使用 Python tesseract 从 PNG 图像中提取文本
Extract text from PNG images using Python tesseract
最近接了一个项目。使用 Python tesseract 将扫描的 PDF 转换为可搜索的 PDF/word。
经过几次尝试,我能够将扫描的 PDF 转换为 PNG 图像文件,之后,我很惊讶有人可以帮助我将 PNG 文件转换为 Word/PDF 可搜索的。my piece of code attached
请找到附件图片以供参考。
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,我写了.....然后我得到了多个“.PNG”图像...现在我只能将一个 PNG 图像转换为文本。
如何将所有图片转换并保存在CSV/word中?
from PIL import image
from pdf2image import convert_from_path
import pytesseract
import OS
import sys
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 = 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()
最近接了一个项目。使用 Python tesseract 将扫描的 PDF 转换为可搜索的 PDF/word。
经过几次尝试,我能够将扫描的 PDF 转换为 PNG 图像文件,之后,我很惊讶有人可以帮助我将 PNG 文件转换为 Word/PDF 可搜索的。my piece of code attached
请找到附件图片以供参考。
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,我写了.....然后我得到了多个“.PNG”图像...现在我只能将一个 PNG 图像转换为文本。
如何将所有图片转换并保存在CSV/word中?
from PIL import image
from pdf2image import convert_from_path
import pytesseract
import OS
import sys
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 = 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()