2020-11-30

最新推荐文章于 2022-02-15 19:30:00 发布

置顶夜ギ声(ಥ_ಥ)~\(≧▽≦)/~

最新推荐文章于 2022-02-15 19:30:00 发布

阅读量81

点赞数 1

文章标签： python

原文链接：https://blog.csdn.net/qq_37272891

版权

基于python的百度APl批量文字图片识别。

coding=utf-8

import os
import sys
import json
import base64

from urllib.request import urlopen
from urllib.request import Request
from urllib.error import URLError
from urllib.parse import urlencode
from urllib.parse import quote_plus

防止https证书校验不正确

import ssl

ssl._create_default_https_context = ssl._create_unverified_context

API_KEY = ‘’# 在这里写入你的API Key

SECRET_KEY = ‘’# 在这里写入你的API私钥

OCR_URL = “https://aip.baidubce.com/rest/2.0/ocr/v1/accurate_basic”#API类型

“”" TOKEN start “”"
TOKEN_URL = ‘https://aip.baidubce.com/oauth/2.0/token’

“”"
获取token
“”"
def fetch_token():
params = {‘grant_type’: ‘client_credentials’,
‘client_id’: API_KEY,
‘client_secret’: SECRET_KEY}
post_data = urlencode(params)
post_data = post_data.encode(‘utf-8’)
req = Request(TOKEN_URL, post_data)
try:
f = urlopen(req, timeout=5)
result_str = f.read()
except URLError as err:
print(err)
result_str = result_str.decode()

result = json.loads(result_str)

if ('access_token' in result.keys() and 'scope' in result.keys()):
    if not 'brain_all_scope' in result['scope'].split(' '):
        print ('please ensure has check the  ability')
        exit()
    return result['access_token']
else:
    print ('please overwrite the correct API_KEY and SECRET_KEY')
    exit()

“”"
读取文件
“”"
def read_file(image_path):
f = None
try:
f = open(image_path, ‘rb’)
return f.read()
except:
print(‘read image file fail’)
return None
finally:
if f:
f.close()

“”"
调用远程服务
“”"
def request(url, data):
req = Request(url, data.encode(‘utf-8’))
has_error = False
try:
f = urlopen(req)
result_str = f.read()
result_str = result_str.decode()
return result_str
except URLError as err:
print(err)

if name == ‘main’:

# 获取access token
path = ""#这里是你的图片所在的文件夹
path1 = ""#这里是你图片文字识别后的文字存放的地方
token = fetch_token()#获取token

# 拼接通用文字识别高精度url
image_url = OCR_URL + "?access_token=" + token

text = ""

# 读取书籍页面图片

files = os.listdir(path)
file_content = []
for i in files:
    filesPath = path+i
    #print(i)
    file_content.append(read_file(filesPath))
    #print(file_content)
for i in file_content:
    # 调用文字识别服务
    result = ""
    result = request(image_url, urlencode({'image': base64.b64encode(i)}))

    # 解析返回结果
    try:
        result_json = json.loads(result)
        for words_result in result_json["words_result"]:
            text = text + words_result["words"]
    except:
        print("错误！")
        continue

    # 打印文字

    file_handle = open(path1, mode='w')
    file_handle.write(text)
    file_handle.write("\n")
    file_handle.close()
    #print(text)