Last active
October 9, 2018 05:04
-
-
Save WillKoehrsen/1c3afe1786cb36296b82892bd3a914f4 to your computer and use it in GitHub Desktop.
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
import xml.sax | |
class WikiXmlHandler(xml.sax.handler.ContentHandler): | |
"""Content handler for Wiki XML data using SAX""" | |
def __init__(self): | |
xml.sax.handler.ContentHandler.__init__(self) | |
self._buffer = None | |
self._values = {} | |
self._current_tag = None | |
self._pages = [] | |
def characters(self, content): | |
"""Characters between opening and closing tags""" | |
if self._current_tag: | |
self._buffer.append(content) | |
def startElement(self, name, attrs): | |
"""Opening tag of element""" | |
if name in ('title', 'text'): | |
self._current_tag = name | |
self._buffer = [] | |
def endElement(self, name): | |
"""Closing tag of element""" | |
if name == self._current_tag: | |
self._values[name] = ' '.join(self._buffer) | |
if name == 'page': | |
self._pages.append((self._values['title'], self._values['text'])) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment