oxeo0/darknet-lantern
1
0
Fork 0
mirror of http://git.nowherejezfoltodf4jiyl6r56jnzintap5vyjlia7fkirfsnfizflqd.onion/nihilist/darknet-lantern.git synced 2025-05-16 20:26:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fill missing description in our unverified.csv that other participants verified.csv have filled

Browse source
This commit is contained in:
valuer 2025-05-10 20:28:48 +02:00
parent 46912beaa1
commit 5d67c21d14
1 changed files with 20 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

20
scripts/lantern.py
View file

@ -729,6 +729,26 @@ Maintenance:
csvdf.drop(i, inplace= True) csvdf.drop(i, inplace= True)
csvdf.to_csv(csvfilepath, index=False) csvdf.to_csv(csvfilepath, index=False)
rows2delete= [] # it is an empty list at first rows2delete= [] # it is an empty list at first
# fill missing description in our unverified.csv that other participants verified.csv have filled
if w == 'verified.csv':
uvdf = pd.read_csv(unverifiedcsvfile, on_bad_lines='skip')
# merge participant's verified.csv on our unverified.csv on URL
merged_df = uvdf.merge(csvdf[['URL', 'Description']],
on='URL',
how='left',
suffixes=('', '_participant'))
# filter empty description that has participant's description
no_descr_filter = ((merged_df['Description'].isna()) | (merged_df['Description'].str.strip() == '')) & \
(~merged_df['Description_participant'].isna()) & (merged_df['Description_participant'].str.strip() != '')
no_descr_filter_count = no_descr_filter.sum()
# update our empty description if the participant has any filled description
if no_descr_filter_count > 0:
merged_df.loc[no_descr_filter, 'Description'] = merged_df.loc[no_descr_filter, 'Description_participant']
# keep only original columns
uvdf_updated = merged_df[uvdf.columns]
uvdf_updated.to_csv(unverifiedcsvfile, index=False)
print(f'[+] Updated {no_descr_filter_count} empty description(s) in your unverified.csv found on partipant\'s {w}')
break break