重新生成依赖列表

main.py

@@ -7,10 +7,12 @@ import pymysql
 import cnocr
 import json
 import numpy as np
+import warnings
 from PIL import Image, ImageFile
 from dotenv import dotenv_values
 from elasticsearch import Elasticsearch
 
+warnings.filterwarnings("ignore")
 ImageFile.LOAD_TRUNCATED_IMAGES = True
 config = dotenv_values(".env")
 oss2.defaults.connection_pool_size = 100
@@ -45,15 +47,17 @@ def save_text(conn, id:int, text:str):
 
 def process_images(conn, ocr, es):
     with conn.cursor(pymysql.cursors.SSCursor) as cursor:
-        cursor.execute("SELECT id, content FROM web_images WHERE text!='' LIMIT 10")
+        cursor.execute("SELECT id, content FROM web_images WHERE text='' LIMIT 10000")
         for id, content in cursor.fetchall():
             image = download_image(content)
             if image is None:
                 continue
             item = [x for x in ocr.ocr(image) if x['text'] and not x['text'].isdigit() and len(x['text']) > 1]
-            save_text(conn, id, json.dumps(item, ensure_ascii=False, cls=MyEncoder))
             text = ' '.join([x['text'] for x in item])
+            print(id, text)
+            save_text(conn, id, json.dumps(item, ensure_ascii=False, cls=MyEncoder))
             es.index(index='web_images', id=id, body={'content': text})
+        conn.commit()
 
 def main():
     es = Elasticsearch(config['ELASTICSEARCH_HOST'], basic_auth=(config['ELASTICSEARCH_USERNAME'], config['ELASTICSEARCH_PASSWORD']), verify_certs=False)

pp.py

@@ -0,0 +1,24 @@
+#!/usr/bin/env python3
+from paddleocr import PaddleOCR, draw_ocr
+
+# Paddleocr目前支持的多语言语种可以通过修改lang参数进行切换
+# 例如`ch`, `en`, `fr`, `german`, `korean`, `japan`
+ocr = PaddleOCR(use_angle_cls=True, lang="ch")  # need to run only once to download and load model into memory
+img_path = './imgs/14.jpg'
+result = ocr.ocr(img_path, cls=True)
+for idx in range(len(result)):
+    res = result[idx]
+    for line in res:
+        print(line)
+
+# 显示结果
+#from PIL import Image
+#result = result[0]
+#image = Image.open(img_path).convert('RGB')
+#boxes = [line[0] for line in result]
+#txts = [line[1][0] for line in result]
+#scores = [line[1][1] for line in result]
+#im_show = draw_ocr(image, boxes, txts, scores, font_path='./fonts/simfang.ttf')
+#im_show = Image.fromarray(im_show)
+#im_show.save('result.jpg')
+

requirements.txt

@@ -1,82 +1,11 @@
-aiohttp==3.8.6
-aiosignal==1.3.1
-appdirs==1.4.4
-async-timeout==4.0.3
-attrs==23.1.0
-certifi==2023.7.22
-charset-normalizer==3.3.2
-click==8.1.7
 cnocr==2.2.4.2
-cnstd==1.2.3.5
+elasticsearch==8.11.0
-coloredlogs==15.0.1
+numpy==1.26.2
-contourpy==1.2.0
+oss2==2.18.3
-cycler==0.12.1
+paddleocr==2.7.0.3
-docker-pycreds==0.4.0
+paddleocr.egg==info
-filelock==3.13.1
+Pillow==10.1.0
-flatbuffers==23.5.26
-fonttools==4.44.0
-frozenlist==1.4.0
-fsspec==2023.10.0
-gitdb==4.0.11
-GitPython==3.1.40
-huggingface-hub==0.19.0
-humanfriendly==10.0
-idna==3.4
-Jinja2==3.1.2
-kiwisolver==1.4.5
-lightning-utilities==0.9.0
-MarkupSafe==2.1.3
-matplotlib==3.8.1
-mpmath==1.3.0
-multidict==6.0.4
-networkx==3.2.1
-numpy==1.26.1
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==8.9.2.26
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-nccl-cu12==2.18.1
-nvidia-nvjitlink-cu12==12.3.52
-nvidia-nvtx-cu12==12.1.105
-onnx==1.15.0
-onnxruntime==1.16.2
-opencv-python==4.8.1.78
-packaging==23.2
-pandas==2.1.3
 Pillow==10.1.0
-Polygon3==3.0.9.1
-protobuf==4.25.0
-psutil==5.9.6
-pyclipper==1.3.0.post5
 PyMySQL==1.1.0
-pyparsing==3.1.1
+python-dotenv==1.0.0
-python-dateutil==2.8.2
+Requests==2.31.0
-pytorch-lightning==2.1.1
-pytz==2023.3.post1
-PyYAML==6.0.1
-requests==2.31.0
-scipy==1.11.3
-seaborn==0.13.0
-sentry-sdk==1.34.0
-setproctitle==1.3.3
-shapely==2.0.2
-six==1.16.0
-smmap==5.0.1
-sympy==1.12
-torch==2.1.0+cpu
-torchaudio==2.1.0
-torchmetrics==1.2.0
-torchvision==0.16.0+cpu
-tqdm==4.66.1
-triton==2.1.0
-typing_extensions==4.8.0
-tzdata==2023.3
-Unidecode==1.3.7
-urllib3==2.0.7
-wandb==0.16.0
-yarl==1.9.2