From 2bd552c801b81a0859efcc489d218e9199974f6a Mon Sep 17 00:00:00 2001
From: WilliamQf <40328063+WilliamQf-AI@users.noreply.github.com>
Date: Mon, 21 Aug 2023 10:25:47 +0800
Subject: [PATCH] =?UTF-8?q?=E5=AE=9E=E7=8E=B0=E5=8A=9F=E8=83=BD=EF=BC=9A?=
 =?UTF-8?q?=E5=BD=93--savefile=E4=B8=BAtrue=E6=97=B6=EF=BC=8C=E5=9C=A8--ou?=
 =?UTF-8?q?tput=E4=B8=8B=E4=BB=A5=E5=BD=93=E5=89=8D=E5=9B=BE=E7=89=87?=
 =?UTF-8?q?=E5=90=8D=E7=A7=B0=E5=90=8E=E6=8E=A5=E2=80=9C.txt=E2=80=9D?=
 =?UTF-8?q?=E4=B8=BA=E6=96=87=E4=BB=B6=E5=90=8D=E4=BF=9D=E5=AD=98ocr?=
 =?UTF-8?q?=E6=8E=A8=E7=90=86=E7=BB=93=E6=9E=9C=EF=BC=8C=E8=A7=A3=E5=86=B3?=
 =?UTF-8?q?=E4=BA=86issues=EF=BC=9A=20(#10628)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* 实现功能：当--savefile为true时，在--output下以当前图片名称后接“.txt”为文件名保存ocr推理结果，解决了issues：
https://github.com/PaddlePaddle/PaddleOCR/issues/10533

* 删除了乱码字符

* 1.删除了乱码字符

* 1.删除了乱码字符
---
 paddleocr.py | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/paddleocr.py b/paddleocr.py
index 549419a1..c76f09a4 100644
--- a/paddleocr.py
+++ b/paddleocr.py
@@ -408,6 +408,7 @@ def parse_args(mMain=True):
     parser.add_argument("--det", type=str2bool, default=True)
     parser.add_argument("--rec", type=str2bool, default=True)
     parser.add_argument("--type", type=str, default='ocr')
+    parser.add_argument("--savefile", type=str2bool, default=False)
     parser.add_argument(
         "--ocr_version",
         type=str,
@@ -619,7 +620,7 @@ class PaddleOCR(predict_system.TextSystem):
     def ocr(self, img, det=True, rec=True, cls=True):
         """
         ocr with paddleocr
-        args：
+        args:
             img: img for ocr, support ndarray, img_path and list or ndarray
             det: use text detection or not. If false, only rec will be exec. Default is True
             rec: use text recognition or not. If false, only det will be exec. Default is True
@@ -768,10 +769,25 @@ def main():
                                 rec=args.rec,
                                 cls=args.use_angle_cls)
             if result is not None:
+                lines = []
                 for idx in range(len(result)):
                     res = result[idx]
                     for line in res:
                         logger.info(line)
+                        val = '['
+                        for box in line[0]:
+                            val += str(box[0]) + ',' + str(box[1]) + ','
+
+                        val = val[:-1]
+                        val += '],' + line[1][0] + ',' + str(line[1][1]) + '\n'
+                        lines.append(val)
+                if args.savefile:
+                    if os.path.exists(args.output) is False:
+                        os.mkdir(args.output)
+                    outfile = args.output + '/' + img_name + '.txt'
+                    with open(outfile,'w',encoding='utf-8') as f:
+                        f.writelines(lines)
+                     
         elif args.type == 'structure':
             img, flag_gif, flag_pdf = check_and_read(img_path)
             if not flag_gif and not flag_pdf:
-- 
GitLab