Statistical information about PDFs

pdfinfo.py

# Get statistical information about PDFs
# Author: 2015 Dmitry Shachnev <[email protected]>

# Required packages (in Debian/Ubuntu):
# - gir1.2-poppler-0.18
# - python3-gi or python-gi

import gi
gi.require_version('Poppler', '0.18')

from gi.repository import GLib, Poppler

CMS_IN_INCH = 2.54
CMS_IN_PT = CMS_IN_INCH / 72
SQUARE_CMS_IN_QUIRE = 3000

CHARS_IN_PAGE_THRESHOLD = 1000
CHARS_IN_QUIRE = 25000

class PdfInfo(object):
    """This class represents the PDF information."""
    pages_count = 0
    characters_count = 0
    quires_count = 0.0
    images_count = 0
    total_area = 0.0
    images_area = 0.0


def _PopplerDocument_get_pages(document):
    n_pages = document.get_n_pages()
    for i in range(n_pages):
        yield document.get_page(i)

Poppler.Document.get_pages = _PopplerDocument_get_pages


def get_area(document):
    """Returns total area of all pages in the documents, in square
    centimeters."""
    total_area_sqcm = 0
    for page in document.get_pages():
        width_pt, height_pt = page.get_size()
        width_cm = round(width_pt * CMS_IN_PT, 4)
        height_cm = round(height_pt * CMS_IN_PT, 4)
        total_area_sqcm += width_cm * height_cm
    return round(total_area_sqcm, 4)


def get_quires_count(document, use_square=False):
    """Returns approximate number of quires needed to print the document."""
    if use_square:
        return get_area(document) / SQUARE_CMS_IN_QUIRE

    images_area = get_images_info(document)[1]
    characters_count = get_characters_count(document)
    quires_from_text = characters_count / CHARS_IN_QUIRE
    quires_from_images = images_area / SQUARE_CMS_IN_QUIRE
    return quires_from_text + quires_from_images


def get_characters_count(document):
    """Returns number of characters in the document."""
    pages = document.get_pages()
    return sum(map(len, map(Poppler.Page.get_text, pages)))


def get_images_info(document):
    """Returns (number of images, total area of all images in square
    centimeters) tuple."""
    images_count = 0
    total_area_sqcm = 0
    for page in document.get_pages():
        for img in page.get_image_mapping():
            images_count += 1
            img_width_cm = (img.area.x2 - img.area.x1) * CMS_IN_PT
            img_height_cm = (img.area.y2 - img.area.y1) * CMS_IN_PT
            total_area_sqcm += img_width_cm * img_height_cm
    return images_count, total_area_sqcm


def get_info(document):
    """Returns an instance of PdfInfo class."""
    info = PdfInfo()
    info.pages_count = document.get_n_pages()
    info.characters_count = get_characters_count(document)
    info.quires_count = get_quires_count(document)
    info.images_count, info.images_area = get_images_info(document)
    info.total_area = get_area(document)
    return info


def document_from_file(filename):
    uri = GLib.filename_to_uri(filename)
    return Poppler.Document.new_from_file(uri)

Пример использования:

>>> import pdfinfo
>>> document = pdfinfo.document_from_file('/home/dmitry/work/referat/work.pdf')
>>> info = pdfinfo.get_info(document)
>>> info.pages_count
13
>>> info.characters_count
24456
>>> info.images_count
1
>>> info.total_area    # в см²
8108.1
>>> info.images_area   # в см²
155.5154197530864
>>> info.quires_count  # печатные листы
1.0300784732510289