mirror of
http://git.nowherejezfoltodf4jiyl6r56jnzintap5vyjlia7fkirfsnfizflqd.onion/nihilist/darknet-lantern.git
synced 2025-07-01 22:06:40 +00:00
96 lines
No EOL
2.9 KiB
Python
96 lines
No EOL
2.9 KiB
Python
import utils
|
|
import os
|
|
import conf
|
|
import requests
|
|
|
|
def download_participant_data(participant):
|
|
"""
|
|
Downloads the participants csv files and banner
|
|
|
|
Parameters:
|
|
participant (str): The url of the webring participant.
|
|
|
|
Returns:
|
|
Boolean: True if all files downloaded, False if any of them failed
|
|
"""
|
|
|
|
try:
|
|
utils.print_colors(f"[+] Downloading webring {participant} csv files and banner")
|
|
|
|
local_participant_dir = utils.generate_local_participant_dir(participant)
|
|
|
|
os.makedirs(local_participant_dir, exist_ok=True)
|
|
|
|
for file_name in conf.CSV_FILES:
|
|
|
|
csv_res = requests.get(f'{utils.generate_participant_url(participant)}{file_name}', proxies=conf.PROXIES, timeout=10)
|
|
|
|
with open(f'{local_participant_dir}{file_name}', "w") as file:
|
|
file.write(csv_res.text)
|
|
|
|
banner_res = requests.get(f'{utils.generate_participant_url(participant)}banner.png', stream=True, proxies=conf.PROXIES, timeout=10)
|
|
|
|
banner_path = f'{local_participant_dir}banner.png'
|
|
|
|
with open(banner_path, 'wb') as f:
|
|
f.write(banner_res.content)
|
|
|
|
# SANITY CHECK ON THE BANNER PNG IMAGE:
|
|
if not utils.IsBannerValid(banner_path):
|
|
# if false, overwrite it with the template banner png file
|
|
os.remove(banner_path)
|
|
shutil.copyfile(f'{conf.TEMPLATE_PATH}banner.png', banner_path)
|
|
|
|
utils.print_colors(f"[+] Downloaded webring {participant} csv files and banner")
|
|
|
|
except Exception as err:
|
|
print_colors("[-] Downloading webring participant's files failed.", is_error=True)
|
|
|
|
def clean_csv(df, blacklist):
|
|
"""
|
|
Cleans duplications and blacklisted rows
|
|
|
|
Parameters:
|
|
df (dataframe): The dataframe we want to clean.
|
|
blacklist (list): The blacklisted words.
|
|
|
|
Returns:
|
|
Dataframe: Cleaned dataframe.
|
|
"""
|
|
try:
|
|
if not df.empty:
|
|
df = utils.remove_duplications(df)
|
|
|
|
df = df[~df.apply(lambda row: any(word in str(value) for word in blacklist for value in row), axis=1)]
|
|
|
|
if not df.empty:
|
|
df = df[df.apply(utils.is_row_valid, axis=1)]
|
|
|
|
except Exception as err:
|
|
print_colors("[-] cleaning dataframe failed", is_error=True)
|
|
|
|
return df
|
|
|
|
def mark_sensitive(df, sensitive_list):
|
|
"""
|
|
Marks rows as sensitive
|
|
|
|
Parameters:
|
|
df (dataframe): The dataframe we want to mark.
|
|
sensitive (list): The sensitive words.
|
|
|
|
Returns:
|
|
Dataframe: Marked dataframe.
|
|
"""
|
|
|
|
try:
|
|
if not df.empty:
|
|
sensitive_rows = df.apply(lambda row: any(word in str(value) for word in sensitive_list for value in row), axis=1)
|
|
|
|
df.loc[sensitive_rows, 'Sensitive'] = 'YES'
|
|
df.loc[~sensitive_rows, 'Sensitive'] = 'NO'
|
|
|
|
except Exception as err:
|
|
print_colors("[-] MArking sensitive words failed.", is_error=True)
|
|
|
|
return df |