index_events_by_topic.py

import json, codecs


topics = ["CoreOS", 
	"Google", 
	"Microsoft", 
	"Joyent", 
	"ECS", 
	"Rancher", 
	"Hashicorp",
	"Swarm", 
	"Machine", 
	"Engine", 
	"Hub", 
	"Compose",  
	"Kubernetes", 
	"Mesos", 
	"OpenShift", 
	"Red Hat",
	"RedHat" 
	"ECS", 
	"Azure", 
	"Fleet", 
	"ETCD", 
	"Consul", 
	"Terraform",
	"hackathon",
	"tutorial",
	"lightning talk",
	"captains"

]

events_by_topic = []
tags_list = []
tagged_events =[]

with open('events.json','r') as f:
	for group in f:
		events = json.loads(group)
		for e in events:
			try:
				tags_list = []
				desc = e.get('description')
				for t in topics:
					if t.lower() in desc.lower():
						tags_list.append(t)
#				events_by_topic.append(e)
			except:
				pass
			if len(tags_list) > 0:
				e[u"tags"]=tags_list
				tagged_events.append(e)

with codecs.open('tagged_events.json','w', encoding='utf-8') as of:
	json.dump(tagged_events, of,sort_keys=True, ensure_ascii=False)