Zad_1_lang_corpus_ML/filter.py

17 lines
303 B
Python

import sys
import regex
for line in sys.stdin:
line = line.strip()
sent_len = len(line.split())
if not regex.search('\p{L}', line):
continue
if sent_len == 1:
if 'http' in line:
continue
if line.isalnum():
continue
print(line)