从图片中提取文字

import pytesseract
from PIL import Image

pytesseract.pytesseract.tesseract_cmd = r"C:\Users\xxx\AppData\Local\Programs\Tesseract-OCR\tesseract.exe"
picture = r"C:\Users\xxx\Downloads\tupianshibie2.png"
image = Image.open(picture)
text = pytesseract.image_to_string(image)
print(text)

一.安装:

1.安装pytesseract

pip install pytesseract

2.下载安装tesseract-qcr

如tesseract-ocr-w64-setup-v5.3.0.20221214.exe

https://digi.bib.uni-mannheim.de/tesseract/tesseract-ocr-w64-setup-v5.3.0.20221214.exe

3.脚本中配置:

pytesseract.pytesseract.tesseract_cmd = r"C:\Users\xxx\AppData\Local\Programs\Tesseract-OCR\tesseract.exe"

二.常见错误:

1.pytesseract.pytesseract.TesseractError: (2, 'Usage: pytesseract [-l lang] input_file')
需要配置pytesseract.pytesseract.tesseract_cmd为tesseract.exe，而不是pytesseract.exe

2.pytesseract.TesseractNotFoundError: tesseract is not installed or it‘s not in your path
安装了pytesseract后却没有安装tesseract-qcr