Merge pull request #172 from wardnath/reset_pandas

add function to clean accumulated pandas storage data
#169 

Twint.py

@@ -122,6 +122,7 @@ def initialize(args):
     c.Videos = args.videos
     c.Media = args.media
     c.Replies = args.replies
+    c.Pandas_clean = args.pandas_clean
     return c
 
 def options():
@@ -184,6 +185,7 @@ def options():
     ap.add_argument("--images", help="Display only Tweets with images.", action="store_true")
     ap.add_argument("--media", help="Display Tweets with only images or videos.", action="store_true")
     ap.add_argument("--replies", help="Display replies to a subject.", action="store_true")
+    ap.add_argument("-pc","--pandas-clean", help="Automatically clean Pandas dataframe at every scrape.")
     args = ap.parse_args()
 
     return args
@@ -210,6 +212,9 @@ def main():
     if not args.essid:
         args.essid = ""
 
+    if args.pandas_clean:
+        twint.storage.panda.clean()
+
     c = initialize(args)
 
     if args.favorites:

twint/config.py

@@ -47,3 +47,4 @@ class Config:
     Videos = False
     Media = False
     Replies = False
+    Pandas_clean = True

twint/run.py

-from . import datelock, feed, get, output, verbose
+from . import datelock, feed, get, output, verbose, storage
 from asyncio import get_event_loop
 from datetime import timedelta
 from .storage import db
@@ -16,6 +16,9 @@ class Twint:
         self.d = datelock.Set(self.config.Until, self.config.Since)
         verbose.Elastic(config.Elasticsearch)
 
+        if self.config.Pandas_clean:
+            storage.panda.clean()
+
         if not self.config.Timedelta:
             if (self.d._until - self.d._since).days > 30:
                 self.config.Timedelta = 30

twint/storage/panda.py

@@ -6,7 +6,6 @@ import warnings
 _blocks = []
 
 def update(Tweet, session):
-    day = weekday(strftime("%A", localtime(Tweet.datetime)))
     dt = f"{Tweet.datestamp} {Tweet.timestamp}"
 
     _data = {
@@ -18,8 +17,6 @@ def update(Tweet, session):
                 "hashtags": Tweet.hashtags,
                 "user_id": Tweet.user_id,
                 "username": Tweet.username,
-                "day": day,
-                "hour": hour(Tweet.datetime),
                 "link": Tweet.link,
                 "retweet": Tweet.retweet,
                 "user_rt": Tweet.user_rt,
@@ -32,6 +29,9 @@ def get():
     df = pd.DataFrame(_blocks)
     return df
 
+def clean():
+    _blocks.clear()
+
 def save(_filename, _dataframe, **options):
     if options.get("dataname"):
         _dataname = options.get("dataname")
@@ -53,7 +53,9 @@ def save(_filename, _dataframe, **options):
 
 def read(_filename, **options):
     if not options.get("dataname"):
-        _dataname = "Twint"
+        _dataname = "twint"
+    else:
+        _dataname = options.get("dataname")
 
     if not options.get("type"):
         _store = pd.HDFStore(_filename)