Fabien SK Fabiensk
Fabiensk
/ wk_dump_extract.py
Created
May 2, 2015 20:16
Extract from a Wikivoyage dump (standard input) a page with a given title (all revisions)
This file contains 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/python3 | |
| import sys | |
| import io | |
| def main(): | |
| f = sys.stdin | |
| title = sys.argv[1].strip() | |
| page = "" | |
| data = None |
This file contains 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/python | |
| import sys, re | |
| def check(expr, text): | |
| res = expr.search(text) | |
| if res==None: | |
| return None | |
| return res.group(1) |