'

processed_input = re.sub(regex_comment, '', text)


header = []
for tag in re.findall(regex_endtag, processed_input):
    header.append(tag)

cleaned_list = [(key, value.replace('\n', '').replace('"', '').strip()) for key, value in header]

cleaned_list_final = [
    (key,) if value == '' else (key, value) 
    for key, value in cleaned_list
]

def print_formatted_list(items):
    for item in items:
        tag = item[0]
        print(tag)
        if len(item) > 1:
            attributes = item[1].split()
            for attribute in attributes:
                key, value = attribute.split('=')
                print(f'-> {key} > {value}')

print_formatted_list(cleaned_list_final)