PDF 范型对象

Implementation of generic PDF objects (dictionary, number, string, ...).

class pypdf.generic.BooleanObject(value: Any)

基类：PdfObject

clone(pdf_dest: PdfWriterProtocol, force_duplicate: bool = False, ignore_fields: Sequence[str | int] | None = ()) → BooleanObject

Clone object into pdf_dest.

hash_bin() → int

Used to detect modified object.

返回:

Hash considering type and value.

write_to_stream(stream: IO[Any], encryption_key: None | str | bytes = None) → None

static read_from_stream(stream: IO[Any]) → BooleanObject

class pypdf.generic.FloatObject(value: Any = '0.0', context: Any | None = None)

基类：float, PdfObject

clone(pdf_dest: Any, force_duplicate: bool = False, ignore_fields: Sequence[str | int] | None = ()) → FloatObject

Clone object into pdf_dest.

hash_bin() → int

Used to detect modified object.

返回:

Hash considering type and value.

myrepr() → str

as_numeric() → float

write_to_stream(stream: IO[Any], encryption_key: None | str | bytes = None) → None

class pypdf.generic.NumberObject(value: Any)

基类：int, PdfObject

NumberPattern = re.compile(b'[^+-.0-9]')

clone(pdf_dest: Any, force_duplicate: bool = False, ignore_fields: Sequence[str | int] | None = ()) → NumberObject

Clone object into pdf_dest.

hash_bin() → int

Used to detect modified object.

返回:

Hash considering type and value.

as_numeric() → int

write_to_stream(stream: IO[Any], encryption_key: None | str | bytes = None) → None

static read_from_stream(stream: IO[Any]) → NumberObject | FloatObject

class pypdf.generic.NameObject

基类：str, PdfObject

delimiter_pattern = re.compile(b'\\s+|[\\(\\)<>\\[\\]{}/%]')

surfix = b'/'

renumber_table: ClassVar[Dict[str, bytes]] = {'\x00': b'#00', '\x01': b'#01', '\x02': b'#02', '\x03': b'#03', '\x04': b'#04', '\x05': b'#05', '\x06': b'#06', '\x07': b'#07', '\x08': b'#08', '\t': b'#09', '\n': b'#0A', '\x0b': b'#0B', '\x0c': b'#0C', '\r': b'#0D', '\x0e': b'#0E', '\x0f': b'#0F', '\x10': b'#10', '\x11': b'#11', '\x12': b'#12', '\x13': b'#13', '\x14': b'#14', '\x15': b'#15', '\x16': b'#16', '\x17': b'#17', '\x18': b'#18', '\x19': b'#19', '\x1a': b'#1A', '\x1b': b'#1B', '\x1c': b'#1C', '\x1d': b'#1D', '\x1e': b'#1E', '\x1f': b'#1F', ' ': b'#20', '#': b'#23', '%': b'#25', '(': b'#28', ')': b'#29', '/': b'#2F'}

clone(pdf_dest: Any, force_duplicate: bool = False, ignore_fields: Sequence[str | int] | None = ()) → NameObject

Clone object into pdf_dest.

hash_bin() → int

Used to detect modified object.

返回:

Hash considering type and value.

write_to_stream(stream: IO[Any], encryption_key: None | str | bytes = None) → None

renumber() → bytes

static unnumber(sin: bytes) → bytes

CHARSETS = ('utf-8', 'gbk', 'latin1')

static read_from_stream(stream: IO[Any], pdf: Any) → NameObject

class pypdf.generic.IndirectObject(idnum: int, generation: int, pdf: Any)

基类：PdfObject

hash_bin() → int

Used to detect modified object.

返回:

Hash considering type and value.

replicate(pdf_dest: PdfWriterProtocol) → PdfObject

clone(pdf_dest: PdfWriterProtocol, force_duplicate: bool = False, ignore_fields: Sequence[str | int] | None = ()) → IndirectObject

Clone object into pdf_dest.

property indirect_reference: IndirectObject

get_object() → PdfObject | None

write_to_stream(stream: IO[Any], encryption_key: None | str | bytes = None) → None

static read_from_stream(stream: IO[Any], pdf: Any) → IndirectObject

class pypdf.generic.NullObject(*args, **kwargs)

基类：PdfObject

clone(pdf_dest: PdfWriterProtocol, force_duplicate: bool = False, ignore_fields: Sequence[str | int] | None = ()) → NullObject

Clone object into pdf_dest.

hash_bin() → int

Used to detect modified object.

返回:

Hash considering type and value.

write_to_stream(stream: IO[Any], encryption_key: None | str | bytes = None) → None

static read_from_stream(stream: IO[Any]) → NullObject

class pypdf.generic.PdfObject(*args, **kwargs)

基类：PdfObjectProtocol

hash_func(*, usedforsecurity=True)

Returns a sha1 hash object; optionally initialized with a string

indirect_reference: IndirectObject | None

hash_bin() → int

Used to detect modified object.

返回:

Hash considering type and value.

hash_value_data() → bytes

hash_value() → bytes

replicate(pdf_dest: PdfWriterProtocol) → PdfObject

Clone object into pdf_dest (PdfWriterProtocol which is an interface for PdfWriter) without ensuring links. This is used in clone_document_from_root with incremental = True.

参数:

pdf_dest -- Target to clone to.

返回:

The cloned PdfObject

clone(pdf_dest: PdfWriterProtocol, force_duplicate: bool = False, ignore_fields: Sequence[str | int] | None = ()) → PdfObject

Clone object into pdf_dest (PdfWriterProtocol which is an interface for PdfWriter).

By default, this method will call _reference_clone (see _reference).

参数:

• pdf_dest -- Target to clone to.

• force_duplicate -- By default, if the object has already been cloned and referenced, the copy will be returned; when True, a new copy will be created. (Default value = False)

• ignore_fields -- List/tuple of field names (for dictionaries) that will be ignored during cloning (applies to children duplication as well). If fields are to be considered for a limited number of levels, you have to add it as integer, for example [1,"/B","/TOTO"] means that "/B" will be ignored at the first level only but "/TOTO" on all levels.

返回:

The cloned PdfObject

get_object() → PdfObject | None

Resolve indirect references.

write_to_stream(stream: IO[Any], encryption_key: None | str | bytes = None) → None

class pypdf.generic.TextStringObject(value: Any)

基类：str, PdfObject

A string object that has been decoded into a real unicode string.

If read from a PDF document, this string appeared to match the PDFDocEncoding, or contained a UTF-16BE BOM mark to cause UTF-16 decoding to occur.

autodetect_pdfdocencoding: bool

autodetect_utf16: bool

utf16_bom: bytes

clone(pdf_dest: Any, force_duplicate: bool = False, ignore_fields: Sequence[str | int] | None = ()) → TextStringObject

Clone object into pdf_dest.

hash_bin() → int

Used to detect modified object.

返回:

Hash considering type and value.

property original_bytes: bytes

It is occasionally possible that a text string object gets created where a byte string object was expected due to the autodetection mechanism -- if that occurs, this "original_bytes" property can be used to back-calculate what the original encoded bytes were.

get_original_bytes() → bytes

get_encoded_bytes() → bytes

write_to_stream(stream: IO[Any], encryption_key: None | str | bytes = None) → None

class pypdf.generic.ByteStringObject(*args, **kwargs)

基类：bytes, PdfObject

Represents a string object where the text encoding could not be determined.

This occurs quite often, as the PDF spec doesn't provide an alternate way to represent strings -- for example, the encryption data stored in files (like /O) is clearly not text, but is still stored in a "String" object.

clone(pdf_dest: Any, force_duplicate: bool = False, ignore_fields: Sequence[str | int] | None = ()) → ByteStringObject

Clone object into pdf_dest.

hash_bin() → int

Used to detect modified object.

返回:

Hash considering type and value.

property original_bytes: bytes

For compatibility with TextStringObject.original_bytes.

write_to_stream(stream: IO[Any], encryption_key: None | str | bytes = None) → None

class pypdf.generic.AnnotationBuilder

基类：object

The AnnotationBuilder is deprecated.

Instead, use the annotation classes in pypdf.annotations.

See adding PDF annotations for its usage combined with PdfWriter.

static text(rect: RectangleObject | Tuple[float, float, float, float], text: str, open: bool = False, flags: int = 0) → None

static free_text(text: str, rect: RectangleObject | Tuple[float, float, float, float], font: str = 'Helvetica', bold: bool = False, italic: bool = False, font_size: str = '14pt', font_color: str = '000000', border_color: str | None = '000000', background_color: str | None = 'ffffff') → None

static popup(*, rect: RectangleObject | Tuple[float, float, float, float], flags: int = 0, parent: DictionaryObject | None = None, open: bool = False) → None

static line(p1: Tuple[float, float], p2: Tuple[float, float], rect: RectangleObject | Tuple[float, float, float, float], text: str = '', title_bar: str | None = None) → None

static polyline(vertices: List[Tuple[float, float]]) → None

static rectangle(rect: RectangleObject | Tuple[float, float, float, float], interiour_color: str | None = None) → None

static highlight(*, rect: RectangleObject | Tuple[float, float, float, float], quad_points: ArrayObject, highlight_color: str = 'ff0000', printing: bool = False) → None

static ellipse(rect: RectangleObject | Tuple[float, float, float, float], interiour_color: str | None = None) → None

static polygon(vertices: List[Tuple[float, float]]) → None

DEFAULT_FIT = <pypdf.generic._fit.Fit object>

static link(rect: ~pypdf.generic._rectangle.RectangleObject | ~typing.Tuple[float, float, float, float], border: ~pypdf.generic._data_structures.ArrayObject | None = None, url: str | None = None, target_page_index: int | None = None, fit: ~pypdf.generic._fit.Fit = <pypdf.generic._fit.Fit object>) → None

class pypdf.generic.ArrayObject(iterable=(), /)

基类：List[Any], PdfObject

replicate(pdf_dest: PdfWriterProtocol) → ArrayObject

clone(pdf_dest: PdfWriterProtocol, force_duplicate: bool = False, ignore_fields: Sequence[str | int] | None = ()) → ArrayObject

Clone object into pdf_dest.

hash_bin() → int

Used to detect modified object.

返回:

Hash considering type and value.

items() → Iterable[Any]

Emulate DictionaryObject.items for a list (index, object).

write_to_stream(stream: IO[Any], encryption_key: None | str | bytes = None) → None

static read_from_stream(stream: IO[Any], pdf: PdfReaderProtocol | None, forced_encoding: None | str | List[str] | Dict[int, str] = None) → ArrayObject

class pypdf.generic.DictionaryObject

基类：Dict[Any, Any], PdfObject

replicate(pdf_dest: PdfWriterProtocol) → DictionaryObject

clone(pdf_dest: PdfWriterProtocol, force_duplicate: bool = False, ignore_fields: Sequence[str | int] | None = ()) → DictionaryObject

Clone object into pdf_dest.

hash_bin() → int

Used to detect modified object.

返回:

Hash considering type and value.

raw_get(key: Any) → Any

get_inherited(key: str, default: Any = None) → Any

Returns the value of a key or from the parent if not found. If not found returns default.

参数:

• key -- string identifying the field to return

• default -- default value to return

返回:

Current key or inherited one, otherwise default value.

setdefault(key: Any, value: Any | None = None) → Any

property xmp_metadata: XmpInformationProtocol | None

Retrieve XMP (Extensible Metadata Platform) data relevant to the this object, if available.

See Table 347 — Additional entries in a metadata stream dictionary.

返回:

Returns a XmpInformation instance that can be used to access XMP metadata from the document. Can also return None if no metadata was found on the document root.

write_to_stream(stream: IO[Any], encryption_key: None | str | bytes = None) → None

static read_from_stream(stream: IO[Any], pdf: PdfReaderProtocol | None, forced_encoding: None | str | List[str] | Dict[int, str] = None) → DictionaryObject

class pypdf.generic.TreeObject(dct: DictionaryObject | None = None)

基类：DictionaryObject

has_children() → bool

children() → Iterable[Any]

add_child(child: Any, pdf: PdfWriterProtocol) → None

inc_parent_counter_default(parent: None | IndirectObject | TreeObject, n: int) → None

inc_parent_counter_outline(parent: None | IndirectObject | TreeObject, n: int) → None

insert_child(child: Any, before: Any, pdf: PdfWriterProtocol, inc_parent_counter: Callable[[...], Any] | None = None) → IndirectObject

remove_child(child: Any) → None

remove_from_tree() → None

Remove the object from the tree it is in.

empty_tree() → None

class pypdf.generic.StreamObject

基类：DictionaryObject

replicate(pdf_dest: PdfWriterProtocol) → StreamObject

hash_bin() → int

Used to detect modified object.

返回:

Hash considering type and value.

get_data() → bytes

set_data(data: bytes) → None

hash_value_data() → bytes

write_to_stream(stream: IO[Any], encryption_key: None | str | bytes = None) → None

static initializeFromDictionary(data: Dict[str, Any]) → None

static initialize_from_dictionary(data: Dict[str, Any]) → EncodedStreamObject | DecodedStreamObject

flate_encode(level: int = -1) → EncodedStreamObject

decode_as_image() → Any

Try to decode the stream object as an image

返回:

a PIL image if proper decoding has been found

抛出:

Exception -- (any)during decoding to to invalid object or errors during decoding will be reported It is recommended to catch exceptions to prevent stops in your program.

class pypdf.generic.DecodedStreamObject

基类：StreamObject

class pypdf.generic.EncodedStreamObject

基类：StreamObject

get_data() → bytes

set_data(data: bytes) → None

class pypdf.generic.ContentStream(stream: Any, pdf: Any, forced_encoding: None | str | List[str] | Dict[int, str] = None)

基类：DecodedStreamObject

In order to be fast, this data structure can contain either:

• raw data in ._data

• parsed stream operations in ._operations.

At any time, ContentStream object can either have both of those fields defined, or one field defined and the other set to None.

These fields are "rebuilt" lazily, when accessed:

• when .get_data() is called, if ._data is None, it is rebuilt from ._operations.

• when .operations is called, if ._operations is None, it is rebuilt from ._data.

Conversely, these fields can be invalidated:

• when .set_data() is called, ._operations is set to None.

• when .operations is set, ._data is set to None.

replicate(pdf_dest: PdfWriterProtocol) → ContentStream

clone(pdf_dest: Any, force_duplicate: bool = False, ignore_fields: Sequence[str | int] | None = ()) → ContentStream

Clone object into pdf_dest.

参数:

• pdf_dest

• force_duplicate

• ignore_fields

返回:

The cloned ContentStream

get_data() → bytes

set_data(data: bytes) → None

property operations: List[Tuple[Any, bytes]]

isolate_graphics_state() → None

write_to_stream(stream: IO[Any], encryption_key: None | str | bytes = None) → None

class pypdf.generic.ViewerPreferences(value: Any = None)

基类：DictionaryObject

property PRINT_SCALING: NameObject

class pypdf.generic.OutlineItem(title: str, page: NumberObject | IndirectObject | NullObject | DictionaryObject, fit: Fit)

基类：Destination

write_to_stream(stream: IO[Any], encryption_key: None | str | bytes = None) → None

class pypdf.generic.OutlineFontFlag(value, names=<not given>, *values, module=None, qualname=None, type=None, start=1, boundary=None)

基类：IntFlag

A class used as an enumerable flag for formatting an outline font.

italic = 1

bold = 2

pypdf.generic.read_object(stream: IO[Any], pdf: PdfReaderProtocol | None, forced_encoding: None | str | List[str] | Dict[int, str] = None) → PdfObject | int | str | ContentStream

pypdf.generic.create_string_object(string: str | bytes, forced_encoding: None | str | List[str] | Dict[int, str] = None) → TextStringObject | ByteStringObject

Create a ByteStringObject or a TextStringObject from a string to represent the string.

参数:

• string -- The data being used

• forced_encoding -- Typically None, or an encoding string

返回:

A ByteStringObject

抛出:

TypeError -- If string is not of type str or bytes.

pypdf.generic.encode_pdfdocencoding(unicode_string: str) → bytes

pypdf.generic.decode_pdfdocencoding(byte_array: bytes) → str

pypdf.generic.hex_to_rgb(value: str) → Tuple[float, float, float]

pypdf.generic.is_null_or_none(x: Any) → TypeGuard[None | NullObject | IndirectObject]

返回:

True if x is None or NullObject.

pypdf.generic.read_hex_string_from_stream(stream: IO[Any], forced_encoding: None | str | List[str] | Dict[int, str] = None) → TextStringObject | ByteStringObject

pypdf.generic.read_string_from_stream(stream: IO[Any], forced_encoding: None | str | List[str] | Dict[int, str] = None) → TextStringObject | ByteStringObject

class pypdf._protocols.PdfObjectProtocol(*args, **kwargs)

基类：Protocol

indirect_reference: Any

clone(pdf_dest: Any, force_duplicate: bool = False, ignore_fields: Tuple[str, ...] | List[str] | None = ()) → Any

get_object() → PdfObjectProtocol | None

hash_value() → bytes

write_to_stream(stream: IO[Any], encryption_key: None | str | bytes = None) → None

class pypdf._protocols.XmpInformationProtocol(*args, **kwargs)

基类：PdfObjectProtocol

class pypdf._protocols.PdfCommonDocProtocol(*args, **kwargs)

基类：Protocol

property pdf_header: str

property pages: List[Any]

property root_object: PdfObjectProtocol

get_object(indirect_reference: Any) → PdfObjectProtocol | None

property strict: bool

class pypdf._protocols.PdfReaderProtocol(*args, **kwargs)

基类：PdfCommonDocProtocol, Protocol

abstract property xref: Dict[int, Dict[int, Any]]

abstract property trailer: Dict[str, Any]

class pypdf._protocols.PdfWriterProtocol(*args, **kwargs)

基类：PdfCommonDocProtocol, Protocol

incremental: bool

abstract write(stream: Path | str | IO[Any]) → Tuple[bool, IO[Any]]