Index

_

__add__() (pdfscraper.layout.utils.Bbox method) (pdfscraper.page.Page method) __bool__() (pdfscraper.layout.text.TextLine method) __contains__() (pdfscraper.layout.image.Image method) (pdfscraper.layout.text.TextLine method) __eq__() (pdfscraper.layout.text.Word method) (pdfscraper.layout.utils.Bbox method) (pdfscraper.layout.utils.Color method) __getitem__() (pdfscraper.layout.text.TextLine method) __hash__() (pdfscraper.layout.image.Image method) (pdfscraper.layout.text.Word method) __repr__() (pdfscraper.layout.text.Block method) (pdfscraper.layout.text.Line method) (pdfscraper.layout.text.SortedTextlines method) (pdfscraper.layout.text.Span method) (pdfscraper.layout.text.TextLine method) (pdfscraper.layout.text.Word method) (pdfscraper.page.Page method)

__slots__ (pdfscraper.layout.text.Block attribute) (pdfscraper.layout.text.Line attribute) (pdfscraper.layout.text.Span attribute) __str__() (pdfscraper.layout.text.TextLine method) (pdfscraper.layout.text.Word method) (pdfscraper.layout.utils.Bbox method) _save_pdfminer() (pdfscraper.layout.image.Image method) _save_pymupdf() (pdfscraper.layout.image.Image method) _split_sequence_by_condition() (pdfscraper.page.Page static method)

A

anno_type (pdfscraper.layout.annotations.PyMuPDFAnnotation attribute) Annotation (class in pdfscraper.layout.annotations), [1] arbitrary_types_allowed (pdfscraper.layout.image.Image.Config attribute), [1]

attr_as() (in module pdfscraper.layout.image) author (pdfscraper.layout.annotations.Annotation attribute), [1] (pdfscraper.layout.annotations.PDFMinerAnnotation attribute)

B

b (pdfscraper.layout.utils.Color attribute) Backend (class in pdfscraper.layout.utils) Bbox (class in pdfscraper.layout.utils) bbox (pdfscraper.layout.annotations.Annotation attribute), [1] (pdfscraper.layout.drawing.Drawing attribute) (pdfscraper.layout.image.Image attribute), [1] (pdfscraper.layout.image.MuPDFImage attribute) (pdfscraper.layout.utils.Rectangular attribute)

Block (class in pdfscraper.layout.text) border (pdfscraper.layout.annotations.PyMuPDFAnnotation attribute) bottom_is_zero (pdfscraper.layout.utils.PageOrientation property) (pdfscraper.layout.utils.VerticalOrientation attribute) bpc (pdfscraper.layout.image.Image attribute), [1] (pdfscraper.layout.image.MuPDFImage attribute)

C

cmyk_to_rgb() (in module pdfscraper.layout.drawing) Color (class in pdfscraper.layout.utils) color (pdfscraper.layout.annotations.PDFMinerAnnotation attribute) colors (pdfscraper.layout.annotations.PyMuPDFAnnotation attribute) colorspace_n (pdfscraper.layout.image.Image attribute), [1] colorspace_name (pdfscraper.layout.image.Image attribute), [1] (pdfscraper.layout.image.MuPDFImage attribute) condition (pdfscraper.page.PageSection attribute)

content (pdfscraper.layout.annotations.Annotation attribute), [1] (pdfscraper.layout.annotations.PDFMinerAnnotation attribute) create() (pdfscraper.layout.utils.Orientation class method) (pdfscraper.layout.utils.PageOrientation class method) create_bbox_backend() (in module pdfscraper.layout.utils) create_sections() (pdfscraper.document.Document method), [1] creation_date (pdfscraper.layout.annotations.Annotation attribute), [1] (pdfscraper.layout.annotations.PDFMinerAnnotation attribute) CurveShape (class in pdfscraper.layout.drawing)

D

decode_filter (pdfscraper.layout.image.MuPDFImage attribute) DEFAULT_BACKEND_PAGE_ORIENTATIONS (in module pdfscraper.layout.utils) doc (pdfscraper.document.Document attribute), [1]

Document (class in pdfscraper.document), [1] Drawing (class in pdfscraper.layout.drawing) drawings (pdfscraper.page.PageSection attribute)

F

fill (pdfscraper.layout.drawing.Drawing attribute) fill_color (pdfscraper.layout.drawing.Drawing attribute) flags (pdfscraper.layout.annotations.PDFMinerAnnotation attribute) (pdfscraper.layout.annotations.PyMuPDFAnnotation attribute) flatten() (in module pdfscraper.layout.utils) from_annot() (pdfscraper.layout.annotations.PDFMinerAnnotation class method) (pdfscraper.layout.annotations.PyMuPDFAnnotation class method) from_coords() (pdfscraper.layout.utils.Bbox class method) from_pdfminer() (pdfscraper.document.Document class method), [1] (pdfscraper.layout.image.Image class method), [1] (pdfscraper.layout.text.Span class method) (pdfscraper.page.Page class method)

from_pdfminer_annot() (pdfscraper.layout.annotations.Annotation class method), [1] from_pymupdf() (pdfscraper.document.Document class method), [1] (pdfscraper.layout.image.Image class method), [1] (pdfscraper.layout.text.Span class method) (pdfscraper.page.Page class method) from_pymupdf_annot() (pdfscraper.layout.annotations.Annotation class method), [1]

G

g (pdfscraper.layout.utils.Color attribute) get_bbox() (in module pdfscraper.layout.utils) get_bottommost() (in module pdfscraper.layout.utils) get_center() (in module pdfscraper.layout.utils) get_center_group() (in module pdfscraper.layout.utils) get_image() (in module pdfscraper.layout.image) get_images_from_pymupdf_page() (in module pdfscraper.layout.image)

get_leftmost() (in module pdfscraper.layout.utils) get_pts() (in module pdfscraper.layout.drawing) get_rightmost() (in module pdfscraper.layout.utils) get_span_bbox() (in module pdfscraper.layout.text) get_topmost() (in module pdfscraper.layout.utils) group_objs() (in module pdfscraper.layout.utils) groupby_consec() (in module pdfscraper.layout.utils)

H

has_popup (pdfscraper.layout.annotations.PyMuPDFAnnotation attribute) height (pdfscraper.layout.image.Image property) (pdfscraper.layout.utils.Bbox property) (pdfscraper.layout.utils.Rectangular property)

horizontal_orientation (pdfscraper.layout.utils.Orientation attribute) HorizontalOrientation (class in pdfscraper.layout.utils)

I

Image (class in pdfscraper.layout.image), [1] Image.Config (class in pdfscraper.layout.image), [1] images (pdfscraper.page.PageSection attribute) ImageSource (in module pdfscraper.layout.image)

info (pdfscraper.layout.annotations.PyMuPDFAnnotation attribute) is_open (pdfscraper.layout.annotations.PyMuPDFAnnotation attribute) isclose() (pdfscraper.layout.utils.Bbox method) isinside() (pdfscraper.layout.utils.Bbox method)

L

left_is_zero (pdfscraper.layout.utils.HorizontalOrientation attribute) (pdfscraper.layout.utils.PageOrientation property) Line (class in pdfscraper.layout.text)

line2str() (in module pdfscraper.layout.text) line_ends (pdfscraper.layout.annotations.PyMuPDFAnnotation attribute) LineShape (class in pdfscraper.layout.drawing)

M

mask_xref (pdfscraper.layout.image.MuPDFImage attribute) mod_date (pdfscraper.layout.annotations.Annotation attribute), [1] (pdfscraper.layout.annotations.PDFMinerAnnotation attribute) module pdfscraper pdfscraper.document pdfscraper.layout pdfscraper.layout.annotations pdfscraper.layout.drawing pdfscraper.layout.image pdfscraper.layout.text pdfscraper.layout.utils pdfscraper.page

move() (pdfscraper.layout.image.Image method) (pdfscraper.layout.utils.Bbox method) (pdfscraper.layout.utils.Rectangular method) MuPDFImage (class in pdfscraper.layout.image)

N

name (pdfscraper.layout.annotations.PDFMinerAnnotation attribute) (pdfscraper.layout.image.Image attribute), [1] (pdfscraper.layout.image.MuPDFImage attribute) (pdfscraper.page.PageSection attribute)

next_annotation (pdfscraper.layout.annotations.PyMuPDFAnnotation attribute) normalize_value() (pdfscraper.layout.annotations.PDFMinerAnnotation class method)

O

opacity (pdfscraper.layout.annotations.PyMuPDFAnnotation attribute) Orientation (class in pdfscraper.layout.utils)

orientation (pdfscraper.document.Document attribute), [1] (pdfscraper.layout.utils.PageOrientation attribute)

P

Page (class in pdfscraper.page) page_height (pdfscraper.layout.utils.PageOrientation attribute) page_width (pdfscraper.layout.utils.PageOrientation attribute) PageOrientation (class in pdfscraper.layout.utils) pages (pdfscraper.document.Document attribute), [1] PageSection (class in pdfscraper.page) parent (pdfscraper.page.PageSection attribute) parent_object (pdfscraper.layout.image.Image attribute), [1] PDFMINER (pdfscraper.layout.utils.Backend attribute) PDFMinerAnnotation (class in pdfscraper.layout.annotations) pdfscraper module pdfscraper.document module pdfscraper.layout module pdfscraper.layout.annotations module pdfscraper.layout.drawing module

pdfscraper.layout.image module pdfscraper.layout.text module pdfscraper.layout.utils module pdfscraper.page module Point (class in pdfscraper.layout.drawing) points (pdfscraper.layout.drawing.CurveShape attribute) (pdfscraper.layout.drawing.LineShape attribute) (pdfscraper.layout.drawing.RectShape attribute) popup_rect (pdfscraper.layout.annotations.PyMuPDFAnnotation attribute) popup_xref (pdfscraper.layout.annotations.PyMuPDFAnnotation attribute) process_pdfminer_drawing() (in module pdfscraper.layout.drawing) process_pymupdf_drawing() (in module pdfscraper.layout.drawing) PYMUPDF (pdfscraper.layout.utils.Backend attribute) PyMuPDFAnnotation (class in pdfscraper.layout.annotations)

R

r (pdfscraper.layout.utils.Color attribute) raw_object (pdfscraper.layout.image.Image attribute), [1] rect (pdfscraper.layout.annotations.PDFMinerAnnotation attribute) (pdfscraper.layout.annotations.PyMuPDFAnnotation attribute)

Rectangular (class in pdfscraper.layout.utils) RectShape (class in pdfscraper.layout.drawing) resort() (pdfscraper.layout.text.SortedTextlines method)

S

save() (pdfscraper.layout.image.Image method), [1] select() (pdfscraper.layout.text.SortedTextlines method) (pdfscraper.page.Page method) Shape (in module pdfscraper.layout.drawing) sorted (pdfscraper.page.Page property) sorted_lines (pdfscraper.page.Page property) SortedTextlines (class in pdfscraper.layout.text) source (pdfscraper.layout.image.Image attribute), [1]

source_height (pdfscraper.layout.image.Image attribute), [1] (pdfscraper.layout.image.MuPDFImage attribute) source_width (pdfscraper.layout.image.Image attribute), [1] (pdfscraper.layout.image.MuPDFImage attribute) Span (class in pdfscraper.layout.text) split() (pdfscraper.page.Page method) stroke (pdfscraper.layout.drawing.Drawing attribute) stroke_color (pdfscraper.layout.drawing.Drawing attribute) subject (pdfscraper.layout.annotations.PDFMinerAnnotation attribute)

T

take_screenshot() (pdfscraper.page.Page method) text (pdfscraper.layout.text.Line property) (pdfscraper.layout.text.Span property) (pdfscraper.layout.text.TextLine property)

TextLine (class in pdfscraper.layout.text)

V

vertical_orientation (pdfscraper.layout.utils.Orientation attribute)

VerticalOrientation (class in pdfscraper.layout.utils) vertices (pdfscraper.layout.annotations.PyMuPDFAnnotation attribute)

W

width (pdfscraper.layout.image.Image property) (pdfscraper.layout.utils.Bbox property) (pdfscraper.layout.utils.Rectangular property)

Word (class in pdfscraper.layout.text) words (pdfscraper.page.PageSection attribute)

X

x (pdfscraper.layout.drawing.Point attribute) x0 (pdfscraper.layout.image.Image property) (pdfscraper.layout.utils.Bbox attribute) (pdfscraper.layout.utils.Rectangular property) x1 (pdfscraper.layout.image.Image property) (pdfscraper.layout.utils.Bbox attribute) (pdfscraper.layout.utils.Rectangular property)

xref (pdfscraper.layout.annotations.PyMuPDFAnnotation attribute) (pdfscraper.layout.image.Image attribute), [1] (pdfscraper.layout.image.MuPDFImage attribute)

Y

y (pdfscraper.layout.drawing.Point attribute) y0 (pdfscraper.layout.image.Image property) (pdfscraper.layout.utils.Bbox attribute) (pdfscraper.layout.utils.Rectangular property)

y1 (pdfscraper.layout.image.Image property) (pdfscraper.layout.utils.Bbox attribute) (pdfscraper.layout.utils.Rectangular property)