`archivebox.index.schema`

WARNING: THIS FILE IS ALL LEGACY CODE TO BE REMOVED.

DO NOT ADD ANY NEW FEATURES TO THIS FILE, NEW CODE GOES HERE: core/models.py

These are the old types we used to use before ArchiveBox v0.4 (before we switched to Django).

Module Contents

Classes

`ArchiveResult`
`Link`

Data

`LinkDict`
`ArchiveOutput`

API

exception archivebox.index.schema.ArchiveError(message, hints=None)[source]: Bases: Exception

archivebox.index.schema.LinkDict[source]: None

archivebox.index.schema.ArchiveOutput[source]: None

class archivebox.index.schema.ArchiveResult[source]

Bases: pydantic.BaseModel

model_config[source]: ‘ConfigDict(…)’

TYPE: str[source]: ‘index.schema.ArchiveResult’

cmd: list[str][source]: None

pwd: str | None[source]: None

cmd_version: str | None[source]: None

output: archivebox.index.schema.ArchiveOutput | None[source]: None

status: str[source]: None

start_ts: datetime.datetime[source]: None

end_ts: datetime.datetime[source]: None

index_texts: list[str] | None[source]: None

_field_names: ClassVar[list[str] | None][source]: None

classmethod validate_status(v: str) → str[source]

classmethod validate_cmd(v: List[str]) → List[str][source]

classmethod validate_pwd(v: Optional[str]) → Optional[str][source]

classmethod validate_cmd_version(v: Optional[str]) → Optional[str][source]

model_dump(**kwargs) → dict[source]: Backwards compatible with _asdict()

classmethod field_names() → List[str][source]: Get all field names of the model

classmethod guess_ts(dict_info: dict) → tuple[datetime.datetime, datetime.datetime][source]: Guess timestamps from dictionary info

classmethod from_json(json_info: dict, guess: bool = False) → archivebox.index.schema.ArchiveResult[source]: Create instance from JSON data

to_dict(*keys: str) → dict[source]: Convert to dictionary, optionally filtering by keys

to_json(indent: int = 4, sort_keys: bool = True) → str[source]: Convert to JSON string

to_csv(cols: Optional[List[str]] = None, separator: str = ',', ljust: int = 0) → str[source]: Convert to CSV string

duration() → int[source]: Calculate duration in seconds between start and end timestamps

class archivebox.index.schema.Link[source]

Bases: pydantic.BaseModel

model_config[source]: ‘ConfigDict(…)’

TYPE: str[source]: ‘index.schema.Link’

timestamp: str[source]: None

url: str[source]: None

title: str | None[source]: None

tags: str | None[source]: None

sources: list[str][source]: ‘Field(…)’

history: dict[str, list[archivebox.index.schema.ArchiveResult]][source]: ‘Field(…)’

downloaded_at: datetime.datetime | None[source]: None

_field_names: ClassVar[list[str] | None][source]: None

__str__() → str[source]

__eq__(other: Any) → bool[source]

__gt__(other: Any) → bool[source]

classmethod validate_timestamp(v: str) → str[source]

classmethod validate_url(v: str) → str[source]

classmethod validate_title(v: Optional[str]) → Optional[str][source]

classmethod validate_sources(v: List[str]) → List[str][source]

_asdict(extended: bool = False) → dict[source]

overwrite(**kwargs) → archivebox.index.schema.Link[source]: Pure functional version of dict.update that returns a new instance

classmethod field_names() → list[str][source]

classmethod from_json(json_info: dict, guess: bool = False) → archivebox.index.schema.Link[source]

to_json(indent: int = 4, sort_keys: bool = True) → str[source]

to_csv(cols: Optional[List[str]] = None, separator: str = ',', ljust: int = 0) → str[source]

property link_dir: str[source]

property archive_path: str[source]

bookmarked_date() → Optional[str][source]

downloaded_datestr() → Optional[str][source]

property archive_dates: list[datetime.datetime][source]

property oldest_archive_date: Optional[datetime.datetime][source]

property newest_archive_date: Optional[datetime.datetime][source]

property num_outputs: int[source]

property num_failures: int[source]

latest_outputs(status: Optional[str] = None) → dict[str, Any][source]: Get the latest output that each archive method produced for link

canonical_outputs() → Dict[str, Optional[str]][source]: Predict the expected output paths that should be present after archiving

property url_hash: str[source]

property scheme: str[source]

property domain: str[source]

property path: str[source]

property basename: str[source]

property extension: str[source]

property base_url: str[source]

property is_static: bool[source]

property is_archived: bool[source]

as_snapshot()[source]: Implement this based on your Django model requirements

static _ts_to_date_str(dt: Optional[datetime.datetime]) → Optional[str][source]

static _parse_date(date_str: Optional[str]) → Optional[datetime.datetime][source]