Created
October 5, 2012 14:34
-
-
Save max747/3840122 to your computer and use it in GitHub Desktop.
BeautifulScrap
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
| #!/usr/bin/env python | |
| from __future__ import print_function | |
| from BeautifulSoup import BeautifulSoup | |
| def scrape(src, expr): | |
| soup = BeautifulSoup(src) | |
| expr_stack = expr.split(".") | |
| scrap = _scrape(soup, expr_stack) | |
| print(scrap) | |
| def _scrape(soup, expr_stack): | |
| _soup = soup.findAll(expr_stack[0]) | |
| for token in expr_stack[1:]: | |
| if token.isdigit(): | |
| _soup = _soup.__getitem__(int(token)) | |
| elif hasattr(_soup, "__getslice__"): | |
| _soup = _soup.__getitem__(0) | |
| else: | |
| _soup = getattr(_soup, token) | |
| return _soup | |
| if __name__ == "__main__": | |
| import sys | |
| expr = sys.argv[1] | |
| src = sys.stdin.read() | |
| scrape(src, expr) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment