kopia lustrzana https://github.com/bellingcat/auto-archiver
Fix manifests for required configs.
rodzic
fade68c6f4
commit
527438826c
|
@ -8,7 +8,6 @@
|
|||
},
|
||||
"configs": {
|
||||
"api_endpoint": {
|
||||
"default": None,
|
||||
"required": True,
|
||||
"help": "API endpoint where calls are made to",
|
||||
},
|
||||
|
|
|
@ -7,7 +7,6 @@
|
|||
},
|
||||
"configs": {
|
||||
"api_token": {
|
||||
"default": None,
|
||||
"type": "str",
|
||||
"required": True,
|
||||
"help": "An Atlos API token. For more information, see https://docs.atlos.org/technical/api/",
|
||||
|
|
|
@ -22,8 +22,7 @@
|
|||
"help": "how to name stored files: 'random' creates a random string; 'static' uses a replicable strategy such as a hash.",
|
||||
"choices": ["random", "static"],
|
||||
},
|
||||
"root_folder_id": {"default": None,
|
||||
# "required": True,
|
||||
"root_folder_id": {"required": True,
|
||||
"help": "root google drive folder ID to use as storage, found in URL: 'https://drive.google.com/drive/folders/FOLDER_ID'"},
|
||||
"oauth_token": {"default": None,
|
||||
"help": "JSON filename with Google Drive OAuth token: check auto-archiver repository scripts folder for create_update_gdrive_oauth_token.py. NOTE: storage used will count towards owner of GDrive folder, therefore it is best to use oauth_token_filename over service_account."},
|
||||
|
|
|
@ -12,8 +12,7 @@
|
|||
"configs": {
|
||||
"access_token": {"default": None,
|
||||
"help": "a valid instagrapi-api token"},
|
||||
"api_endpoint": {"default": None,
|
||||
# "required": True,
|
||||
"api_endpoint": {"required": True,
|
||||
"help": "API endpoint to use"},
|
||||
"full_profile": {
|
||||
"default": False,
|
||||
|
|
|
@ -9,11 +9,9 @@
|
|||
},
|
||||
"requires_setup": True,
|
||||
"configs": {
|
||||
"username": {"default": None,
|
||||
"required": True,
|
||||
"username": {"required": True,
|
||||
"help": "a valid Instagram username"},
|
||||
"password": {
|
||||
"default": None,
|
||||
"required": True,
|
||||
"help": "the corresponding Instagram account password",
|
||||
},
|
||||
|
|
|
@ -7,11 +7,9 @@
|
|||
"python": ["loguru", "vk_url_scraper"],
|
||||
},
|
||||
"configs": {
|
||||
"username": {"default": None,
|
||||
"required": True,
|
||||
"username": {"required": True,
|
||||
"help": "valid VKontakte username"},
|
||||
"password": {"default": None,
|
||||
"required": True,
|
||||
"password": {"required": True,
|
||||
"help": "valid VKontakte password"},
|
||||
"session_file": {
|
||||
"default": "secrets/vk_config.v2.json",
|
||||
|
|
|
@ -1 +0,0 @@
|
|||
from .wayback_enricher import WaybackExtractorEnricher
|
|
@ -1,30 +0,0 @@
|
|||
{
|
||||
"name": "Wayback Machine Enricher",
|
||||
"type": ["enricher", "archiver"],
|
||||
"requires_setup": True,
|
||||
"dependencies": {
|
||||
"python": ["loguru", "requests"],
|
||||
},
|
||||
"entry_point": "wayback_enricher::WaybackExtractorEnricher",
|
||||
"configs": {
|
||||
"timeout": {"default": 15, "help": "seconds to wait for successful archive confirmation from wayback, if more than this passes the result contains the job_id so the status can later be checked manually."},
|
||||
"if_not_archived_within": {"default": None, "help": "only tell wayback to archive if no archive is available before the number of seconds specified, use None to ignore this option. For more information: https://docs.google.com/document/d/1Nsv52MvSjbLb2PCpHlat0gkzw0EvtSgpKHu4mk0MnrA"},
|
||||
"key": {"default": None, "required": True, "help": "wayback API key. to get credentials visit https://archive.org/account/s3.php"},
|
||||
"secret": {"default": None, "required": True, "help": "wayback API secret. to get credentials visit https://archive.org/account/s3.php"},
|
||||
"proxy_http": {"default": None, "help": "http proxy to use for wayback requests, eg http://proxy-user:password@proxy-ip:port"},
|
||||
"proxy_https": {"default": None, "help": "https proxy to use for wayback requests, eg https://proxy-user:password@proxy-ip:port"},
|
||||
},
|
||||
"description": """
|
||||
Submits the current URL to the Wayback Machine for archiving and returns either a job ID or the completed archive URL.
|
||||
|
||||
### Features
|
||||
- Archives URLs using the Internet Archive's Wayback Machine API.
|
||||
- Supports conditional archiving based on the existence of prior archives within a specified time range.
|
||||
- Provides proxies for HTTP and HTTPS requests.
|
||||
- Fetches and confirms the archive URL or provides a job ID for later status checks.
|
||||
|
||||
### Notes
|
||||
- Requires a valid Wayback Machine API key and secret.
|
||||
- Handles rate-limiting by Wayback Machine and retries status checks with exponential backoff.
|
||||
"""
|
||||
}
|
|
@ -0,0 +1 @@
|
|||
from .wayback_extractor_enricher import WaybackExtractorEnricher
|
|
@ -0,0 +1,56 @@
|
|||
{
|
||||
"name": "Wayback Machine Enricher",
|
||||
"type": ["enricher", "archiver"],
|
||||
"entry_point": "wayback_extractor_enricher::WaybackExtractorEnricher",
|
||||
"requires_setup": True,
|
||||
"dependencies": {
|
||||
"python": ["loguru", "requests"],
|
||||
},
|
||||
"configs": {
|
||||
"timeout": {
|
||||
"default": 15,
|
||||
"help": "seconds to wait for successful archive confirmation from wayback, if more than this passes the result contains the job_id so the status can later be checked manually.",
|
||||
},
|
||||
"if_not_archived_within": {
|
||||
"default": None,
|
||||
"help": "only tell wayback to archive if no archive is available before the number of seconds specified, use None to ignore this option. For more information: https://docs.google.com/document/d/1Nsv52MvSjbLb2PCpHlat0gkzw0EvtSgpKHu4mk0MnrA",
|
||||
},
|
||||
"key": {
|
||||
"required": True,
|
||||
"help": "wayback API key. to get credentials visit https://archive.org/account/s3.php",
|
||||
},
|
||||
"secret": {
|
||||
"required": True,
|
||||
"help": "wayback API secret. to get credentials visit https://archive.org/account/s3.php",
|
||||
},
|
||||
"proxy_http": {
|
||||
"default": None,
|
||||
"help": "http proxy to use for wayback requests, eg http://proxy-user:password@proxy-ip:port",
|
||||
},
|
||||
"proxy_https": {
|
||||
"default": None,
|
||||
"help": "https proxy to use for wayback requests, eg https://proxy-user:password@proxy-ip:port",
|
||||
},
|
||||
},
|
||||
"description": """
|
||||
Submits the current URL to the Wayback Machine for archiving and returns either a job ID or the completed archive URL.
|
||||
|
||||
### Features
|
||||
- Archives URLs using the Internet Archive's Wayback Machine API.
|
||||
- Supports conditional archiving based on the existence of prior archives within a specified time range.
|
||||
- Provides proxies for HTTP and HTTPS requests.
|
||||
- Fetches and confirms the archive URL or provides a job ID for later status checks.
|
||||
|
||||
### Notes
|
||||
- Requires a valid Wayback Machine API key and secret.
|
||||
- Handles rate-limiting by Wayback Machine and retries status checks with exponential backoff.
|
||||
|
||||
### Steps to Get an Wayback API Key:
|
||||
- Sign up for an account at [Internet Archive](https://archive.org/account/signup).
|
||||
- Log in to your account.
|
||||
- Navigte to your [account settings](https://archive.org/account).
|
||||
- or: https://archive.org/developers/tutorial-get-ia-credentials.html
|
||||
- Under Wayback Machine API Keys, generate a new key.
|
||||
- Note down your API key and secret, as they will be required for authentication.
|
||||
""",
|
||||
}
|
Ładowanie…
Reference in New Issue