You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
15 lines
514 B
Python
15 lines
514 B
Python
import csv, sys
|
|
|
|
outf = csv.writer(sys.stdout)
|
|
last_row = None
|
|
outf.writerow(["url", "start", "end", "text"])
|
|
for row in csv.DictReader(sys.stdin):
|
|
if last_row is not None:
|
|
if last_row['url'] == row['url']:
|
|
outf.writerow([last_row['url'], last_row['start'], row['start'], last_row['text']])
|
|
else:
|
|
outf.writerow([last_row['url'], last_row['start'], None, last_row['text']])
|
|
last_row = row
|
|
|
|
outf.writerow([last_row['url'], last_row['start'], None, last_row['text']])
|