The DPS pages can be indexed in Solr.

dpsCreateSolrIndex.py

# Interesting features from the HTML can then be loaded into a Solr index.

import json
from bs4 import BeautifulSoup
import solr

s = solr.SolrConnection('http://localhost:8983/solr')

for recordNum, line in enumerate(open('/Users/awoolford/Documents/scrapeDPS/dpsk12_org/dpsk12_org.json', 'r').readlines()):
	try:
		record = json.loads(line.strip())
		soup = BeautifulSoup(record['html'])
		url = record['url']
		title = soup.title.getText().strip()

		s.add(id=recordNum, url=url, title=title)
		s.commit()

	except:
		pass