不正经

这个屌丝很懒，什么也没留下！

热门标签

为后端做准备

作者：不正经 | 2024-04-05 07:45:34

踩

为后端做准备

这里写目录标题

flask 文件上传与接收

文件流接收
1、前端传来的对象是二进制文件流，有两种方法保存本地。

（1）通过open()方法将文件流写入保存

（2）直接用调用 file.save() 方法保存传来的文件流：

flask应答（接收请求（文件、数据）

from flask import Flask,request
app = Flask(__name__)


@app.route('/upload',methods = ['POST'])
def file_receive():
    # 获取文件对象
    file = request.files['file']
    # 获取文件名
    filename = file.filename
    # file.save 也可保存传来的文件
    # file.save(f'./{filename}')
    with open(f'./{filename}','wb') as f:
        f.write(file.stream.read())

    return {'success':1}

if __name__ == '__main__':
    app.run()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19

flask请求（上传文件）

测试该段代码的文件上传可以用requests实现，用open()创建一个二进制对象，传给后端：

import requests

def uploads():
    url = 'http://127.0.0.1:5000/upload'
    files = {'file':open('C:\\Users\\xxx\\Desktop\\push\\test.mp4','rb')}
    r = requests.post(url,files = files)
    print(r.text)

if __name__=="__main__":
    uploads()
1
2
3
4
5
6
7
8
9
10

传递参数和文件

试过了，行不通request.data为空，真是的

from flask import Flask,request
app = Flask(__name__)

@app.route('/upload',methods = ['POST'])
def file_receive():
    # 获取文件对象
    file = request.files['file']
    # 获取参数body
    body = request.data
    filename = file.filename
    # file.save 也可保存传来的文件
    # file.save(f'./{filename}')
    with open(f'./{filename}','wb') as f:
        f.write(file.stream.read())

    return {'success':1}

if __name__ == '__main__':
    app.run()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19

requests 测试代码：

import requests

def uploads():
    url = 'http://127.0.0.1:5000/upload'
    body = {'info':'test'}
    files = {'file':open('C:\\Users\\xxx\\Desktop\\push\\test.mp4','rb')}
    r = requests.post(url,json = body,files = files)
    print(r.text)

if __name__=="__main__":
    uploads()
1
2
3
4
5
6
7
8
9
10
11

flask 文件上传与接收
假设我们目前有一些文件，和参数需要通过POST发送到请求服务端，我们可以通过content type为multipart/form-data 来同时传入这两个参数。

准备参数
我们先设置需要传入的参数，这里 file_path 需要改成自己的文件


import requests

# 设置要上传的文件
file_path = "path/to/your/file"	# 这里替换成文件目录
files = {
    "file1": ("filename", open(file_path, "rb"))
}

# 设置要发送的JSON数据
params = {
    'key1': 'value1',
    'key2': 'value2'
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15

编写service
在服务端要如何获取文件和JSON参数？我们首先要知道，通过如上方式传入数据，content-type是multipart/form-data 。所以我们在服务端应该使用 request.form.to_dict() 来获取表格里的参数内容。

我们新建一个命名为 service.py 的文件，写入一下脚本来启动命名为"upload-endpoint"的服务。我们这里服务没有做数据处理，只是把它们打印出来。


from flask import Flask, request, jsonify

app = Flask(__name__)

@app.route('/upload-endpoint', methods=['POST'])
def upload_endpoint():
    try:
        # 获取JSON数据
        params = request.form.to_dict()
        print(params)
        # 获取上传的文件
        file1 = request.files['file1']
        print(file1)
        
        # 处理JSON数据和文件
        # 在这里，你可以根据需要对JSON数据和文件进行操作
        # 例如，你可以保存文件到服务器，访问JSON数据等

        # 返回一个响应
        response_data = {
            'message': 'JSON参数和文件已成功接收和处理'
        }
        return jsonify(response_data), 200
    except Exception as e:
        error_message = str(e)
        return jsonify({'error': error_message}), 400

if __name__ == '__main__':
    app.run(debug=True, port=5000)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30

请求


# 发送POST请求，同时传送JSON数据和文件
response = requests.post('http://127.0.0.1:5000/upload-endpoint', data=params, files=files)
1
2
3

如何用python request同时上传文件和JSON参数

argparse 不从命令行调用参数

1、设置default值

parser.add_argument('-f', '--config_file', dest='config_file', type=argparse.FileType(mode='r')）

1
2

改进如下

yaml_path='test.yaml'
parser.add_argument('-f', '--config_file', dest='config_file',type=argparse.FileType(mode='r'),default=yaml_path)

1
2
3

2、“从命令行传入的参数”.split()

现在很多python代码使用parser解析输入参数, 我们如果想要在IDE里(如pycharm)分析源代码，不可能每一次都使用命令行进行，因此这里面使用了一个技巧，即源程序在定义完入口命令行参数后，使用了args = parser.parse_args() 来接送实际使用命令行时的输入，我们这里把这句代码替换为：

args= parser.parse_args(“从命令行传入的参数”.split())

 args = parser.parse_args("--input ../example_graphs/karate.adjlist --output ./output".split())
1

str=“–input …/example_graphs/karate.adjlist”
args = parser.parse_args(str.split())
就报错AttributeError: 'str' object has no attribute 'spilt'
可以使用第三种方式
args = parser.parse_args(【'--input',str】)
Pycham不用命令行传入参数

3、[‘–input’,‘内容’]

Python 中使用 argparse 解析命令行参数 | Linux 中国
有一些第三方库用于命令行解析，但标准库 argparse 与之相比也毫不逊色。

无需添加很多依赖，你就可以编写带有实用参数解析功能的漂亮命令行工具。

Python 中的参数解析
使用 argparse 解析命令行参数时，第一步是配置一个 ArgumentParser 对象。这通常在全局模块内完成，因为单单_配置_一个解析器没有副作用。

import argparse

PARSER = argparse.ArgumentParser()
1
2
3

ArgumentParser 中最重要的方法是 .add_argument()，它有几个变体。默认情况下，它会添加一个参数，并期望一个值。

PARSER.add_argument("--value")
1

查看实际效果，调用 .parse_args()：

PARSER.parse_args(["--value", "some-value"])
Namespace(value='some-value')
1
2

也可以使用 = 语法：

PARSER.parse_args(["--value=some-value"])
Namespace(value='some-value')
1
2

为了缩短在命令行输入的命令，你还可以为选项指定一个短“别名”：

PARSER.add_argument("--thing", "-t")
1

可以传入短选项：

PARSER.parse_args(“-t some-thing”.split())
Namespace(value=None, thing=‘some-thing’)
或者长选项：

PARSER.parse_args(“–thing some-thing”.split())
Namespace(value=None, thing=‘some-thing’)
类型
有很多类型的参数可供你使用。除了默认类型，最流行的两个是布尔类型和计数器。布尔类型有一个默认为 True 的变体和一个默认为 False 的变体。

PARSER.add_argument(“–active”, action=“store_true”)
PARSER.add_argument(“–no-dry-run”, action=“store_false”, dest=“dry_run”)
PARSER.add_argument(“–verbose”, “-v”, action=“count”)
除非显式传入 --active，否则 active 就是 False。dry-run 默认是 True，除非传入 --no-dry-run。无值的短选项可以并列。

传递所有参数会导致非默认状态：

PARSER.parse_args(“–active --no-dry-run -vvvv”.split())
Namespace(value=None, thing=None, active=True, dry_run=False, verbose=4)
默认值则比较单一：

PARSER.parse_args(“”.split())
Namespace(value=None, thing=None, active=False, dry_run=True, verbose=None)
子命令
经典的 Unix 命令秉承了“一次只做一件事，并做到极致”，但现代的趋势把“几个密切相关的操作”放在一起。

git、podman 和 kubectl 充分说明了这种范式的流行。argparse 库也可以做到：

MULTI_PARSER = argparse.ArgumentParser()
subparsers = MULTI_PARSER.add_subparsers()
get = subparsers.add_parser(“get”)
get.add_argument(“–name”)
get.set_defaults(command=“get”)
search = subparsers.add_parser(“search”)
search.add_argument(“–query”)
search.set_defaults(command=“search”)
MULTI_PARSER.parse_args(“get --name awesome-name”.split())
Namespace(name=‘awesome-name’, command=‘get’)
MULTI_PARSER.parse_args(“search --query name~awesome”.split())
Namespace(query=‘name~awesome’, command=‘search’)`
程序架构
使用 argparse 的一种方法是使用下面的结构：

## my_package/__main__.py
import argparse
import sys

from my_package import toplevel

parsed_arguments = toplevel.PARSER.parse_args(sys.argv[1:])
toplevel.main(parsed_arguments)

## my_package/toplevel.py

PARSER = argparse.ArgumentParser()
## .add_argument, etc.

def main(parsed_args):

    ...

    # do stuff with parsed_args
    
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20

在这种情况下，使用 python -m my_package 运行。或者，你可以在包安装时使用 console_scprits 入口点。

总结
argparse 模块是一个强大的命令行参数解析器，还有很多功能没能在这里介绍。它能实现你想象的一切。

python解压压缩包

在这里插入图片描述

python解压压缩包
如果是从前端上传的zip，只想将解压后的文件夹存在服务器中，那么先解压再保存（保存之后才存在文件路径），可以将前端输入的zip文件

现在我们直接使用上一步产生的 spam.zip 文件内容，首先假定输入为字节数据，然后窥探其中每一个条目的文件信息与内容

import zipfile
import io
import os
 
 
def read_zipfiles(path, folder=''):
    for member in path.iterdir():
        filename = os.path.join(folder, member.name)
        if member.is_file():
            print(filename, ':', member.read_text()) # member.read_bytes()
        else:
            read_zipfiles(member, filename)
 
 
with open('spam.zip', 'rb') as myzip:
    zip_data = myzip.read()
 
 
with zipfile.ZipFile(io.BytesIO(zip_data)) as zip_file:
    read_zipfiles(zipfile.Path(zip_file))
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22

Python zipfile 只借助内存进行压缩与解压缩

        # 处理压缩文件
        if file and allowed_file(file.filename):
            filename = secure_filename(file.filename)
            file.save(os.path.join(app.config['UPLOAD_FOLDER'], filename))  # 压缩文件保存在项目路径下
            local_dir = os.path.join(base_dir, '11')  # 新创建一个路径，用来放压缩后的文件
            hh = os.path.join(base_dir, filename)  # 这个是找到压缩文件路径-------C:/Code/haha.zip
            print(hh)
            print(local_dir)
            shutil.unpack_archive(filename=hh, extract_dir=local_dir)# 把文件保存在刚刚设定好的路径下

            os.remove(hh) # 最后把压缩文件删除
1
2
3
4
5
6
7
8
9
10
11

flask上传文件及上传zip文件实例

python将文件如jpg保存到指定文件夹报错

dst = open(dst, "wb")

```python

from PIL import Image

import os

# 打开图片

image = Image.open('example.jpg')

# 保存图片到指定文件夹

if not os.path.exists('new_folder'):

os.makedirs('new_folder')

image.save('new_folder/example_new.jpg')

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18

上述代码中，使用os模块创建一个新的文件夹new_folder，并将图片保存到这个文件夹中。

我的代码报错

python - IO错误: Errno 13 Permission denied for specific files
些许类似，没明白

一团糟

    if suffix.lower() in ['jpg', 'png', 'jpeg']:
        # uploaded_file.save(image_folder + uploaded_file.filename.split('.')[-2])
        # image_folder = image_folder + uploaded_file.filename.split('.')[-2]

        save_path=image_folder + uploaded_file.filename.split('.')[-2]
        # # uploaded_file.save(save_path + uploaded_file.filename)
        # image_folder = image_folder + uploaded_file.filename.split('.')[-2]

        # uploaded_file.save('./images/hhh/'+ uploaded_file.filename)
        # image_folder = image_folder + 'hhh/'

        # save_path=image_folder + uploaded_file.filename.split('.')[-2]+'/'+ uploaded_file.filename.split('.')[-2]+'.'
        # print(save_path)
        # uploaded_file.save(save_path + suffix.lower())
        # image_folder = image_folder + uploaded_file.filename.split('.')[-2]
        print(uploaded_file.filename)
        print(type(uploaded_file.filename))
        save_path=os.path.join(save_path, uploaded_file.filename)
        print(save_path)
        with open(uploaded_file.filename, 'wb') as f:
            print('222')
            f.write(uploaded_file)
        print('111')
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23

# from paddleocr import PaddleOCR
import os
import sys
import importlib

__dir__ = os.path.dirname(__file__)

sys.path.append(os.path.join(__dir__, ''))

import cv2
import logging
import numpy as np
from pathlib import Path
# import base64
# from io import BytesIO
from PIL import Image


def _import_file(module_name, file_path, make_importable=False):
    spec = importlib.util.spec_from_file_location(module_name, file_path)
    module = importlib.util.module_from_spec(spec)
    spec.loader.exec_module(module)
    if make_importable:
        sys.modules[module_name] = module
    return module


tools = _import_file(
    'tools', os.path.join(__dir__, 'tools/__init__.py'), make_importable=True)
ppocr = importlib.import_module('ppocr', 'paddleocr')
ppstructure = importlib.import_module('ppstructure', 'paddleocr')
from ppocr.utils.logging import get_logger
from tools.infer import predict_system
from ppocr.utils.utility import check_and_read, get_image_file_list, alpha_to_color, binarize_img
from ppocr.utils.network import maybe_download, download_with_progressbar, is_link, confirm_model_dir_url
from tools.infer.utility import draw_ocr, str2bool, check_gpu
from ppstructure.utility import init_args, draw_structure_result
from ppstructure.predict_system import StructureSystem, save_structure_res, to_excel

logger = get_logger()
__all__ = [
    'PaddleOCR', 'PPStructure', 'draw_ocr', 'draw_structure_result',
    'save_structure_res', 'download_with_progressbar', 'to_excel'
]

SUPPORT_DET_MODEL = ['DB']
VERSION = '2.7.0.3'
SUPPORT_REC_MODEL = ['CRNN', 'SVTR_LCNet']
BASE_DIR = os.path.expanduser("~/.paddleocr/")

DEFAULT_OCR_MODEL_VERSION = 'PP-OCRv4'
SUPPORT_OCR_MODEL_VERSION = ['PP-OCR', 'PP-OCRv2', 'PP-OCRv3', 'PP-OCRv4']
DEFAULT_STRUCTURE_MODEL_VERSION = 'PP-StructureV2'
SUPPORT_STRUCTURE_MODEL_VERSION = ['PP-Structure', 'PP-StructureV2']
MODEL_URLS = {
    'OCR': {
        'PP-OCRv4': {
            'det': {
                'ch': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv4/chinese/ch_PP-OCRv4_det_infer.tar',
                },
                'en': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar',
                },
                'ml': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/Multilingual_PP-OCRv3_det_infer.tar'
                }
            },
            'rec': {
                'ch': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv4/chinese/ch_PP-OCRv4_rec_infer.tar',
                    'dict_path': './ppocr/utils/ppocr_keys_v1.txt'
                },
                'en': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv4/english/en_PP-OCRv4_rec_infer.tar',
                    'dict_path': './ppocr/utils/en_dict.txt'
                },
                'korean': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/korean_PP-OCRv4_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/korean_dict.txt'
                },
                'japan': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/japan_PP-OCRv4_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/japan_dict.txt'
                },
                'chinese_cht': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/chinese_cht_PP-OCRv3_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/chinese_cht_dict.txt'
                },
                'ta': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/ta_PP-OCRv4_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/ta_dict.txt'
                },
                'te': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/te_PP-OCRv4_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/te_dict.txt'
                },
                'ka': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/ka_PP-OCRv4_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/ka_dict.txt'
                },
                'latin': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/latin_PP-OCRv3_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/latin_dict.txt'
                },
                'arabic': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/arabic_PP-OCRv4_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/arabic_dict.txt'
                },
                'cyrillic': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/cyrillic_PP-OCRv3_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/cyrillic_dict.txt'
                },
                'devanagari': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/devanagari_PP-OCRv4_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/devanagari_dict.txt'
                },
            },
            'cls': {
                'ch': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar',
                }
            },
        },
        'PP-OCRv3': {
            'det': {
                'ch': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar',
                },
                'en': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar',
                },
                'ml': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/Multilingual_PP-OCRv3_det_infer.tar'
                }
            },
            'rec': {
                'ch': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar',
                    'dict_path': './ppocr/utils/ppocr_keys_v1.txt'
                },
                'en': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar',
                    'dict_path': './ppocr/utils/en_dict.txt'
                },
                'korean': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/korean_PP-OCRv3_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/korean_dict.txt'
                },
                'japan': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/japan_PP-OCRv3_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/japan_dict.txt'
                },
                'chinese_cht': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/chinese_cht_PP-OCRv3_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/chinese_cht_dict.txt'
                },
                'ta': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/ta_PP-OCRv3_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/ta_dict.txt'
                },
                'te': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/te_PP-OCRv3_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/te_dict.txt'
                },
                'ka': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/ka_PP-OCRv3_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/ka_dict.txt'
                },
                'latin': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/latin_PP-OCRv3_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/latin_dict.txt'
                },
                'arabic': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/arabic_PP-OCRv3_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/arabic_dict.txt'
                },
                'cyrillic': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/cyrillic_PP-OCRv3_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/cyrillic_dict.txt'
                },
                'devanagari': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/devanagari_PP-OCRv3_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/devanagari_dict.txt'
                },
            },
            'cls': {
                'ch': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar',
                }
            },
        },
        'PP-OCRv2': {
            'det': {
                'ch': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar',
                },
            },
            'rec': {
                'ch': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar',
                    'dict_path': './ppocr/utils/ppocr_keys_v1.txt'
                }
            },
            'cls': {
                'ch': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar',
                }
            },
        },
        'PP-OCR': {
            'det': {
                'ch': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar',
                },
                'en': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_ppocr_mobile_v2.0_det_infer.tar',
                },
                'structure': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar'
                }
            },
            'rec': {
                'ch': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar',
                    'dict_path': './ppocr/utils/ppocr_keys_v1.txt'
                },
                'en': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_infer.tar',
                    'dict_path': './ppocr/utils/en_dict.txt'
                },
                'french': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/french_mobile_v2.0_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/french_dict.txt'
                },
                'german': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/german_mobile_v2.0_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/german_dict.txt'
                },
                'korean': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_mobile_v2.0_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/korean_dict.txt'
                },
                'japan': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_mobile_v2.0_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/japan_dict.txt'
                },
                'chinese_cht': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/chinese_cht_mobile_v2.0_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/chinese_cht_dict.txt'
                },
                'ta': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ta_mobile_v2.0_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/ta_dict.txt'
                },
                'te': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/te_mobile_v2.0_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/te_dict.txt'
                },
                'ka': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ka_mobile_v2.0_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/ka_dict.txt'
                },
                'latin': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/latin_ppocr_mobile_v2.0_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/latin_dict.txt'
                },
                'arabic': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/arabic_ppocr_mobile_v2.0_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/arabic_dict.txt'
                },
                'cyrillic': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/cyrillic_ppocr_mobile_v2.0_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/cyrillic_dict.txt'
                },
                'devanagari': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_mobile_v2.0_rec_infer.tar',
                    'dict_path': './ppocr/utils/dict/devanagari_dict.txt'
                },
                'structure': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar',
                    'dict_path': 'ppocr/utils/dict/table_dict.txt'
                }
            },
            'cls': {
                'ch': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar',
                }
            },
        }
    },
    'STRUCTURE': {
        'PP-Structure': {
            'table': {
                'en': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar',
                    'dict_path': 'ppocr/utils/dict/table_structure_dict.txt'
                }
            }
        },
        'PP-StructureV2': {
            'table': {
                'en': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar',
                    'dict_path': 'ppocr/utils/dict/table_structure_dict.txt'
                },
                'ch': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar',
                    'dict_path': 'ppocr/utils/dict/table_structure_dict_ch.txt'
                }
            },
            'layout': {
                'en': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout_infer.tar',
                    'dict_path':
                    'ppocr/utils/dict/layout_dict/layout_publaynet_dict.txt'
                },
                'ch': {
                    'url':
                    'https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout_cdla_infer.tar',
                    'dict_path':
                    'ppocr/utils/dict/layout_dict/layout_cdla_dict.txt'
                }
            }
        }
    }
}


def parse_args(mMain=True):
    import argparse
    parser = init_args()
    parser.add_help = mMain
    parser.add_argument("--lang", type=str, default='ch')
    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(
        "--ocr_version",
        type=str,
        choices=SUPPORT_OCR_MODEL_VERSION,
        default='PP-OCRv4',
        help='OCR Model version, the current model support list is as follows: '
        '1. PP-OCRv4/v3 Support Chinese and English detection and recognition model, and direction classifier model'
        '2. PP-OCRv2 Support Chinese detection and recognition model. '
        '3. PP-OCR support Chinese detection, recognition and direction classifier and multilingual recognition model.'
    )
    parser.add_argument(
        "--structure_version",
        type=str,
        choices=SUPPORT_STRUCTURE_MODEL_VERSION,
        default='PP-StructureV2',
        help='Model version, the current model support list is as follows:'
        ' 1. PP-Structure Support en table structure model.'
        ' 2. PP-StructureV2 Support ch and en table structure model.')

    for action in parser._actions:
        if action.dest in [
                'rec_char_dict_path', 'table_char_dict_path', 'layout_dict_path'
        ]:
            action.default = None
    if mMain:
        return parser.parse_args()
    else:
        inference_args_dict = {}
        for action in parser._actions:
            inference_args_dict[action.dest] = action.default
        return argparse.Namespace(**inference_args_dict)


def parse_lang(lang):
    latin_lang = [
        'af', 'az', 'bs', 'cs', 'cy', 'da', 'de', 'es', 'et', 'fr', 'ga', 'hr',
        'hu', 'id', 'is', 'it', 'ku', 'la', 'lt', 'lv', 'mi', 'ms', 'mt', 'nl',
        'no', 'oc', 'pi', 'pl', 'pt', 'ro', 'rs_latin', 'sk', 'sl', 'sq', 'sv',
        'sw', 'tl', 'tr', 'uz', 'vi', 'french', 'german'
    ]
    arabic_lang = ['ar', 'fa', 'ug', 'ur']
    cyrillic_lang = [
        'ru', 'rs_cyrillic', 'be', 'bg', 'uk', 'mn', 'abq', 'ady', 'kbd', 'ava',
        'dar', 'inh', 'che', 'lbe', 'lez', 'tab'
    ]
    devanagari_lang = [
        'hi', 'mr', 'ne', 'bh', 'mai', 'ang', 'bho', 'mah', 'sck', 'new', 'gom',
        'sa', 'bgc'
    ]
    if lang in latin_lang:
        lang = "latin"
    elif lang in arabic_lang:
        lang = "arabic"
    elif lang in cyrillic_lang:
        lang = "cyrillic"
    elif lang in devanagari_lang:
        lang = "devanagari"
    assert lang in MODEL_URLS['OCR'][DEFAULT_OCR_MODEL_VERSION][
        'rec'], 'param lang must in {}, but got {}'.format(
            MODEL_URLS['OCR'][DEFAULT_OCR_MODEL_VERSION]['rec'].keys(), lang)
    if lang == "ch":
        det_lang = "ch"
    elif lang == 'structure':
        det_lang = 'structure'
    elif lang in ["en", "latin"]:
        det_lang = "en"
    else:
        det_lang = "ml"
    return lang, det_lang


def get_model_config(type, version, model_type, lang):
    if type == 'OCR':
        DEFAULT_MODEL_VERSION = DEFAULT_OCR_MODEL_VERSION
    elif type == 'STRUCTURE':
        DEFAULT_MODEL_VERSION = DEFAULT_STRUCTURE_MODEL_VERSION
    else:
        raise NotImplementedError

    model_urls = MODEL_URLS[type]
    if version not in model_urls:
        version = DEFAULT_MODEL_VERSION
    if model_type not in model_urls[version]:
        if model_type in model_urls[DEFAULT_MODEL_VERSION]:
            version = DEFAULT_MODEL_VERSION
        else:
            logger.error('{} models is not support, we only support {}'.format(
                model_type, model_urls[DEFAULT_MODEL_VERSION].keys()))
            sys.exit(-1)

    if lang not in model_urls[version][model_type]:
        if lang in model_urls[DEFAULT_MODEL_VERSION][model_type]:
            version = DEFAULT_MODEL_VERSION
        else:
            logger.error(
                'lang {} is not support, we only support {} for {} models'.
                format(lang, model_urls[DEFAULT_MODEL_VERSION][model_type].keys(
                ), model_type))
            sys.exit(-1)
    return model_urls[version][model_type][lang]


def img_decode(content: bytes):
    np_arr = np.frombuffer(content, dtype=np.uint8)
    return cv2.imdecode(np_arr, cv2.IMREAD_UNCHANGED)


def check_img(img):
    if isinstance(img, bytes):
        img = img_decode(img)
    if isinstance(img, str):
        # download net image
        if is_link(img):
            download_with_progressbar(img, 'tmp.jpg')
            img = 'tmp.jpg'
        image_file = img
        img, flag_gif, flag_pdf = check_and_read(image_file)
        if not flag_gif and not flag_pdf:
            with open(image_file, 'rb') as f:
                img_str = f.read()
                img = img_decode(img_str)
            if img is None:
                try:
                    buf = BytesIO()
                    image = BytesIO(img_str)
                    im = Image.open(image)
                    rgb = im.convert('RGB')
                    rgb.save(buf, 'jpeg')
                    buf.seek(0)
                    image_bytes = buf.read()
                    data_base64 = str(base64.b64encode(image_bytes),
                                      encoding="utf-8")
                    image_decode = base64.b64decode(data_base64)
                    img_array = np.frombuffer(image_decode, np.uint8)
                    img = cv2.imdecode(img_array, cv2.IMREAD_COLOR)
                except:
                    logger.error("error in loading image:{}".format(image_file))
                    return None
        if img is None:
            logger.error("error in loading image:{}".format(image_file))
            return None
    if isinstance(img, np.ndarray) and len(img.shape) == 2:
        img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)

    return img


class PaddleOCR(predict_system.TextSystem):
    def __init__(self, **kwargs):
        """
        paddleocr package
        args:
            **kwargs: other params show in paddleocr --help
        """
        params = parse_args(mMain=False)
        params.__dict__.update(**kwargs)
        assert params.ocr_version in SUPPORT_OCR_MODEL_VERSION, "ocr_version must in {}, but get {}".format(
            SUPPORT_OCR_MODEL_VERSION, params.ocr_version)
        params.use_gpu = check_gpu(params.use_gpu)

        if not params.show_log:
            logger.setLevel(logging.INFO)
        self.use_angle_cls = params.use_angle_cls
        lang, det_lang = parse_lang(params.lang)

        # init model dir
        det_model_config = get_model_config('OCR', params.ocr_version, 'det',
                                            det_lang)
        params.det_model_dir, det_url = confirm_model_dir_url(
            params.det_model_dir,
            os.path.join(BASE_DIR, 'whl', 'det', det_lang),
            det_model_config['url'])
        rec_model_config = get_model_config('OCR', params.ocr_version, 'rec',
                                            lang)
        params.rec_model_dir, rec_url = confirm_model_dir_url(
            params.rec_model_dir,
            os.path.join(BASE_DIR, 'whl', 'rec', lang), rec_model_config['url'])
        cls_model_config = get_model_config('OCR', params.ocr_version, 'cls',
                                            'ch')
        params.cls_model_dir, cls_url = confirm_model_dir_url(
            params.cls_model_dir,
            os.path.join(BASE_DIR, 'whl', 'cls'), cls_model_config['url'])
        if params.ocr_version in ['PP-OCRv3', 'PP-OCRv4']:
            params.rec_image_shape = "3, 48, 320"
        else:
            params.rec_image_shape = "3, 32, 320"
        # download model if using paddle infer
        if not params.use_onnx:
            maybe_download(params.det_model_dir, det_url)
            maybe_download(params.rec_model_dir, rec_url)
            maybe_download(params.cls_model_dir, cls_url)

        if params.det_algorithm not in SUPPORT_DET_MODEL:
            logger.error('det_algorithm must in {}'.format(SUPPORT_DET_MODEL))
            sys.exit(0)
        if params.rec_algorithm not in SUPPORT_REC_MODEL:
            logger.error('rec_algorithm must in {}'.format(SUPPORT_REC_MODEL))
            sys.exit(0)

        if params.rec_char_dict_path is None:
            params.rec_char_dict_path = str(
                Path(__file__).parent / rec_model_config['dict_path'])

        logger.debug(params)
        # init det_model and rec_model
        super().__init__(params)
        self.page_num = params.page_num

    def ocr(self,
            img,
            det=True,
            rec=True,
            cls=True,
            bin=False,
            inv=False,
            alpha_color=(255, 255, 255)):
        """
        OCR with PaddleOCR
        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
            cls: use angle classifier or not. Default is True. If True, the text with rotation of 180 degrees can be recognized. If no text is rotated by 180 degrees, use cls=False to get better performance. Text with rotation of 90 or 270 degrees can be recognized even if cls=False.
            bin: binarize image to black and white. Default is False.
            inv: invert image colors. Default is False.
            alpha_color: set RGB color Tuple for transparent parts replacement. Default is pure white.
        """
        assert isinstance(img, (np.ndarray, list, str, bytes))
        if isinstance(img, list) and det == True:
            logger.error('When input a list of images, det must be false')
            exit(0)
        if cls == True and self.use_angle_cls == False:
            logger.warning(
                'Since the angle classifier is not initialized, it will not be used during the forward process'
            )

        img = check_img(img)
        # for infer pdf file
        if isinstance(img, list):
            if self.page_num > len(img) or self.page_num == 0:
                self.page_num = len(img)
            imgs = img[:self.page_num]
        else:
            imgs = [img]

        def preprocess_image(_image):
            _image = alpha_to_color(_image, alpha_color)
            if inv:
                _image = cv2.bitwise_not(_image)
            if bin:
                _image = binarize_img(_image)
            return _image

        if det and rec:
            ocr_res = []
            for idx, img in enumerate(imgs):
                img = preprocess_image(img)
                dt_boxes, rec_res, _ = self.__call__(img, cls)
                if not dt_boxes and not rec_res:
                    ocr_res.append(None)
                    continue
                tmp_res = [[box.tolist(), res]
                           for box, res in zip(dt_boxes, rec_res)]
                ocr_res.append(tmp_res)
            return ocr_res
        elif det and not rec:
            ocr_res = []
            for idx, img in enumerate(imgs):
                img = preprocess_image(img)
                dt_boxes, elapse = self.text_detector(img)
                if not dt_boxes:
                    ocr_res.append(None)
                    continue
                tmp_res = [box.tolist() for box in dt_boxes]
                ocr_res.append(tmp_res)
            return ocr_res
        else:
            ocr_res = []
            cls_res = []
            for idx, img in enumerate(imgs):
                if not isinstance(img, list):
                    img = preprocess_image(img)
                    img = [img]
                if self.use_angle_cls and cls:
                    img, cls_res_tmp, elapse = self.text_classifier(img)
                    if not rec:
                        cls_res.append(cls_res_tmp)
                rec_res, elapse = self.text_recognizer(img)
                ocr_res.append(rec_res)
            if not rec:
                return cls_res
            return ocr_res


import json
import os
import io
import zipfile
import shutil

class Result:
    def __init__(self, id, value):
        self.id = id
        self.value = value




def result_encoder(obj):
    if isinstance(obj, Result):
        return {'id': obj.id, 'PaddleOCR': obj.value}
    return json.JSONEncoder.default(obj)

import paddle

paddle.disable_signal_handler() # 在2.2版本提供了disable_signal_handler接口

from flask import Flask, request

app = Flask(__name__)

@app.route('/OCR', methods=['GET','POST'])
def fun():
    print(request.files)
    uploaded_file = request.files['file']
    if not uploaded_file:
        return {'error': 'No file is provided'}

    suffix = uploaded_file.filename.split('.')[-1]  # 取得文件的后缀名
    # #也可以根据文件的后缀名对文件类型进行过滤，如:
    if suffix.lower() not in ['jpg', 'png', 'jpeg', 'zip']:
        return {'error': 'The uploaded file type is invalid'}

    image_folder = './images/'
    if not os.path.exists(image_folder):
        os.makedirs(image_folder)
    if suffix.lower() in ['jpg', 'png', 'jpeg']:
        # uploaded_file.save(image_folder + uploaded_file.filename.split('.')[-2])
        # image_folder = image_folder + uploaded_file.filename.split('.')[-2]

        save_path=image_folder + uploaded_file.filename.split('.')[-2]
        if not os.path.exists(save_path):
            os.makedirs(save_path)
        uploaded_file.save(os.path.join(save_path, uploaded_file.filename))
        image_folder = save_path

    else:
        zip_buffer = io.BytesIO(uploaded_file.read())
        with zipfile.ZipFile(zip_buffer, 'r') as zip_ref:
            zip_ref.extractall(image_folder)  # 解压缩到指定的目标文件夹

        save_path=image_folder + uploaded_file.filename.split('.')[-2]
        # uploaded_file.save(image_folder+'/'+uploaded_file.filename)
        # with zipfile.ZipFile('/data1/xyj/PaddleOCR/images/app_test.zip', 'r') as zip_ref:
        #     zip_ref.extractall(image_folder)  # 解压缩到指定的目标文件夹
        # image_folder = save_path

        # with zipfile.ZipFile('/data1/xyj/PaddleOCR/images/app_test.zip', 'r') as zip_ref:
        #     for member in zip_ref.infolist():
        #         zip_ref.extract(member.filename, image_folder)
        # image_folder = save_path

        # shutil.unpack_archive('/data1/xyj/PaddleOCR/images/app_test.zip', image_folder, 'zip')
        image_folder = save_path
    # image_folder = "/data1/xyj/datasets/zh_test"
    # image_folder = request.json['image_folder']
    output_path = 'outputs/'
    if not os.path.exists(output_path):
        os.makedirs(output_path)

    output_path = os.path.join(output_path, "zh_test_PaddleOCR.json")
    if (os.path.exists(output_path)):
        os.remove(output_path)

    # 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

    ans = {}
    for filename in os.listdir(image_folder):
        img_path = os.path.join(image_folder, filename)
        result = ocr.ocr(img_path, cls=True)
        for res in result:
            outputs=''
            if res is not None:
                for line in res:
                    outputs=outputs+line[1][0]+' '

        res = Result(filename, outputs)
        with open(output_path, "a", encoding="utf8") as file:
            json.dump(result_encoder(res), file, ensure_ascii=False, indent=4)
        ans[filename] = outputs
# 将列表转换为 JSON 格式的字符串
    json_data = json.dumps(ans, ensure_ascii=False)

    # 将 JSON 字符串写入文件
    with open("data.json", "w") as file:
        file.write(json_data)
    return {'result': json_data}

if __name__ == '__main__':
    app.run(host='0.0.0.0', port=5009)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797

app_ppocr.py

声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/不正经/article/detail/364279