Last active
November 14, 2019 11:20
-
-
Save ultrafunkamsterdam/a4c7e12a658a26113e48f2655670ea09 to your computer and use it in GitHub Desktop.
Print indented html tag structure from BeautifulSoup tag
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """ | |
| Print indented html tag structure from Beautifulsoup tag | |
| example: | |
| >>> soup = bs4.BeautifulSoup(some_html, 'html.parser') # or 'lxml' | |
| >>> make_structure(soup) | |
| out: | |
| <html> | |
| <head> | |
| <title> | |
| </title> | |
| <script> | |
| </script> | |
| <script> | |
| </script> | |
| <script> | |
| </script> | |
| <script> | |
| </script> | |
| <script> | |
| </script> | |
| </head> | |
| <body> | |
| <div> | |
| <nav> | |
| <div> | |
| <div> | |
| <a> | |
| </a> | |
| <div> | |
| </div> | |
| <div> | |
| <div> | |
| <span> | |
| </span> | |
| </div> | |
| <div> | |
| <a> | |
| </a> | |
| """ | |
| import bs4 | |
| def make_structure(tag:bs4.Tag, i=0): | |
| try: | |
| children = list(tag.children) | |
| except: | |
| children = [] | |
| if len(children): | |
| i += 1 | |
| print(' ' * i, '<' + tag.name + '>') | |
| for t in children: | |
| make_structure(t, i) | |
| print(' ' * i, '</' + tag.name + '>') | |
| else: | |
| i -= 1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment