extract tweet's information

couchDB/process.py

+import io
+import json
+from datetime import datetime
+import re
+from textblob import TextBlob
+
+
+file1='tweetsWA.json'
+
+output_file=io.open('extractedWA.json','w')
+
+count=1
+
+remove_ms = lambda x:re.sub("\+\d+\s","",x)
+mk_dt = lambda x:datetime.strptime(remove_ms(x), "%a %b %d %H:%M:%S %Y")
+my_date = lambda x:"{:%Y-%m-%d}".format(mk_dt(x))
+my_time = lambda x:"{:%H:%M:%S}".format(mk_dt(x))
+
+with io.open(file1,'r',encoding="utf-8") as f:
+	for line in f:
+		try:
+			my_dict={}
+			my_dict['id']=json.loads(line)['id']
+			create_time=json.loads(line)['created_at']
+			my_dict['date']=my_date(create_time)
+			my_dict['time']=my_time(create_time)
+			tweet = json.loads(line)['text']
+			my_dict['polarity']=TextBlob(tweet).sentiment.polarity
+			my_dict['lang'] = json.loads(line)['lang']
+			json.dump(my_dict,output_file,indent=4)
+		except:
+			pass
+			
+output_file.close()
+
+			
+			
+		
+