`archivebox.personas.importers`

Shared persona browser discovery/import helpers.

These helpers are used by both the CLI and the Django admin so Persona import behavior stays consistent regardless of where it is triggered from.

Module Contents

Classes

`PersonaImportSource`
`PersonaImportResult`

Functions

`get_chrome_user_data_dir`	Get the default Chrome user data directory for the current platform.
`get_brave_user_data_dir`	Get the default Brave user data directory for the current platform.
`get_edge_user_data_dir`	Get the default Edge user data directory for the current platform.
`get_browser_binary`
`validate_persona_name`	Validate persona name to prevent path traversal.
`discover_local_browser_profiles`
`discover_persona_template_profiles`
`resolve_browser_import_source`
`resolve_browser_profile_source`
`resolve_custom_import_source`
`pick_default_profile_dir`
`import_persona_from_source`
`copy_browser_user_data_dir`
`export_browser_state`
`_list_profile_names`
`_looks_like_profile_dir`
`_looks_like_cdp_url`
`_parse_netscape_cookies`
`_write_netscape_cookies`
`_merge_netscape_cookies`
`_merge_auth_storage`
`_load_auth_storage`
`_merge_cookie_dicts`
`_apply_imported_user_agent`

Data

`BROWSER_LABELS`
`BROWSER_PROFILE_DIR_NAMES`
`VOLATILE_PROFILE_COPY_PATTERNS`
`PERSONA_PROFILE_DIR_CANDIDATES`
`BROWSER_PROFILE_FINDERS`
`CHROMIUM_BROWSERS`
`NETSCAPE_COOKIE_HEADER`

API

archivebox.personas.importers.BROWSER_LABELS[source]: None

archivebox.personas.importers.BROWSER_PROFILE_DIR_NAMES[source]: (‘Default’, ‘Profile ‘, ‘Guest Profile’)

archivebox.personas.importers.VOLATILE_PROFILE_COPY_PATTERNS[source]: (‘Cache’, ‘Code Cache’, ‘GPUCache’, ‘ShaderCache’, ‘Service Worker’, ‘GCM Store’, ‘*.log’, ‘Crashpad…

archivebox.personas.importers.PERSONA_PROFILE_DIR_CANDIDATES[source]: (‘chrome_profile’, ‘chrome_user_data’)

class archivebox.personas.importers.PersonaImportSource[source]

kind: str[source]: None

browser: str[source]: ‘custom’

source_name: str | None[source]: None

user_data_dir: pathlib.Path | None[source]: None

profile_dir: str | None[source]: None

browser_binary: str | None[source]: None

cdp_url: str | None[source]: None

property browser_label: str[source]

property profile_path: pathlib.Path | None[source]

property display_label: str[source]

property choice_value: str[source]

as_choice_label() → django.utils.safestring.SafeString[source]

classmethod from_choice_value(value: str) → archivebox.personas.importers.PersonaImportSource[source]

class archivebox.personas.importers.PersonaImportResult[source]

source: archivebox.personas.importers.PersonaImportSource[source]: None

profile_copied: bool[source]: False

cookies_imported: bool[source]: False

storage_captured: bool[source]: False

user_agent_imported: bool[source]: False

warnings: list[str][source]: ‘field(…)’

property did_work: bool[source]

archivebox.personas.importers.get_chrome_user_data_dir() → pathlib.Path | None[source]: Get the default Chrome user data directory for the current platform.

archivebox.personas.importers.get_brave_user_data_dir() → pathlib.Path | None[source]: Get the default Brave user data directory for the current platform.

archivebox.personas.importers.get_edge_user_data_dir() → pathlib.Path | None[source]: Get the default Edge user data directory for the current platform.

archivebox.personas.importers.get_browser_binary(browser: str) → str | None[source]

archivebox.personas.importers.BROWSER_PROFILE_FINDERS[source]: None

archivebox.personas.importers.CHROMIUM_BROWSERS[source]: ‘tuple(…)’

archivebox.personas.importers.NETSCAPE_COOKIE_HEADER[source]: [’# Netscape HTTP Cookie File’, ‘# https://curl.se/docs/http-cookies.html’, ‘# This file was generat…

archivebox.personas.importers.validate_persona_name(name: str) → tuple[bool, str][source]: Validate persona name to prevent path traversal.

archivebox.personas.importers.discover_local_browser_profiles() → list[archivebox.personas.importers.PersonaImportSource][source]

archivebox.personas.importers.discover_persona_template_profiles(personas_dir: pathlib.Path | None = None) → list[archivebox.personas.importers.PersonaImportSource][source]

archivebox.personas.importers.resolve_browser_import_source(browser: str, profile_dir: str | None = None) → archivebox.personas.importers.PersonaImportSource[source]

archivebox.personas.importers.resolve_browser_profile_source(browser: str, user_data_dir: pathlib.Path, profile_dir: str, source_name: str | None = None, browser_binary: str | None = None) → archivebox.personas.importers.PersonaImportSource[source]

archivebox.personas.importers.resolve_custom_import_source(raw_value: str, profile_dir: str | None = None) → archivebox.personas.importers.PersonaImportSource[source]

archivebox.personas.importers.pick_default_profile_dir(user_data_dir: pathlib.Path) → str | None[source]

archivebox.personas.importers.import_persona_from_source(persona: archivebox.personas.models.Persona, source: archivebox.personas.importers.PersonaImportSource, *, copy_profile: bool = True, import_cookies: bool = True, capture_storage: bool = False) → archivebox.personas.importers.PersonaImportResult[source]

archivebox.personas.importers.copy_browser_user_data_dir(source_dir: pathlib.Path, destination_dir: pathlib.Path) → None[source]

archivebox.personas.importers.export_browser_state(*, user_data_dir: pathlib.Path | None = None, cdp_url: str | None = None, profile_dir: str | None = None, chrome_binary: str | None = None, cookies_output_file: pathlib.Path | None = None, auth_output_file: pathlib.Path | None = None) → tuple[bool, dict | None, str][source]

archivebox.personas.importers._list_profile_names(user_data_dir: pathlib.Path) → list[str][source]

archivebox.personas.importers._looks_like_profile_dir(path: pathlib.Path) → bool[source]

archivebox.personas.importers._looks_like_cdp_url(value: str) → bool[source]

archivebox.personas.importers._parse_netscape_cookies(path: pathlib.Path) → dict[tuple[str, str, str], tuple[str, str, str, str, str, str, str]][source]

archivebox.personas.importers._write_netscape_cookies(path: pathlib.Path, cookies: dict[tuple[str, str, str], tuple[str, str, str, str, str, str, str]]) → None[source]

archivebox.personas.importers._merge_netscape_cookies(existing_file: pathlib.Path, new_file: pathlib.Path) → None[source]

archivebox.personas.importers._merge_auth_storage(existing_file: pathlib.Path, new_file: pathlib.Path) → None[source]

archivebox.personas.importers._load_auth_storage(path: pathlib.Path) → dict[source]

archivebox.personas.importers._merge_cookie_dicts(existing: list[dict], new: list[dict]) → list[dict][source]

archivebox.personas.importers._apply_imported_user_agent(persona: archivebox.personas.models.Persona, auth_payload: dict | None) → bool[source]

archivebox.personas.importers