import requests import os from PIL import Image import pytesseract # 下载图片 # session = requests.session() # img_url = 'https://ss1.bdstatic.com/70cFuXSh_Q1YnxGkpoWK1HF6hhy/it/u=1320441599,4127074888&fm=26&gp=0.jpg' # agent = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36' # headers = {'User-Agent': agent} # r = session.get(img_url, headers=headers) # with open('cap.jpg', 'wb') as f: # f.write(r.content) # 打开并显示文件 im = Image.open('img.png') # im.show() # 灰度图片 gray = im.convert('L') gray.save('c_gray2.jpg') im.close() # 二值化 threshold = 130 table = [] for i in range(256): if i < threshold: table.append(0) else: table.append(1) out = gray.point(table, '1') out.save('c_th.jpg') # # th = Image.open("c_th.jpg") # print(pytesseract.image_to_string(th,lang='chi_sim+eng')) code = pytesseract.image_to_string(th) print(code) # 各种语言识别库 https://github.com/tesseract-ocr/tessdata # 放到 /usr/local/Cellar/tesseract/版本/share/tessdata # 先安装依赖库libpng, jpeg, libtiff, leptonica # brew install leptonica # 安装tesseract # brew install tesseract # 与python对接需要安装的包 # pip3 install Pillow # pip3 install pytesseract