Created
January 2, 2013 03:33
-
-
Save georgewhewell/4431912 to your computer and use it in GitHub Desktop.
tweepy wrapper to search twitter between datetime
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import tweepy | |
import datetime | |
import time | |
def time_search(*args, **kwargs): | |
begin = kwargs['begin'] | |
end = kwargs['end'] | |
start_time = begin | |
end_time = end | |
# kwargs['since'] = start_time.strftime('%Y-%m-%d') | |
kwargs['until'] = (end_time + datetime.timedelta(days=1)).strftime('%Y-%m-%d') | |
kwargs['rpp'] = 100 | |
results = [] | |
api = tweepy.API() | |
finished = False | |
max_id = 0 | |
while not finished: | |
if len(results) > 0: | |
kwargs['max_id'] = results[len(results) - 1 ].id | |
if kwargs.has_key("until"): | |
del kwargs["until"] | |
Cursor = tweepy.Cursor(api.search, *args, **kwargs) | |
try: | |
for page in Cursor.pages(): | |
for result in page: | |
print "created: %s, start: %s" % (result.created_at, start_time) | |
if result.created_at > end_time: | |
continue | |
if result.created_at < start_time: | |
finished = True | |
break | |
results.append(result) | |
if finished: | |
break | |
except: | |
# Ran out of pages / api quota? | |
pass | |
return results |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment