Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- #!/usr/local/bin/python3.7
- # -*- coding: utf-8 -*import
- import re
- text = input()
- pattern = r'(?<=<title>)(?P<title>.+)(?=<\/title>)'
- match = re.search(pattern, text)
- title = match.group('title')
- pattern_content = r'(?<=<body>).+(?=<\/body>)'
- content_match = re.search(pattern_content, text)
- content = content_match.group(0)
- cleaner = re.compile('<[^>]*>|\\[rnt]')
- clean_text = re.sub(cleaner, ' ', content)
- search = r'<[^>]*>|\[rnt]'
- m = re.findall(search, content)
- print(m)
- # cln = re.compile(r'\\[rnt]')
- # cln_text = re.sub(cln, ' ', clean_text)
- print(f'Title: {title}')
- print(f'Content: {clean_text}')
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement