我尝试从电脑创建的PDF中提取文本,它可以正常工作,但我无法从扫描的PDF中提取文本,例如这个链接中带有图像和多页的文件:https://docdro.id/gUuO21l,其中包含如下页面:
以下是我使用的代码:
# libraries
## split
from PyPDF2 import PdfFileWriter, PdfFileReader
## read
import sys
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfpage import PDFPage
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
from pdfminer.layout import LAParams
import io
# remove files
import os
# split in case there is several pages
def pdfspliter(filename):
inputpdf = PdfFileReader(open(filename, "rb"))
for i in range(inputpdf.numPages):
output = PdfFileWriter()
output.addPage(inputpdf.getPage(i))
with open("document-page%s.pdf" % i, "wb") as outputStream:
output.write(outputStream)
pdfparser("document-page%s.pdf" % i)
os.remove("document-page%s.pdf" % i)
# read a given page
def pdfparser(data):
fp = open(data, 'rb')
rsrcmgr = PDFResourceManager()
retstr = io.StringIO()
codec = 'utf-8'
laparams = LAParams()
device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
# Create a PDF interpreter object.
interpreter = PDFPageInterpreter(rsrcmgr, device)
# Process each page contained in the document.
for page in PDFPage.get_pages(fp):
interpreter.process_page(page)
data = retstr.getvalue()
print(data)
if __name__ == '__main__':
filename = sys.argv[1]
pdfspliter(filename)
您能帮助提取这种文件中的文本吗?
使用Tesseract OCR进行更新
我尝试使用Python中的Tesseract OCR,它可以提取PDF文本的一些页面,但是需要很长时间,并且似乎在某个时候停止了:
# import the necessary packages
from PIL import Image
import pytesseract
import argparse
import cv2
import os
## split
from PyPDF2 import PdfFileWriter, PdfFileReader
# remove
import sys
#
from pdf2image import convert_from_path
# import all files with a name
import glob
# functions
def pdfspliterimager(filename):
inputpdf = PdfFileReader(open(filename, "rb"))
for i in range(inputpdf.numPages):
output = PdfFileWriter()
output.addPage(inputpdf.getPage(i))
with open("document-page%s.pdf" % i, "wb") as outputStream:
output.write(outputStream)
pages = convert_from_path("document-page%s.pdf" % i, 500)
for page in pages:
page.save('out%s.jpg'%i, 'JPEG')
os.remove("document-page%s.pdf" % i)
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True,
help="path to input image to be OCR'd")
ap.add_argument("-p", "--preprocess", type=str, default="thresh",
help="type of preprocessing to be done")
args = vars(ap.parse_args())
# we test if it is a pdf
image_path = args["image"]
# if it is a pdf we convert it to an image
if image_path.endswith('.pdf'):
pdfspliterimager(image_path)
# for all files with out in their name
file_names = glob.glob("out*")
for file_name in file_names:
# load the image and convert it to grayscale
image = cv2.imread(file_name)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# check to see if we should apply thresholding to preprocess the
# image
if args["preprocess"] == "thresh":
gray = cv2.threshold(gray, 0, 255,
cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
# make a check to see if median blurring should be done to remove
# noise
elif args["preprocess"] == "blur":
gray = cv2.medianBlur(gray, 3)
# write the grayscale image to disk as a temporary file so we can
# apply OCR to it
filename = "{}.png".format(os.getpid())
cv2.imwrite(filename, gray)
# load the image as a PIL/Pillow image, apply OCR, and then delete
# the temporary file
text = pytesseract.image_to_string(Image.open(filename))
os.remove(filename)
print(text)
# show the output images
cv2.imshow("Image", image)
cv2.imshow("Output", gray)
cv2.waitKey(0)