bellingcat/auto-archiver
1
0
Fork 0
mirror of https://github.com/bellingcat/auto-archiver.git synced 2026-06-12 05:08:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #217 from bellingcat/settings_page

Browse Source 
Settings page user interface
This commit is contained in:
Patrick Robertson
2025-03-07 16:10:50 +00:00
committed by GitHub
parent 928c6f88a9 333201acec
commit 3fac353407
36 changed files with 55642 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/auto_archiver/core/module.py
View File

@@ -80,7 +80,10 @@ class ModuleFactory:
available = self.available_modules(limit_to_modules=[module_name], suppress_warnings=suppress_warnings)
if not available:
raise IndexError(f"Module '{module_name}' not found. Are you sure it's installed/exists?")
message = f"Module '{module_name}' not found. Are you sure it's installed/exists?"
if 'archiver' in module_name:
message += f" Did you mean {module_name.replace('archiver', 'extractor')}?"
raise IndexError(message)
return available[0]
def available_modules(self, limit_to_modules: List[str]= [], suppress_warnings: bool = False) -> List[LazyBaseModule]:

47
src/auto_archiver/core/orchestrator.py
View File

@@ -73,10 +73,20 @@ class ArchivingOrchestrator:
self.basic_parser = parser
return parser
def check_steps(self, config):
for module_type in MODULE_TYPES:
if not config['steps'].get(f"{module_type}s", []):
if module_type == 'feeder' or module_type == 'formatter' and config['steps'].get(f"{module_type}"):
raise SetupError(f"It appears you have '{module_type}' set under 'steps' in your configuration file, but as of version 0.13.0 of Auto Archiver, you must use '{module_type}s'. Change this in your configuration file and try again. \
Here's how that would look: \n\nsteps:\n {module_type}s:\n - [your_{module_type}_name_here]\n {'extractors:...' if module_type == 'feeder' else '...'}\n")
if module_type == 'extractor' and config['steps'].get('archivers'):
raise SetupError(f"As of version 0.13.0 of Auto Archiver, the 'archivers' step name has been changed to 'extractors'. Change this in your configuration file and try again. \
Here's how that would look: \n\nsteps:\n extractors:\n - [your_extractor_name_here]\n enrichers:...\n")
raise SetupError(f"No {module_type}s were configured. Make sure to set at least one {module_type} in your configuration file or on the command line (using --{module_type}s)")
def setup_complete_parser(self, basic_config: dict, yaml_config: dict, unused_args: list[str]) -> None:
# modules parser to get the overridden 'steps' values
modules_parser = argparse.ArgumentParser(
add_help=False,
@@ -101,6 +111,7 @@ class ArchivingOrchestrator:
# but should we add them? Or should we just add them to the 'complete' parser?
if is_valid_config(yaml_config):
self.check_steps(yaml_config)
# only load the modules enabled in config
# TODO: if some steps are empty (e.g. 'feeders' is empty), should we default to the 'simple' ones? Or only if they are ALL empty?
enabled_modules = []
@@ -116,10 +127,6 @@ class ArchivingOrchestrator:
simple_modules = [module for module in self.module_factory.available_modules() if not module.requires_setup]
self.add_individual_module_args(simple_modules, parser)
# for simple mode, we use the cli_feeder and any modules that don't require setup
if not yaml_config['steps']['feeders']:
yaml_config['steps']['feeders'] = ['cli_feeder']
# add them to the config
for module in simple_modules:
for module_type in module.type:
@@ -172,9 +179,6 @@ class ArchivingOrchestrator:
if not parser:
parser = self.parser
# allow passing URLs directly on the command line
parser.add_argument('urls', nargs='*', default=[], help='URL(s) to archive, either a single URL or a list of urls, should not come from config.yaml')
parser.add_argument('--authentication', dest='authentication', help='A dictionary of sites and their authentication methods \
(token, username etc.) that extractors can use to log into \
a website. If passing this on the command line, use a JSON string. \
@@ -194,7 +198,11 @@ class ArchivingOrchestrator:
modules = self.module_factory.available_modules()
for module in modules:
if module.name == 'cli_feeder':
# special case. For the CLI feeder, allow passing URLs directly on the command line without setting --cli_feeder.urls=
parser.add_argument('urls', nargs='*', default=[], help='URL(s) to archive, either a single URL or a list of urls, should not come from config.yaml')
continue
if not module.configs:
# this module has no configs, don't show anything in the help
# (TODO: do we want to show something about this module though, like a description?)
@@ -278,27 +286,6 @@ class ArchivingOrchestrator:
raise SetupError(f"Only one {module_type} is allowed, found {len(step_items)} {module_type}s. Please remove one of the following from your configuration file: {modules_to_load}")
for module in modules_to_load:
if module == 'cli_feeder':
# cli_feeder is a pseudo module, it just takes the command line args for [URLS]
urls = self.config['urls']
if not urls:
raise SetupError("No URLs provided. Please provide at least one URL via the command line, or set up an alternative feeder. Use --help for more information.")
def feed(self) -> Generator[Metadata]:
for url in urls:
logger.debug(f"Processing URL: '{url}'")
yield Metadata().set_url(url)
pseudo_module = type('CLIFeeder', (Feeder,), {
'name': 'cli_feeder',
'display_name': 'CLI Feeder',
'__iter__': feed
})()
pseudo_module.__iter__ = feed
step_items.append(pseudo_module)
continue
if module in invalid_modules:
continue

23
src/auto_archiver/modules/cli_feeder/__manifest__.py Normal file
View File

@@ -0,0 +1,23 @@
{
'name': 'Command Line Feeder',
'type': ['feeder'],
'entry_point': 'cli_feeder::CLIFeeder',
'requires_setup': False,
'description': 'Feeds URLs to orchestrator from the command line',
'configs': {
'urls': {
'default': None,
'help': 'URL(s) to archive, either a single URL or a list of urls, should not come from config.yaml',
},
},
'description': """
The Command Line Feeder is the default enabled feeder for the Auto Archiver. It allows you to pass URLs directly to the orchestrator from the command line
without the need to specify any additional configuration or command line arguments:
`auto-archiver --feeder cli_feeder -- "https://example.com/1/,https://example.com/2/"`
You can pass multiple URLs by separating them with a space. The URLs will be processed in the order they are provided.
`auto-archiver --feeder cli_feeder -- https://example.com/1/ https://example.com/2/`
""",
}

21
src/auto_archiver/modules/cli_feeder/cli_feeder.py Normal file
View File

@@ -0,0 +1,21 @@
from loguru import logger
from auto_archiver.core.feeder import Feeder
from auto_archiver.core.metadata import Metadata
class CLIFeeder(Feeder):
def setup(self) -> None:
self.urls = self.config['urls']
if not self.urls:
raise ValueError("No URLs provided. Please provide at least one URL via the command line, or set up an alternative feeder. Use --help for more information.")
def __iter__(self) -> Metadata:
urls = self.config['urls']
for url in urls:
logger.debug(f"Processing {url}")
m = Metadata().set_url(url)
m.set_context("folder", "cli")
yield m
logger.success(f"Processed {len(urls)} URL(s)")

2
src/auto_archiver/modules/csv_db/__manifest__.py
View File

@@ -6,7 +6,7 @@
},
'entry_point': 'csv_db::CSVDb',
"configs": {
"csv_file": {"default": "db.csv", "help": "CSV file name"}
"csv_file": {"default": "db.csv", "help": "CSV file name to save metadata to"},
},
"description": """
Handles exporting archival results to a CSV file.

4
src/auto_archiver/modules/gsheet_feeder/__manifest__.py
View File

@@ -12,7 +12,9 @@
"default": None,
"help": "the id of the sheet to archive (alternative to 'sheet' config)",
},
"header": {"default": 1, "help": "index of the header row (starts at 1)", "type": "int"},
"header": {"default": 1,
"type": "int",
"help": "index of the header row (starts at 1)", "type": "int"},
"service_account": {
"default": "secrets/service_account.json",
"help": "service account JSON file path. Learn how to create one: https://gspread.readthedocs.io/en/latest/oauth2.html",

4
src/auto_archiver/modules/html_formatter/__manifest__.py
View File

@@ -7,7 +7,9 @@
"bin": [""]
},
"configs": {
"detect_thumbnails": {"default": True, "help": "if true will group by thumbnails generated by thumbnail enricher by id 'thumbnail_00'"}
"detect_thumbnails": {"default": True,
"help": "if true will group by thumbnails generated by thumbnail enricher by id 'thumbnail_00'",
"type": "bool"},
},
"description": """ """,
}

4
src/auto_archiver/modules/local_storage/__manifest__.py
View File

@@ -17,7 +17,9 @@
"choices": ["random", "static"],
},
"save_to": {"default": "./local_archive", "help": "folder where to save archived content"},
"save_absolute": {"default": False, "help": "whether the path to the stored file is absolute or relative in the output result inc. formatters (WARN: leaks the file structure)"},
"save_absolute": {"default": False,
"type": "bool",
"help": "whether the path to the stored file is absolute or relative in the output result inc. formatters (WARN: leaks the file structure)"},
},
"description": """
LocalStorage: A storage module for saving archived content locally on the filesystem.

24
src/auto_archiver/modules/screenshot_enricher/__manifest__.py
View File

@@ -6,13 +6,25 @@
"python": ["loguru", "selenium"],
},
"configs": {
"width": {"default": 1280, "help": "width of the screenshots"},
"height": {"default": 1024, "help": "height of the screenshots"},
"timeout": {"default": 60, "help": "timeout for taking the screenshot"},
"sleep_before_screenshot": {"default": 4, "help": "seconds to wait for the pages to load before taking screenshot"},
"width": {"default": 1280,
"type": "int",
"help": "width of the screenshots"},
"height": {"default": 1024,
"type": "int",
"help": "height of the screenshots"},
"timeout": {"default": 60,
"type": "int",
"help": "timeout for taking the screenshot"},
"sleep_before_screenshot": {"default": 4,
"type": "int",
"help": "seconds to wait for the pages to load before taking screenshot"},
"http_proxy": {"default": "", "help": "http proxy to use for the webdriver, eg http://proxy-user:password@proxy-ip:port"},
"save_to_pdf": {"default": False, "help": "save the page as pdf along with the screenshot. PDF saving options can be adjusted with the 'print_options' parameter"},
"print_options": {"default": {}, "help": "options to pass to the pdf printer"}
"save_to_pdf": {"default": False,
"type": "bool",
"help": "save the page as pdf along with the screenshot. PDF saving options can be adjusted with the 'print_options' parameter"},
"print_options": {"default": {},
"help": "options to pass to the pdf printer, in JSON format. See https://www.selenium.dev/documentation/webdriver/interactions/print_page/ for more information",
"type": "json_loader"},
},
"description": """
Captures screenshots and optionally saves web pages as PDFs using a WebDriver.

4
src/auto_archiver/modules/ssl_enricher/__manifest__.py
View File

@@ -7,7 +7,9 @@
},
'entry_point': 'ssl_enricher::SSLEnricher',
"configs": {
"skip_when_nothing_archived": {"default": True, "help": "if true, will skip enriching when no media is archived"},
"skip_when_nothing_archived": {"default": True,
"type": 'bool',
"help": "if true, will skip enriching when no media is archived"},
},
"description": """
Retrieves SSL certificate information for a domain and stores it as a file.

4
src/auto_archiver/modules/telethon_extractor/__manifest__.py
View File

@@ -14,7 +14,9 @@
"api_hash": {"default": None, "help": "telegram API_HASH value, go to https://my.telegram.org/apps"},
"bot_token": {"default": None, "help": "optional, but allows access to more content such as large videos, talk to @botfather"},
"session_file": {"default": "secrets/anon", "help": "optional, records the telegram login session for future usage, '.session' will be appended to the provided value."},
"join_channels": {"default": True, "help": "disables the initial setup with channel_invites config, useful if you have a lot and get stuck"},
"join_channels": {"default": True,
"type": "bool",
"help": "disables the initial setup with channel_invites config, useful if you have a lot and get stuck"},
"channel_invites": {
"default": {},
"help": "(JSON string) private channel invite links (format: t.me/joinchat/HASH OR t.me/+HASH) and (optional but important to avoid hanging for minutes on startup) channel id (format: CHANNEL_ID taken from a post url like https://t.me/c/CHANNEL_ID/1), the telegram account will join any new channels on setup",

16
src/auto_archiver/modules/wacz_extractor_enricher/__manifest__.py
View File

@@ -17,11 +17,19 @@
"configs": {
"profile": {"default": None, "help": "browsertrix-profile (for profile generation see https://github.com/webrecorder/browsertrix-crawler#creating-and-using-browser-profiles)."},
"docker_commands": {"default": None, "help":"if a custom docker invocation is needed"},
"timeout": {"default": 120, "help": "timeout for WACZ generation in seconds"},
"extract_media": {"default": False, "help": "If enabled all the images/videos/audio present in the WACZ archive will be extracted into separate Media and appear in the html report. The .wacz file will be kept untouched."},
"extract_screenshot": {"default": True, "help": "If enabled the screenshot captured by browsertrix will be extracted into separate Media and appear in the html report. The .wacz file will be kept untouched."},
"timeout": {"default": 120,
"type": "int",
"help": "timeout for WACZ generation in seconds", "type": "int"},
"extract_media": {"default": False,
"type": 'bool',
"help": "If enabled all the images/videos/audio present in the WACZ archive will be extracted into separate Media and appear in the html report. The .wacz file will be kept untouched."
},
"extract_screenshot": {"default": True,
"type": 'bool',
"help": "If enabled the screenshot captured by browsertrix will be extracted into separate Media and appear in the html report. The .wacz file will be kept untouched."
},
"socks_proxy_host": {"default": None, "help": "SOCKS proxy host for browsertrix-crawler, use in combination with socks_proxy_port. eg: user:password@host"},
"socks_proxy_port": {"default": None, "help": "SOCKS proxy port for browsertrix-crawler, use in combination with socks_proxy_host. eg 1234"},
"socks_proxy_port": {"default": None, "type":"int", "help": "SOCKS proxy port for browsertrix-crawler, use in combination with socks_proxy_host. eg 1234"},
"proxy_server": {"default": None, "help": "SOCKS server proxy URL, in development"},
},
"description": """

1
src/auto_archiver/modules/wayback_extractor_enricher/__manifest__.py
View File

@@ -9,6 +9,7 @@
"configs": {
"timeout": {
"default": 15,
"type": "int",
"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": {

8
src/auto_archiver/modules/whisper_enricher/__manifest__.py
View File

@@ -10,8 +10,12 @@
"help": "WhisperApi api endpoint, eg: https://whisperbox-api.com/api/v1, a deployment of https://github.com/bellingcat/whisperbox-transcribe."},
"api_key": {"required": True,
"help": "WhisperApi api key for authentication"},
"include_srt": {"default": False, "help": "Whether to include a subtitle SRT (SubRip Subtitle file) for the video (can be used in video players)."},
"timeout": {"default": 90, "help": "How many seconds to wait at most for a successful job completion."},
"include_srt": {"default": False,
"type": "bool",
"help": "Whether to include a subtitle SRT (SubRip Subtitle file) for the video (can be used in video players)."},
"timeout": {"default": 90,
"type": "int",
"help": "How many seconds to wait at most for a successful job completion."},
"action": {"default": "translate",
"help": "which Whisper operation to execute",
"choices": ["transcribe", "translate", "language_detection"]},