David Fox davidallenfox
davidallenfox
/ dbpedia_redirects.py
Last active
August 25, 2016 01:18
Accepts a term, queries DBpedia for page redirects, returns a set of synonyms.
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
| import sys | |
| from SPARQLWrapper import SPARQLWrapper, JSON, XML, N3, RDF | |
| def dbpedia(term): | |
| term = term.strip() | |
| nterm = term.capitalize().replace(' ','_') | |
| query = """ | |
| PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> | |
| SELECT ?label |
davidallenfox
/ chunk-txt-sm.py
Created
January 15, 2014 15:00
Converts a list of items to a chunked sitemap. Run on the command line; first argument is the text file; second argument is the amount with which to 'chunk'.
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
| from itertools import islice | |
| from lxml import etree, objectify | |
| import sys | |
| def main(filen,chunk): | |
| increment = 0 | |
| with open(filen) as f: | |
| while True: | |
| increment = increment + 1 | |
| smf = "output_"+str(increment)+".xml" |