Last active
March 31, 2016 00:24
-
-
Save JaimieMurdock/89b943bed88b69ab5a503f8bd03b6979 to your computer and use it in GitHub Desktop.
InPhO SEP-Wikipedia Crosswalk
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/env python | |
import codecs | |
import json | |
import urllib.request | |
import sys | |
# 1. Get Data from InPhO API | |
# https://inpho.cogs.indiana.edu/docs/ | |
# select datatype from ['entity', 'idea', 'thinker'] | |
datatype = 'entity' | |
INPHO_URL = 'https://inpho.cogs.indiana.edu/{}.json'.format(datatype) | |
print("Fetching InPhO data from " + INPHO_URL, file=sys.stderr) | |
with urllib.request.urlopen(INPHO_URL) as response: | |
reader = codecs.getreader('utf8') | |
inpho = json.load(reader(response)) | |
inpho = inpho['responseData']['results'] | |
# build dictionary from sep articles to wiki pages, | |
# and wiki pages to sep articles | |
print("Building SEP-Wiki maps", file=sys.stderr) | |
sep_wiki = dict() | |
wiki_sep = dict() | |
for entity in inpho: | |
if entity.get('sep_dir') and entity.get('wiki'): | |
sep_wiki[entity['sep_dir']] = entity['wiki'] | |
wiki_sep[entity['wiki']] = entity['sep_dir'] | |
if __name__ == '__main__': | |
SEP_URL = 'http://plato.stanford.edu/entries/{}/' | |
WIKI_URL = 'https://en.wikipedia.org/wiki/{}' | |
for sep, wiki in sep_wiki.items(): | |
print(','.join([sep,wiki,SEP_URL.format(sep),WIKI_URL.format(wiki)])) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment