tgoop.com/python2day/6649
Create:
Last Update:
Last Update:
Python PDF Handling Tutorial — интересная подборка скриптов для работы с PDF-файлами в Python:
Вы научитесь:
Пример извлечения текста:
from io import StringIO
from pdfminer.pdfinterp import PDFPageInterpreter, PDFResourceManager
from pdfminer.pdfpage import PDFPage
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
# PDFMiner Analyzers
rsrcmgr = PDFResourceManager()
sio = StringIO()
codec = "utf-8"
laparams = LAParams()
device = TextConverter(rsrcmgr, sio, codec=codec, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
# path to our input file
pdf_file = "sample.pdf"
# Extract text
pdfFile = open(pdf_file, "rb")
for page in PDFPage.get_pages(pdfFile):
interpreter.process_page(page)
pdfFile.close()
# Return text from StringIO
text = sio.getvalue()
print(text)
# Freeing Up
device.close()
sio.close()
Пример извлечения изображений:
import fitz
import io
from PIL import Image
# path to our input file
pdf_file = "sample.pdf"
# Input PDF file
pdf_file = fitz.open(pdf_file)
for page_no in range(len(pdf_file)):
curr_page = pdf_file[page_no]
images = curr_page.getImageList()
for image_no, image in enumerate(curr_page.getImageList()):
# get the XREF of the image
xref = image[0]
# extract the image bytes
curr_image = pdf_file.extractImage(xref)
img_bytes = curr_image["image"]
# get the image extension
img_extension = curr_image["ext"]
# load it to PIL
image = Image.open(io.BytesIO(img_bytes))
# save it to local disk
image.save(open(f"page{page_no+1}_img{image_no}.{img_extension}", "wb"))
#python #soft #github
