Using wand, pillow and tesseract

注意：pdf必须是白色底，否则识别不出来。

其实就是根据pdf转为jpg再解析，真的是，就是从前面两篇提取结合，easy job!

import io #多用了io库
from PIL import Image
import pytesseract
from wand.image import Image as wi

pdf = wi(filename='jun.pdf',resolution=300)
pdfImg = pdf.convert('jpeg')

imgBlobs = []

for img in pdfImg.sequence:
    page = wi(image=img)
    imgBlobs.append(page.make_blob('jpeg'))

extracted_text = []

for imgBlobs in imgBlobs:
    im = Image.open(io.BytesIO(imgBlobs))
    text = pytesseract.image_to_string(im,lang='chi_sim')
    extracted_text.append(text)

print(extracted_text[0])