From 7e6b75ec9d218fd51d0977a733e84f7003274c76 Mon Sep 17 00:00:00 2001 From: doctor_dev Date: Fri, 30 May 2025 15:30:01 +0000 Subject: [PATCH 1/7] Started refactoring 9 --- scripts/lantern.py | 2 ++ scripts/utils.py | 90 ++++++++++++++++++++++++++++++++++++++++------ 2 files changed, 81 insertions(+), 11 deletions(-) diff --git a/scripts/lantern.py b/scripts/lantern.py index 8985bcd..befcd5f 100644 --- a/scripts/lantern.py +++ b/scripts/lantern.py @@ -1002,6 +1002,7 @@ Maintenance: case 9: print_colors("[+] 9) Cleaning up all duplicates in your own unverified + verified.csv (based on the url)") + for w in ['verified.csv', 'unverified.csv']: csvfilepath = os.path.join(instancepath, w) print_colors(f"Processing file: {csvfilepath}") @@ -1022,6 +1023,7 @@ 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)") + participantspath = rootpath+'www/participants/' for participant in os.listdir(participantspath): print_colors(f"Participant: {participant}") diff --git a/scripts/utils.py b/scripts/utils.py index 513bd15..f31340e 100644 --- a/scripts/utils.py +++ b/scripts/utils.py @@ -469,6 +469,23 @@ def remove_duplications(df): return df +def remove_cross_dataframe_replications(main_df, sub_df): + try: + + main_df = remove_duplications(main_df) + sub_df = remove_duplications(sub_df) + + mask = sub_df['URL'].isin(main_fd['URL']) | df_a['Name'].isin(df_b['Name']) + + sub_df = sub_df[~mask] + + return sub_df + + except: + pass + + return main_df, sub_df + ###TODO: can later remove the inputs and have a "global" local verified and unverified or a class of the local(lantern host) participant def save_local_verified_and_unverified(verified_df, unverified_df): """ @@ -521,6 +538,39 @@ def generate_local_participant_dir(participant): return f'{conf.PARTICIPANT_DIR}{participant}/' +def get_participant_local_verified_and_unverified(participant): + """ + reads the local verified csv and the local unverified csv of a participant + + Parameters: + participant (str): participant's onion address/instance + + Returns: + verified_df(Dataframe): verified.csv as dataframe + unverified_df(Dataframe): unverified.csv as dataframe + """ + + try: + current_instance = get_current_instance() + '/' + try: + verified_df = pd.read_csv(f'{participant}verified.csv') + + except FileNotFoundError: + print_colors("[-] File not found: verified.csv", is_error=True) + + try: + unverified_df = pd.read_csv(f'{participant}unverified.csv') + + except FileNotFoundError: + print_colors("[-] Participant File not found: unverified.csv", is_error=True) + + return verified_df, unverified_df + + except Exception: + print_colors('[-] Failed reading the verified and unverified files',is_error=True) + + return pd.DataFrame(), pd.DataFrame() + def get_official_participants(): """ reads all the official webring participants @@ -548,22 +598,32 @@ def get_local_blacklist_and_sensitive(): """ try: current_instance = get_current_instance() + '/' + try: + blacklist_df = pd.read_csv(f'{conf.PARTICIPANT_DIR}{current_instance}blacklist.csv') + blacklist = blacklist_df.iloc[:, 0].tolist() - blacklist_df = pd.read_csv(f'{conf.PARTICIPANT_DIR}{current_instance}blacklist.csv') - blacklist = blacklist_df.iloc[:, 0].tolist() + except FileNotFoundError: + print_colors("[-] File not found: blacklist.csv", is_error=True) + + try: + sensitive_df = pd.read_csv(f'{conf.PARTICIPANT_DIR}{current_instance}sensitive.csv') + sensitive_list = sensitive_df.iloc[:, 0].tolist() + + except FileNotFoundError: + print_colors("[-] File not found: sensitive.csv", is_error=True) - sensitive_df = pd.read_csv(f'{conf.PARTICIPANT_DIR}{current_instance}sensitive.csv') - sensitive_list = sensitive_df.iloc[:, 0].tolist() return blacklist, sensitive_list + except Exception: - print_colors('[-] Failed reading the blacklist and sensitive words file',is_error=True ) - return [], [] + print_colors('[-] Failed reading the blacklist and sensitive words file',is_error=True) + + return [], [] def get_local_verified_and_unverified(): """ - reads the local verified csv and the local unverified csv + reads the local verified csv and the local unverified csv of the instance Returns: verified_df(Dataframe): verified.csv as dataframe @@ -572,16 +632,24 @@ def get_local_verified_and_unverified(): try: current_instance = get_current_instance() + '/' + try: + verified_df = pd.read_csv(f'{conf.PARTICIPANT_DIR}{current_instance}verified.csv') + + except FileNotFoundError: + print_colors("[-] File not found: verified.csv", is_error=True) - verified_df = pd.read_csv(f'{conf.PARTICIPANT_DIR}{current_instance}verified.csv') + try: + unverified_df = pd.read_csv(f'{conf.PARTICIPANT_DIR}{current_instance}unverified.csv') - unverified_df = pd.read_csv(f'{conf.PARTICIPANT_DIR}{current_instance}unverified.csv') + except FileNotFoundError: + print_colors("[-] File not found: unverified.csv", is_error=True) return verified_df, unverified_df except Exception: - print_colors('[-] Failed reading the verified and unverified files',is_error=True ) - return pd.DataFrame(), pd.DataFrame() + print_colors('[-] Failed reading the verified and unverified files',is_error=True) + + return pd.DataFrame(), pd.DataFrame() def get_local_webring_participants(): """ From 6a70e12646d04f8817488846bbf5d18c0d49685a Mon Sep 17 00:00:00 2001 From: doctor_dev Date: Fri, 30 May 2025 15:30:38 +0000 Subject: [PATCH 2/7] Started refactoring 9 - again --- scripts/lantern.py | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/scripts/lantern.py b/scripts/lantern.py index befcd5f..5e2fae6 100644 --- a/scripts/lantern.py +++ b/scripts/lantern.py @@ -1003,6 +1003,10 @@ Maintenance: case 9: print_colors("[+] 9) Cleaning up all duplicates in your own unverified + verified.csv (based on the url)") + verified_df, unverified_df = utils.get_local_verified_and_unverified() + + + for w in ['verified.csv', 'unverified.csv']: csvfilepath = os.path.join(instancepath, w) print_colors(f"Processing file: {csvfilepath}") @@ -1014,8 +1018,6 @@ Maintenance: #print_colors(f"{csvdf[['URL']]}") csvdf.to_csv(csvfilepath, index=False) print_colors(f"Cleaned data:\n{csvdf[['URL']]}") - except FileNotFoundError: - print_colors(f"File not found: {csvfilepath}") except Exception as e: print_colors(f"An error occurred while processing {csvfilepath}: {e}") break @@ -1023,7 +1025,7 @@ 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)") - + participantspath = rootpath+'www/participants/' for participant in os.listdir(participantspath): print_colors(f"Participant: {participant}") From c4ebef10a48681607a9445d39fa4028108c59bf1 Mon Sep 17 00:00:00 2001 From: doctor_dev Date: Fri, 30 May 2025 17:59:12 +0000 Subject: [PATCH 3/7] finished option 9 ready for test --- .gitignore | 1 + scripts/conf.py | 2 + scripts/lantern.py | 110 ++++++++++++++++++++++----------------------- scripts/utils.py | 10 ++--- 4 files changed, 61 insertions(+), 62 deletions(-) diff --git a/.gitignore b/.gitignore index 8c43f1e..868c262 100644 --- a/.gitignore +++ b/.gitignore @@ -6,4 +6,5 @@ __pycache__/ env/ submissions/submission.csv venv/ +local_testing/* diff --git a/scripts/conf.py b/scripts/conf.py index 3c2728e..9b79107 100644 --- a/scripts/conf.py +++ b/scripts/conf.py @@ -1,3 +1,5 @@ +import re + ROOT_PATH = '/srv/darknet-lantern/' STATIC_PATH = ROOT_PATH + 'www/' TEMPLATE_PATH = ROOT_PATH + 'templates/' diff --git a/scripts/lantern.py b/scripts/lantern.py index 2bd1454..7a2109d 100644 --- a/scripts/lantern.py +++ b/scripts/lantern.py @@ -533,55 +533,60 @@ Maintenance: case 4: print_colors("4) Synchronize new links from new or existing webring participants, into your local csv files") - print_colors('[+] Syncing official webrings to local webrings') + try: - webring_df = verify_official_participants_registered() - - current_instance = get_current_instance() + print_colors('[+] Syncing official webrings to local webrings') - for participant in webring_df.itertuples(index=False, name='columns'): - # Check if the participant is my instance - if current_instance in participant: - continue + webring_df = verify_official_participants_registered() - if not is_participant_reachable(participant.URL): - print_colors("[-] Webring {participant.URL} isn't reachable, skipping", is_error=True) - continue + current_instance = get_current_instance() - print_colors('[+] Downloading participant\'s files to store locally') - lantern.download_participant_data(participant.URL) + for participant in webring_df.itertuples(index=False, name='columns'): + # Check if the participant is my instance + if current_instance in participant: + continue - print_colors('[+] Reading local blacklist and sensitive words') - local_blacklist, local_sensitive = get_local_blacklist_and_sensitive() - - print_colors('[+] Reading local verified and unverified') - local_verified_df, local_unverified_df = get_local_verified_and_unverified() - - 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('[+] 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) + if not is_participant_reachable(participant.URL): + print_colors("[-] Webring {participant.URL} isn't reachable, skipping", is_error=True) + continue - if participant.Trusted == 'YES': - print_colors('[+] This participant is trusted, copying participant\'s verified to local verified') - local_verified_df = merge_verification_df(local_verified_df, participant_verified_df) - - else: - print_colors('[+] This participant is not trusted, copying participant\'s verified to local unverified') - local_unverified_df = merge_verification_df(local_unverified_df, participant_verified_df) - - print_colors('[+] Copying participant\'s unverified to local unverified') - local_unverified_df = merge_verification_df(local_unverified_df, participant_unverified_df) + print_colors('[+] Downloading participant\'s files to store locally') + lantern.download_participant_data(participant.URL) - print_colors('[+] Saving local verified and unverified') - save_local_verified_and_unverified(local_verified_df, local_unverified_df) + print_colors('[+] Reading local blacklist and sensitive words') + local_blacklist, local_sensitive = get_local_blacklist_and_sensitive() - break + print_colors('[+] Reading local verified and unverified') + local_verified_df, local_unverified_df = get_local_verified_and_unverified() + + 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('[+] 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) + + if participant.Trusted == 'YES': + print_colors('[+] This participant is trusted, copying participant\'s verified to local verified') + local_verified_df = merge_verification_df(local_verified_df, participant_verified_df) + + else: + print_colors('[+] This participant is not trusted, copying participant\'s verified to local unverified') + local_unverified_df = merge_verification_df(local_unverified_df, participant_verified_df) + + print_colors('[+] Copying participant\'s unverified to local unverified') + local_unverified_df = merge_verification_df(local_unverified_df, participant_unverified_df) + + print_colors('[+] Saving local verified and unverified') + save_local_verified_and_unverified(local_verified_df, local_unverified_df) + + break + + except Exception: + print_colors("[-] Option 4 failed suddently, please try again", is_error=True) case 5: print_colors("[+] Add a new webring participant (and download their files into their directory (without trusting them yet!))") @@ -997,26 +1002,17 @@ Maintenance: case 9: print_colors("[+] 9) Cleaning up all duplicates in your own unverified + verified.csv (based on the url)") + + try: - verified_df, unverified_df = utils.get_local_verified_and_unverified() + verified_df, unverified_df = utils.get_local_verified_and_unverified() + verified_df, unverified_df = remove_cross_dataframe_replications(verified_df, unverified_df) + save_local_verified_and_unverified(verified_df, unverified_df) - for w in ['verified.csv', 'unverified.csv']: - csvfilepath = os.path.join(instancepath, w) - print_colors(f"Processing file: {csvfilepath}") - try: - csvdf = pd.read_csv(csvfilepath, on_bad_lines='skip') - print_colors(f"Removing duplicates in {csvfilepath}") - #print_colors(f"{csvdf[['URL']]}") - csvdf = csvdf.drop_duplicates(subset=['URL'], keep="first", inplace=False) - #print_colors(f"{csvdf[['URL']]}") - csvdf.to_csv(csvfilepath, index=False) - print_colors(f"Cleaned data:\n{csvdf[['URL']]}") - except Exception as e: - print_colors(f"An error occurred while processing {csvfilepath}: {e}") - break - break + except Exception: + print_colors("[-] Option 9 failed suddently, please try again", is_error=True) case 10: print_colors("[+] 10) perform sanity checks on all csv files (to mark them as sensitive / or remove the ones that are blacklisted)") diff --git a/scripts/utils.py b/scripts/utils.py index e33482d..9c0580c 100644 --- a/scripts/utils.py +++ b/scripts/utils.py @@ -334,7 +334,7 @@ def remove_duplications(df): df = df.drop_duplicates(subset='URL') except Exception: - pass + print_colors('[-] Removing duplication failed',is_error=True) return df @@ -348,10 +348,8 @@ def remove_cross_dataframe_replications(main_df, sub_df): sub_df = sub_df[~mask] - return sub_df - except: - pass + print_colors('[-] Removing cross dataframe duplications failed',is_error=True) return main_df, sub_df @@ -374,10 +372,12 @@ def save_local_verified_and_unverified(verified_df, unverified_df): unverified_df.to_csv(f'{conf.PARTICIPANT_DIR}{current_instance}unverified.csv', index=False) + print_colors('[+] Verified and unverified saved successfully') + return True except Exception: - print_colors('[-] Saving verified and unverified failed',is_error=True ) + print_colors('[-] Saving verified and unverified failed',is_error=True) return False ###################### Getters/Generators ###################### From 1b67f7a2184640e3ba0844b32dacf98c2f2c8c67 Mon Sep 17 00:00:00 2001 From: doctor_dev Date: Fri, 30 May 2025 18:20:52 +0000 Subject: [PATCH 4/7] starting work on option 10 --- scripts/lantern.py | 20 +++++++++++++++----- scripts/logic/lantern_logic.py | 8 ++++---- scripts/utils.py | 26 ++++++++++++++------------ 3 files changed, 33 insertions(+), 21 deletions(-) diff --git a/scripts/lantern.py b/scripts/lantern.py index 7a2109d..1f6a556 100644 --- a/scripts/lantern.py +++ b/scripts/lantern.py @@ -583,10 +583,11 @@ Maintenance: print_colors('[+] Saving local verified and unverified') save_local_verified_and_unverified(local_verified_df, local_unverified_df) - break - - except Exception: + except Exception as err: print_colors("[-] Option 4 failed suddently, please try again", is_error=True) + raise err + + break case 5: print_colors("[+] Add a new webring participant (and download their files into their directory (without trusting them yet!))") @@ -1005,18 +1006,27 @@ Maintenance: try: - verified_df, unverified_df = utils.get_local_verified_and_unverified() + verified_df, unverified_df = get_local_verified_and_unverified() verified_df, unverified_df = remove_cross_dataframe_replications(verified_df, unverified_df) save_local_verified_and_unverified(verified_df, unverified_df) - except Exception: + except Exception as err: print_colors("[-] Option 9 failed suddently, please try again", is_error=True) + break + case 10: print_colors("[+] 10) perform sanity checks on all csv files (to mark them as sensitive / or remove the ones that are blacklisted)") + + + print_colors('[+] Reading local blacklist and sensitive words') + local_blacklist, local_sensitive = get_local_blacklist_and_sensitive() + + + participantspath = rootpath+'www/participants/' for participant in os.listdir(participantspath): print_colors(f"Participant: {participant}") diff --git a/scripts/logic/lantern_logic.py b/scripts/logic/lantern_logic.py index e0f732f..61590fb 100644 --- a/scripts/logic/lantern_logic.py +++ b/scripts/logic/lantern_logic.py @@ -43,7 +43,7 @@ def download_participant_data(participant): utils.print_colors(f"[+] Downloaded webring {participant} csv files and banner") - except Exception: + except Exception as err: print_colors("[-] Downloading webring participant's files failed.", is_error=True) def clean_csv(df, blacklist): @@ -66,7 +66,7 @@ def clean_csv(df, blacklist): if not df.empty: df = df[df.apply(utils.is_row_valid, axis=1)] - except Exception: + except Exception as err: print_colors("[-] cleaning dataframe failed", is_error=True) return df @@ -90,7 +90,7 @@ def mark_sensitive(df, sensitive_list): df.loc[sensitive_rows, 'Sensitive'] = 'YES' df.loc[~sensitive_rows, 'Sensitive'] = 'NO' - except Exception: + except Exception as err: print_colors("[-] MArking sensitive words failed.", is_error=True) - + return df \ No newline at end of file diff --git a/scripts/utils.py b/scripts/utils.py index 9c0580c..0411822 100644 --- a/scripts/utils.py +++ b/scripts/utils.py @@ -152,7 +152,7 @@ def is_participant_reachable(instance): status = requests.get(f'{url}{file_name}',proxies=conf.PROXIES, timeout=10).status_code if status != 200: return False - except Exception: + except Exception as err: return False return True @@ -288,7 +288,7 @@ def is_row_valid(row): IsScoreValid(row['Score']) ) - except Exception: + except Exception as err: return False ###################### General ###################### @@ -316,7 +316,7 @@ def merge_verification_df(receiving_df, merging_df): else: return pd.concat([receiving_df, filtered_df], ignore_index=True) - except Exception: + except Exception as err: return receiving_df def remove_duplications(df): @@ -333,7 +333,7 @@ def remove_duplications(df): df = df.drop_duplicates(subset='Name') df = df.drop_duplicates(subset='URL') - except Exception: + except Exception as err: print_colors('[-] Removing duplication failed',is_error=True) return df @@ -344,12 +344,14 @@ def remove_cross_dataframe_replications(main_df, sub_df): main_df = remove_duplications(main_df) sub_df = remove_duplications(sub_df) - mask = sub_df['URL'].isin(main_fd['URL']) | df_a['Name'].isin(df_b['Name']) + mask = sub_df['URL'].isin(main_df['URL']) | sub_df['Name'].isin(main_df['Name']) sub_df = sub_df[~mask] - except: + except Exception as err: print_colors('[-] Removing cross dataframe duplications failed',is_error=True) + raise err #REMOVE!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! + return main_df, sub_df @@ -376,7 +378,7 @@ def save_local_verified_and_unverified(verified_df, unverified_df): return True - except Exception: + except Exception as err: print_colors('[-] Saving verified and unverified failed',is_error=True) return False @@ -435,7 +437,7 @@ def get_participant_local_verified_and_unverified(participant): return verified_df, unverified_df - except Exception: + except Exception as err: print_colors('[-] Failed reading the verified and unverified files',is_error=True) return pd.DataFrame(), pd.DataFrame() @@ -454,7 +456,7 @@ def get_official_participants(): with open(conf.OFFICIAL_PARTICIPANTS_FILE, 'r') as file: return [line.strip() for line in file if current_instance not in line] - except Exception: + except Exception as err: print_colors('[-] Couldn\'t read official webring participants file',is_error=True ) def get_local_blacklist_and_sensitive(): @@ -485,7 +487,7 @@ def get_local_blacklist_and_sensitive(): return blacklist, sensitive_list - except Exception: + except Exception as err: print_colors('[-] Failed reading the blacklist and sensitive words file',is_error=True) return [], [] @@ -515,7 +517,7 @@ def get_local_verified_and_unverified(): return verified_df, unverified_df - except Exception: + except Exception as err: print_colors('[-] Failed reading the verified and unverified files',is_error=True) return pd.DataFrame(), pd.DataFrame() @@ -542,7 +544,7 @@ def get_local_webring_participants(): return webring_df - except Exception: + except Exception as err: print_colors(f'[-] failed reading webring participants file',is_error=True ) return pd.DataFrame() From 19e582203b515be271aa8cc169611987551139df Mon Sep 17 00:00:00 2001 From: doctor_dev Date: Fri, 30 May 2025 18:21:40 +0000 Subject: [PATCH 5/7] starting work on option 10 - again --- scripts/lantern.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/lantern.py b/scripts/lantern.py index 1f6a556..db178b8 100644 --- a/scripts/lantern.py +++ b/scripts/lantern.py @@ -537,7 +537,7 @@ Maintenance: print_colors('[+] Syncing official webrings to local webrings') - webring_df = verify_official_participants_registered() + webring_df = get_local_webring_participants() current_instance = get_current_instance() From 2a827c0b8b7b336c6b3c93578470306f1ec7e490 Mon Sep 17 00:00:00 2001 From: doctor_dev Date: Fri, 30 May 2025 19:38:04 +0000 Subject: [PATCH 6/7] Finished refactoring options 9 and 10 --- scripts/lantern.py | 103 +++++++++++++-------------------------------- scripts/utils.py | 78 ++++++++++++++++++++++++---------- 2 files changed, 84 insertions(+), 97 deletions(-) diff --git a/scripts/lantern.py b/scripts/lantern.py index db178b8..701d834 100644 --- a/scripts/lantern.py +++ b/scripts/lantern.py @@ -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: diff --git a/scripts/utils.py b/scripts/utils.py index 0411822..c15c57e 100644 --- a/scripts/utils.py +++ b/scripts/utils.py @@ -60,7 +60,7 @@ def IsXFTPServerValid(url: str) -> bool: Returns True if URL is a valid SimpleX XFTP Server URL False otherwise """ - return conf.RecognizeSimplexType(url) == 'xftp' + return RecognizeSimplexType(url) == 'xftp' # stub function def IsSMPServerValid(url: str) -> bool: @@ -68,7 +68,7 @@ def IsSMPServerValid(url: str) -> bool: Returns True if URL is a valid SimpleX SMP Server URL False otherwise """ - return conf.RecognizeSimplexType(url) == 'smp' + return RecognizeSimplexType(url) == 'smp' def IsClearnetLinkValid(url: str) -> bool: """ @@ -242,7 +242,7 @@ def IsNameValid(name: str) -> bool: Check the parameter name only contains [a-zA-Z0-9] and is 64 chars long. """ try: - return bool(VALID_NAME_PATTERN.fullmatch(name.strip())) + return bool(conf.VALID_NAME_PATTERN.fullmatch(name.strip())) except Exception: return False @@ -278,10 +278,10 @@ def is_row_valid(row): """ try: return ( - IsUrlValid(row['Instance']) and + IsURLValid(row['Instance']) and IsCategoryValid(row['Category']) and IsNameValid(row['Name']) and - IsUrlValid(row['URL']) and + IsURLValid(row['URL']) and IsStatusValid(row['Sensitive']) and IsDescriptionValid(row['Description']) and IsStatusValid(row['Status']) and @@ -339,6 +339,17 @@ def remove_duplications(df): return df def remove_cross_dataframe_replications(main_df, sub_df): + """ + remove replications from sub_df that exist in main_df + + Parameters: + main_df (Dataframe): the dataframe to keep replications + sub_df (Dataframe): the dataframe to remove replications + + Returns: + Dataframe: the main_df with removed duplications + Dataframe: the sub_df with removed duplications and removed replications + """ try: main_df = remove_duplications(main_df) @@ -350,7 +361,6 @@ def remove_cross_dataframe_replications(main_df, sub_df): except Exception as err: print_colors('[-] Removing cross dataframe duplications failed',is_error=True) - raise err #REMOVE!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! return main_df, sub_df @@ -365,7 +375,7 @@ def save_local_verified_and_unverified(verified_df, unverified_df): unverified_df (Dataframe): local unverified rows dataframe Returns: - Dataframe: the combined dataframe will be returned + bool: True if successful, False if not """ try: current_instance = get_current_instance() + '/' @@ -382,6 +392,32 @@ def save_local_verified_and_unverified(verified_df, unverified_df): print_colors('[-] Saving verified and unverified failed',is_error=True) return False +def save_local_participant_verified_and_unverified(verified_df, unverified_df, participant): + """ + saves the local verified and unverified of a participant + + Parameters: + verified_df (Dataframe): local verified rows dataframe + unverified_df (Dataframe): local unverified rows dataframe + participant (str): participant's onion local path + + Returns: + bool: True if successful, False if not + """ + try: + + verified_df.to_csv(f'{participant}verified.csv', index=False) + + unverified_df.to_csv(f'{participant}unverified.csv', index=False) + + print_colors('[+] Verified and unverified saved successfully') + + return True + + except Exception as err: + print_colors('[-] Saving verified and unverified failed',is_error=True) + return False + ###################### Getters/Generators ###################### def generate_participant_url(participant): """ @@ -414,7 +450,7 @@ def get_participant_local_verified_and_unverified(participant): reads the local verified csv and the local unverified csv of a participant Parameters: - participant (str): participant's onion address/instance + participant (str): participant's local files path Returns: verified_df(Dataframe): verified.csv as dataframe @@ -422,25 +458,21 @@ def get_participant_local_verified_and_unverified(participant): """ try: - current_instance = get_current_instance() + '/' - try: - verified_df = pd.read_csv(f'{participant}verified.csv') - - except FileNotFoundError: - print_colors("[-] File not found: verified.csv", is_error=True) + verified_df = pd.read_csv(f'{participant}verified.csv') + + except FileNotFoundError: + print_colors("[-] File not found: verified.csv", is_error=True) + return pd.Dataframe(), pd.Dataframe() - try: - unverified_df = pd.read_csv(f'{participant}unverified.csv') + try: + unverified_df = pd.read_csv(f'{participant}unverified.csv') - except FileNotFoundError: - print_colors("[-] Participant File not found: unverified.csv", is_error=True) + except FileNotFoundError: + print_colors("[-] Participant File not found: unverified.csv", is_error=True) + return pd.Dataframe(), pd.Dataframe() - return verified_df, unverified_df + return verified_df, unverified_df - except Exception as err: - print_colors('[-] Failed reading the verified and unverified files',is_error=True) - - return pd.DataFrame(), pd.DataFrame() def get_official_participants(): """ From 8b0ba4833fcf456597da57deecf44e185e11664f Mon Sep 17 00:00:00 2001 From: doctor_dev Date: Fri, 30 May 2025 19:50:34 +0000 Subject: [PATCH 7/7] added dummy folder to git --- .gitignore | 1 + scripts/local_testing/.gitkeep | 0 2 files changed, 1 insertion(+) create mode 100644 scripts/local_testing/.gitkeep diff --git a/.gitignore b/.gitignore index 868c262..e1495ea 100644 --- a/.gitignore +++ b/.gitignore @@ -7,4 +7,5 @@ env/ submissions/submission.csv venv/ local_testing/* +!your_folder/.gitkeep diff --git a/scripts/local_testing/.gitkeep b/scripts/local_testing/.gitkeep new file mode 100644 index 0000000..e69de29