Added index for users and more

Added new index for users

Added function `elasticsearch.UserProfile()` to index users into Elasticsearch instance

Added `_save_` to save the format of dates and times before formatting for Elasticsearch format

index-tweets.json

 PUT twint
 {
-  "mappings" : {
+  "mappings": {
     "items": {
       "properties": {
         "id": {"type": "long"},

index-user.json

+PUT twintUser
+{
+  "mappings": {
+    "items": {
+      "properties": {
+        "id": {"type": "keyword"},
+        "name": {"type": "keyword"},
+        "username": {"type": "keyword"},
+        "bio": {"type": "text"},
+        "location": {"type": "keyword"},
+        "url": {"type": "text"},
+        "join_datetime": {"type": "date", "format": "yyyy-MM-dd HH:mm:ss"},
+        "join_date": {"type": "date", "format": "yyyy-MM-dd"},
+        "join_time": {"type": "date", "format": "HH:mm:ss"},
+        "tweets": {"type": "integer"},
+        "following": {"type": "integer"},
+        "followers": {"type": "integer"},
+        "likes": {"type": "integer"},
+        "media": {"type": "integer"},
+        "private": {"type": "boolean"},
+        "verified": {"type": "boolean"},
+        "avatar": {"type": "text"},
+        "session": {"type": "keyword"}
+      }
+    }
+  }
+  ,
+  "settings": {
+    "number_of_shards": 1
+  }
+}
\ No newline at end of file

twint/elasticsearch.py

@@ -150,7 +150,7 @@ def Follow(es, user, follow, session):
     actions = []
 
     j_data = {
-            "_index": "twintgraph2",
+            "_index": "twintGraph",
             "_type": "items",
             "_id": user + "_" + follow + "_" + session,
             "_source": {
@@ -165,3 +165,38 @@ def Follow(es, user, follow, session):
     with nostdout():
         helpers.bulk(es, actions, chunk_size=2000, request_timeout=200)
     actions = []
+
+def UserProfile(es, user, follow, session):
+    actions = []
+
+    j_data = {
+            "_index": "twintUser",
+            "_type": "items",
+            "_id": user.id + "_" + user.join_date + "_" + user.join_time + "_" + session,
+            "_source": {
+                "id": user.id,
+                "name": user.name,
+                "username": user.username,
+                "bio": user.bio,
+                "location": user.location,
+                "url": user.url,
+                "join_datetime": user.join_date + " " + user.join_time,
+                "join_date": user.join_date,
+                "join_time": user.join_time,
+                "tweets": user.tweets,
+                "following": user.following,
+                "followers": user.followers,
+                "likes": user.likes,
+                "media": user.media_count,
+                "private": user.is_private,
+                "verified": user.is_verified,
+                "avatar": user.avatat,
+                "session": session
+                }
+            }
+    actions.append(j_data)
+
+    es = Elasticsearch(es)
+    with nostdout():
+        helpers.bulk(es, actions, chunk_size=2000, request_timeout=200)
+    actions = []

twint/output.py

+from datetime import datetime
+
 from . import db, elasticsearch, format, write
 from .tweet import Tweet
 from .user import User
@@ -53,8 +55,14 @@ async def Users(u, config, conn):
         db.user(conn, config.Username, config.Followers, user)
 
     #if config.Elasticsearch:
-    #    elasticsearch.Follow(config.Elasticsearch, user,
+    #    _save_date =  user.join_date
+    #    _save_time = user.join_time
+    #    user.join_date = str(datetime.strptime(user.join_date, "%d %b %Y")).split()[0]
+    #    user.join_time = str(datetime.strptime(user.join_time, "%I:%M %p")).split()[1]
+    #    elasticsearch.UserProfile(config.Elasticsearch, user,
     #            config.Username, config.Essid)
+    #    user.join_date = _save_date
+    #    user.join_time = _save_time
 
     _output(user, output, config)