最近,我接了一个项目。使用Python tesseract将扫描的PDF转换为可搜索的PDFword。
经过几次尝试,我可以将扫描的PDF转换为PNG图像文件,之后,我很奇怪,有谁可以帮助我将PNG文件转换为WordPDF搜索。我的代码附后
请参考附件中的图片。
Import os
Import sys
from PIL import image
Import pytesseract
from pytesseract import image_to_string
Libpath =r'_______' #site-package
Pop_path=r'_______' #poppler dlls
Sys.path.insert(0,LibPath)
from pdf2image import convert_from_path
Pdfpath=r'_______' # PDF file directory
imgpath=r'_______' #image output path
images= convert_from_path(pdf_path = pdfpath,
dpi=500, poppler_path= pop_path)
for idx, of in enumerate (images):
pg.save(imgPath+'PDF_Page_'+'.png',"PNG")
print('{} page converted'.format(str(idx)))
try:
from PIL import image
except ImportError:
import image
import pytesseract
def ocr-core(images):
Text =
pytesseract.image_to_string(image.open(images))
return text
print(ocr_core("image path/imagename))
就是这样,我已经写好了......然后我得到了多张".PNG "图片......现在我只能将一张PNG图片转换成文字。
如何将所有的图片转换并保存在CSVword中?
我得到了答案,我的问题
from PIL import Image
from pdf2image import convert_from_path
import pytesseract
Pdf_file_path = '_______' #your file path
Images = convert_from_path(Pdf_file_path, dpi=500)
Counter=1
for page in Images:
idx= "image_"+str(Counter)+".jpg" ##or ".png"
page.save(idx, 'JPEG')
Counter += 1
file=Counter-1
output= '_____' #where you want to save and file name
f=open(output, "w")
for i in range(1,file+1):
idx= "image_"+str(Counter)+".jpg" ##or ".png"
text=str(pytesseract.image_to_string(Image.open(idx)))
f.write(text)
f.close()