天天看點

爬蟲驗證碼識别_工具篇:安裝pytesseract&Tesseract-OCR

步驟

1.pytcharm中

ctrl+al+s

調出setting選項,添加pytesseract包;

2.下載下傳安裝Tesseract-OCR,并将安裝目錄添加至系統環境變量;

  • 連結:https://pan.baidu.com/s/1bYp856AqfDEuqv4hCm0_Ng
  • 提取碼:lvyu

安裝詳細步驟參考:Tesseract-OCR下載下傳和安裝

測試代碼

from PIL import Image
import pytesseract

print(pytesseract.image_to_string(Image.open('code_img.jpg')))
# LTMA
           
爬蟲驗證碼識别_工具篇:安裝pytesseract&Tesseract-OCR

備注:

1,直接在pycharm中安裝Tesseractocr會報錯;

2.如果隻安裝pytesseract,去運作上述測試代碼,則會報:pytesseract.pytesseract.TesseractNotFoundError: tesseract is not installed or it’s not in your path;

3.結果的識别準确率偏低;