adds multiprocessing to scrape tweets.
This commit is contained in:
@ -6,6 +6,12 @@ Created on Wed Jun 21 13:58:42 2023
|
||||
@author: michael
|
||||
'''
|
||||
def deDupe(inFile, outFile):
|
||||
"""Reads file line by line and removes duplicates. Saves deduplicated lines into another file.
|
||||
|
||||
Args:
|
||||
inFile (string): Path to file that shall be deduplicated.
|
||||
outFile (string): Path to output-file.
|
||||
"""
|
||||
from collections import Counter
|
||||
with open(inFile) as f:
|
||||
lines = f.readlines()
|
||||
|
Reference in New Issue
Block a user