def combine_users_tweets():
timelines_cursor = get_users_timeline_from_db()
urls_pattern = 'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+'
i=0
for tl in timelines_cursor:
i += 1
if i < 10:
continue
DataOperations.append_to_file("temp", str(tl['user_id']))
for tweet in tl['timeline']:
first_text = tweet['text']
lean_text = first_text
lean_text.encode('ascii', 'ignore')
lean_text = remove_entities(lean_text, urls_pattern)
testObj = TextProcesor.TextProcesor()
lean_text = testObj.removeSpecialChars(lean_text)
lean_text_arr = testObj.splitToTokens(lean_text)
lean_text_arr = testObj.removeStopwords(lean_text_arr)
lean_text_arr = testObj.removeSingles(lean_text_arr)
DataOperations.append_arr_to_file("temp", lean_text_arr)
return
