mirror of
http://git.nowherejezfoltodf4jiyl6r56jnzintap5vyjlia7fkirfsnfizflqd.onion/nihilist/darknet-lantern.git
synced 2025-07-01 19:06:41 +00:00
Finished refactoring options 9 and 10
This commit is contained in:
doctor_dev
parent
19e582203b
commit
2a827c0b8b
2 changed files with 84 additions and 97 deletions
|
|
@ -561,9 +561,12 @@ Maintenance:
|
|||
|
||||
participant_url = generate_local_participant_dir(participant.URL)
|
||||
|
||||
print_colors('[+] Reading webrring participant\'s verified and unverified, and removing unverified and blacklisted rows')
|
||||
participant_verified_df = lantern.clean_csv(pd.read_csv(f'{participant_url}verified.csv'), local_blacklist)
|
||||
participant_unverified_df = lantern.clean_csv(pd.read_csv(f'{participant_url}unverified.csv'), local_blacklist)
|
||||
print_colors('[+] Reading webrring participant\'s verified and unverified')
|
||||
participant_verified_df, participant_unverified_df = get_participant_local_verified_and_unverified(participant_url)
|
||||
|
||||
print_colors('[+] Removing unvalidated and blacklisted rows')
|
||||
participant_verified_df = lantern.clean_csv(participant_verified_df, local_blacklist)
|
||||
participant_unverified_df = lantern.clean_csv(participant_unverified_df, local_blacklist)
|
||||
|
||||
print_colors('[+] Marking sensitive rows')
|
||||
participant_verified_df = lantern.mark_sensitive(participant_verified_df, local_sensitive)
|
||||
|
|
@ -585,7 +588,6 @@ Maintenance:
|
|||
|
||||
except Exception as err:
|
||||
print_colors("[-] Option 4 failed suddently, please try again", is_error=True)
|
||||
raise err
|
||||
|
||||
break
|
||||
|
||||
|
|
@ -1005,11 +1007,14 @@ Maintenance:
|
|||
print_colors("[+] 9) Cleaning up all duplicates in your own unverified + verified.csv (based on the url)")
|
||||
|
||||
try:
|
||||
|
||||
|
||||
print_colors('[+] Reading local verified and unverified')
|
||||
verified_df, unverified_df = get_local_verified_and_unverified()
|
||||
|
||||
print_colors('[+] Removing cross dataframe replications')
|
||||
verified_df, unverified_df = remove_cross_dataframe_replications(verified_df, unverified_df)
|
||||
|
||||
print_colors('[+] Saving local verified and unverified')
|
||||
save_local_verified_and_unverified(verified_df, unverified_df)
|
||||
|
||||
except Exception as err:
|
||||
|
|
@ -1020,80 +1025,30 @@ Maintenance:
|
|||
case 10:
|
||||
print_colors("[+] 10) perform sanity checks on all csv files (to mark them as sensitive / or remove the ones that are blacklisted)")
|
||||
|
||||
try:
|
||||
print_colors('[+] Reading local blacklist and sensitive words')
|
||||
local_blacklist, local_sensitive = get_local_blacklist_and_sensitive()
|
||||
|
||||
for participant in os.listdir(conf.PARTICIPANT_DIR):
|
||||
participant_local_dir = conf.PARTICIPANT_DIR + participant + '/'
|
||||
|
||||
print_colors('[+] Reading local blacklist and sensitive words')
|
||||
local_blacklist, local_sensitive = get_local_blacklist_and_sensitive()
|
||||
print_colors('[+] Reading webrring participant\'s verified and unverified')
|
||||
participant_verified_df, participant_unverified_df = get_participant_local_verified_and_unverified(participant_local_dir)
|
||||
|
||||
print_colors('[+] Removing unverified and blacklisted rows')
|
||||
participant_verified_df = lantern.clean_csv(participant_verified_df, local_blacklist)
|
||||
participant_unverified_df = lantern.clean_csv(participant_unverified_df, local_blacklist)
|
||||
|
||||
print_colors('[+] Marking sensitive rows')
|
||||
participant_verified_df = lantern.mark_sensitive(participant_verified_df, local_sensitive)
|
||||
participant_unverified_df = lantern.mark_sensitive(participant_unverified_df, local_sensitive)
|
||||
|
||||
print_colors('[+] Saving local participant verified and unverified')
|
||||
save_local_participant_verified_and_unverified(participant_verified_df, participant_unverified_df, participant_local_dir)
|
||||
|
||||
except Exception as err:
|
||||
print_colors("[-] Option 10 failed suddently, please try again", is_error=True)
|
||||
|
||||
participantspath = rootpath+'www/participants/'
|
||||
for participant in os.listdir(participantspath):
|
||||
print_colors(f"Participant: {participant}")
|
||||
#read=input("Continue?")
|
||||
participantdir= participantspath+participant
|
||||
################ BEGIN SANITY CHECKS FOR EACH PARTICIPANTS ##############
|
||||
# iterate through the participant's verified.csv and unverified.csv files
|
||||
for w in ['verified.csv','unverified.csv']:
|
||||
csvfilepath=participantdir+'/'+w
|
||||
print_colors(f"{csvfilepath}")
|
||||
csvdf = pd.read_csv(csvfilepath, on_bad_lines='skip')
|
||||
rows2delete= [] # it is an empty list at first
|
||||
for i,j in csvdf.iterrows():
|
||||
row=csvdf.loc[i,:].values.tolist()
|
||||
#print_colors(f"{row}")
|
||||
|
||||
|
||||
|
||||
################################ SANITY CHECKS ####################################
|
||||
### SANITY CHECK 0: make sure that ✔️ and x are replaced with YES/NO, as it changed since v1.0.1 ###
|
||||
if csvdf.at[i, 'Status'] == "✔️" or csvdf.at[i, 'Status'] == "YES" :
|
||||
csvdf.at[i, 'Status'] = "YES"
|
||||
csvdf.to_csv(csvfilepath, index=False)
|
||||
else:
|
||||
csvdf.at[i, 'Status'] = "NO"
|
||||
csvdf.to_csv(csvfilepath, index=False)
|
||||
|
||||
if csvdf.at[i, 'Sensitive'] == "✔️" or csvdf.at[i, 'Sensitive'] == "YES" :
|
||||
csvdf.at[i, 'Sensitive'] = "YES"
|
||||
csvdf.to_csv(csvfilepath, index=False)
|
||||
else:
|
||||
csvdf.at[i, 'Sensitive'] = "NO"
|
||||
csvdf.to_csv(csvfilepath, index=False)
|
||||
|
||||
### SANITY CHECK 1: Mark all the rows that have incorrect formatting for deletion###
|
||||
if IsURLValid(csvdf.at[i, 'Instance']) is False or IsCategoryValid(csvdf.at[i, 'Category']) is False or IsNameValid(csvdf.at[i, 'Name']) is False or IsURLValid(csvdf.at[i, 'URL']) is False or IsStatusValid(csvdf.at[i, 'Sensitive']) is False or IsDescriptionValid(csvdf.at[i, 'Description']) is False or IsStatusValid(csvdf.at[i, 'Status']) is False or IsScoreValid(csvdf.at[i, 'Score']) is False:
|
||||
if i not in rows2delete:
|
||||
print_colors(f"Marking row {i} for deletion, as it has invalid inputs")
|
||||
#print_colors(f"{row}")
|
||||
print(IsURLValid(csvdf.at[i, 'Instance']), IsCategoryValid(csvdf.at[i, 'Category']), IsNameValid(csvdf.at[i, 'Name']), IsURLValid(csvdf.at[i, 'URL']), IsStatusValid(csvdf.at[i, 'Sensitive']), IsDescriptionValid(csvdf.at[i, 'Description']), IsStatusValid(csvdf.at[i, 'Status']), IsScoreValid(csvdf.at[i, 'Score']))
|
||||
rows2delete.append(i)
|
||||
read=input("Continue?")
|
||||
|
||||
### SANITY CHECK 2: Mark all rows that are not allowed (blacklist) for deletion ###
|
||||
for k,l in bldf.iterrows():
|
||||
blword=bldf.at[k, 'blacklisted-words']
|
||||
if any(blword in str(x) for x in row) == True:
|
||||
if i not in rows2delete:
|
||||
print_colors(f"Marking row {i} for deletion, as it matches with the blacklisted word {blword}")
|
||||
rows2delete.append(i)
|
||||
#read=input("Continue?")
|
||||
### SANITY CHECK 3: Mark all rows that match sensitive words to be sensitive = YES
|
||||
for k,l in sedf.iterrows():
|
||||
seword=sedf.at[k, 'sensitive-words']
|
||||
if any(seword in str(x) for x in row) == True:
|
||||
print_colors(f"Marking row {i} as sensitive, as it matches with the sensitive word {seword}")
|
||||
csvdf.at[i, 'Sensitive']="YES"
|
||||
csvdf.to_csv(csvfilepath, index=False)
|
||||
#read=input("Continue?")
|
||||
|
||||
|
||||
for i in rows2delete:
|
||||
row=csvdf.loc[i,:].values.tolist()
|
||||
print_colors(f'[+] REMOVING ROW : {i} {row}')
|
||||
csvdf.drop(i, inplace= True)
|
||||
csvdf.to_csv(csvfilepath, index=False)
|
||||
#read=input("Continue?")
|
||||
break
|
||||
|
||||
case 11:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue