adds multiprocessing to scrape tweets.

This commit is contained in:
Michael Beck
2023-06-23 16:41:20 +02:00
parent c675db9d00
commit 5d0c41407e
3 changed files with 71 additions and 52 deletions

View File

@ -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()