a/ebooks
1
1
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

Make each line a status instead of just a big text file of words

Browse source
This commit is contained in:
Anthony Wang 2022-02-21 19:20:38 -06:00
parent 10c21fb1cd
commit 1c1a518fc7
Signed by: a
GPG key ID: BC96B00AEC5F2D76
1 changed files with 9 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
data.py
View file

@ -18,18 +18,16 @@ cur.execute('SELECT text FROM statuses WHERE language=\'en\'')
statuses = cur.fetchall()
# Use regex to remove HTML stuff
text = [unescape(sub(r'<[^>]*>', '', status[0])) for status in statuses]
# Extract all words from statuses
words = [word for message in text for word in message.split()]
# Remove URLs and special characters and convert to lowercase
words = [sub(r'[^a-z0-9]', '', word.lower())
for word in words if word.find('://') == -1]
# Remove empty strings
words = [word for word in words if word != '']
for i in range(len(statuses)):
# Remove HTML stuff
statuses[i] = unescape(sub(r'<[^>]*>', '', statuses[i][0])).split()
# Remove URLs and special characters and convert to lowercase
statuses[i] = [sub(r'[^a-z0-9]', '', word.lower()) for word in statuses[i] if word.find('://') == -1]
# Remove empty strings
statuses[i] = ' '.join([word for word in statuses[i] if word != ''])
# Save to output file
with open(args.output, 'w') as f:
for word in words:
print(word, file=f)
for status in statuses:
print(status, file=f)