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

Fully-working settings page editor

Browse Source
This commit is contained in:
Patrick Robertson
2025-02-26 17:02:49 +00:00
parent bb961b131c
commit 70d89c71ce
21 changed files with 6354 additions and 180 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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/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/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.

14
src/auto_archiver/modules/wacz_extractor_enricher/__manifest__.py
View File

@@ -17,11 +17,17 @@
"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, "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": """