feat: 实现基于FastAPI的OCR服务

This commit is contained in:
kingc2022 2024-10-01 18:26:31 +08:00
commit dcca409772
8 changed files with 515 additions and 0 deletions

323
.gitignore vendored Normal file
View File

@ -0,0 +1,323 @@
### VisualStudioCode template
.vscode/*
!.vscode/settings.json
!.vscode/tasks.json
!.vscode/launch.json
!.vscode/extensions.json
!.vscode/*.code-snippets
# Local History for Visual Studio Code
.history/
# Built Visual Studio Code Extensions
*.vsix
### JetBrains template
# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
# User-specific stuff
.idea/**/workspace.xml
.idea/**/tasks.xml
.idea/**/usage.statistics.xml
.idea/**/dictionaries
.idea/**/shelf
# AWS User-specific
.idea/**/aws.xml
# Generated files
.idea/**/contentModel.xml
# Sensitive or high-churn files
.idea/**/dataSources/
.idea/**/dataSources.ids
.idea/**/dataSources.local.xml
.idea/**/sqlDataSources.xml
.idea/**/dynamic.xml
.idea/**/uiDesigner.xml
.idea/**/dbnavigator.xml
# Gradle
.idea/**/gradle.xml
.idea/**/libraries
# Gradle and Maven with auto-import
# When using Gradle or Maven with auto-import, you should exclude module files,
# since they will be recreated, and may cause churn. Uncomment if using
# auto-import.
# .idea/artifacts
# .idea/compiler.xml
# .idea/jarRepositories.xml
# .idea/modules.xml
# .idea/*.iml
# .idea/modules
# *.iml
# *.ipr
# CMake
cmake-build-*/
# Mongo Explorer plugin
.idea/**/mongoSettings.xml
# File-based project format
*.iws
# IntelliJ
out/
# mpeltonen/sbt-idea plugin
.idea_modules/
# JIRA plugin
atlassian-ide-plugin.xml
# Cursive Clojure plugin
.idea/replstate.xml
# SonarLint plugin
.idea/sonarlint/
# Crashlytics plugin (for Android Studio and IntelliJ)
com_crashlytics_export_strings.xml
crashlytics.properties
crashlytics-build.properties
fabric.properties
# Editor-based Rest Client
.idea/httpRequests
# Android studio 3.1+ serialized cache file
.idea/caches/build_file_checksums.ser
### VirtualEnv template
# Virtualenv
# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
.Python
[Bb]in
[Ii]nclude
[Ll]ib
[Ll]ib64
[Ll]ocal
[Ss]cripts
pyvenv.cfg
.venv
pip-selfcheck.json
### Windows template
# Windows thumbnail cache files
Thumbs.db
Thumbs.db:encryptable
ehthumbs.db
ehthumbs_vista.db
# Dump file
*.stackdump
# Folder config file
[Dd]esktop.ini
# Recycle Bin used on file shares
$RECYCLE.BIN/
# Windows Installer files
*.cab
*.msi
*.msix
*.msm
*.msp
# Windows shortcuts
*.lnk
### macOS template
# General
.DS_Store
.AppleDouble
.LSOverride
# Icon must end with two \r
Icon
# Thumbnails
._*
# Files that might appear in the root of a volume
.DocumentRevisions-V100
.fseventsd
.Spotlight-V100
.TemporaryItems
.Trashes
.VolumeIcon.icns
.com.apple.timemachine.donotpresent
# Directories potentially created on remote AFP share
.AppleDB
.AppleDesktop
Network Trash Folder
Temporary Items
.apdisk
### Python template
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
cover/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
.pybuilder/
target/
# Jupyter Notebook
.ipynb_checkpoints
# IPython
profile_default/
ipython_config.py
# pyenv
# For a library or package, you might want to ignore these files since the code is
# intended to run in multiple environments; otherwise, check them in:
# .python-version
# pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies.
#Pipfile.lock
# poetry
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
# This is especially recommended for binary packages to ensure reproducibility, and is more
# commonly ignored for libraries.
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
#poetry.lock
# pdm
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#pdm.lock
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
# in version control.
# https://pdm.fming.dev/#use-with-ide
.pdm.toml
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
__pypackages__/
# Celery stuff
celerybeat-schedule
celerybeat.pid
# SageMath parsed files
*.sage.py
# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.dmypy.json
dmypy.json
# Pyre type checker
.pyre/
# pytype static type analyzer
.pytype/
# Cython debug symbols
cython_debug/
# PyCharm
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
# and can be added to the global gitignore or merged into this file. For a more nuclear
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
#.idea/

8
.idea/.gitignore vendored Normal file
View File

@ -0,0 +1,8 @@
# 默认忽略的文件
/shelf/
/workspace.xml
# 基于编辑器的 HTTP 客户端请求
/httpRequests/
# Datasource local storage ignored files
/dataSources/
/dataSources.local.xml

View File

@ -0,0 +1,6 @@
<component name="InspectionProjectProfileManager">
<settings>
<option name="USE_PROJECT_PROFILE" value="false" />
<version value="1.0" />
</settings>
</component>

7
.idea/misc.xml Normal file
View File

@ -0,0 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="Black">
<option name="sdkName" value="Python 3.12 (ocr)" />
</component>
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.12 (ocr)" project-jdk-type="Python SDK" />
</project>

8
.idea/modules.xml Normal file
View File

@ -0,0 +1,8 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectModuleManager">
<modules>
<module fileurl="file://$PROJECT_DIR$/.idea/ocr.iml" filepath="$PROJECT_DIR$/.idea/ocr.iml" />
</modules>
</component>
</project>

10
.idea/ocr.iml Normal file
View File

@ -0,0 +1,10 @@
<?xml version="1.0" encoding="UTF-8"?>
<module type="PYTHON_MODULE" version="4">
<component name="NewModuleRootManager">
<content url="file://$MODULE_DIR$">
<excludeFolder url="file://$MODULE_DIR$/.venv" />
</content>
<orderEntry type="inheritedJdk" />
<orderEntry type="sourceFolder" forTests="false" />
</component>
</module>

6
.idea/vcs.xml Normal file
View File

@ -0,0 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="VcsDirectoryMappings">
<mapping directory="$PROJECT_DIR$" vcs="Git" />
</component>
</project>

147
main.py Normal file
View File

@ -0,0 +1,147 @@
from fastapi import FastAPI, UploadFile, File, Query
from fastapi.responses import JSONResponse
import easyocr
from typing import Optional
import asyncio
import aiohttp # 用于异步 HTTP 请求
app = FastAPI()
# 初始化常用的语言组合 OCR 读取器
reader_sim = easyocr.Reader(['ch_sim', 'en'])
# 存储 OCR 读取器的缓存字典
readers = {}
# 使用 asyncio 的异步锁
lock = asyncio.Lock()
# 获取或初始化 OCR 读取器
async def get_reader(lang_1: Optional[str], lang_2: Optional[str]):
global readers, reader_sim, lock
# 语言组合
lang_combination = tuple(sorted([lang_1, lang_2] if lang_1 and lang_2 else [lang_1 or lang_2]))
# 默认使用中文简体和英文的 OCR 读取器
if not lang_1 and not lang_2:
return reader_sim, None # 没有错误
# 检查缓存中是否已经存在该语言组合的读取器
if lang_combination in readers:
return readers[lang_combination], None # 没有错误
# 使用锁避免并发问题,仅在初始化新读取器时需要锁
async with lock:
# 双重检查,确保其他请求在等待锁时未初始化该读取器
if lang_combination not in readers:
try:
# 尝试初始化 OCR 读取器
readers[lang_combination] = easyocr.Reader(list(lang_combination))
except ValueError as ve:
return None, str(ve) # 返回错误信息
except Exception as e:
return None, f"Unexpected error: {str(e)}" # 返回意外错误信息
return readers[lang_combination], None # 没有错误
# 通用的 OCR 处理函数
async def process_ocr(reader, image_data):
try:
# 执行 OCR 处理
result = reader.readtext(image_data)
# 创建一个用于存储提取信息的列表
output = []
# 遍历识别结果
for (bbox, text, confidence) in result:
# 将 bbox 中的每个坐标点转换为 Python 原生 int 类型
bbox = [[int(coord) for coord in point] for point in bbox]
entry = {
"text": text,
"bbox": bbox, # bounding box 位置信息
"confidence": confidence # 置信度
}
output.append(entry)
# 成功处理后返回数据
return {
"status": "success",
"message": "OCR 处理成功",
"data": output
}, 200
except Exception as e:
# 处理失败,返回错误信息
return {
"status": "error",
"message": "OCR 处理失败",
"error": str(e),
"data": None
}, 500
@app.post("/ocr")
async def ocr_image(lang_1: Optional[str] = None, lang_2: Optional[str] = None, image: UploadFile = File(...)):
# 获取 OCR 读取器并捕获可能的错误
reader, error = await get_reader(lang_1, lang_2)
if error:
return JSONResponse(status_code=500, content={
"status": "error",
"message": "OCR 处理失败",
"error": error,
"data": None
})
try:
# 获取图片的二进制数据
image_data = await image.read()
except Exception as e:
return JSONResponse(status_code=500, content={
"status": "error",
"message": "无法读取图片文件",
"error": str(e),
"data": None
})
# 调用通用的 OCR 处理函数
response_data, status_code = await process_ocr(reader, image_data)
return JSONResponse(status_code=status_code, content=response_data)
@app.get("/ocr")
async def ocr_image_from_url(lang_1: Optional[str] = None, lang_2: Optional[str] = None, url: str = Query(...)):
# 使用 aiohttp 进行异步 HTTP 请求
async with aiohttp.ClientSession() as session:
try:
async with session.get(url) as response:
if response.status != 200:
raise Exception(f"无法获取图片, HTTP 状态码: {response.status}")
# 读取图片数据
image_data = await response.read()
except Exception as e:
return JSONResponse(status_code=500, content={
"status": "error",
"message": "无法从 URL 获取图片",
"error": str(e),
"data": None
})
# 获取 OCR 读取器并捕获可能的错误
reader, error = await get_reader(lang_1, lang_2)
if error:
return JSONResponse(status_code=500, content={
"status": "error",
"message": "OCR 处理失败",
"error": error,
"data": None
})
# 调用通用的 OCR 处理函数
response_data, status_code = await process_ocr(reader, image_data)
return JSONResponse(status_code=status_code, content=response_data)