def ocr(pic):
try:
with open(pic, 'rb') as f:
f1 = f.read()
pic_base64 = str(base64.b64encode(f1), 'utf-8')
cred = credential.Credential("AKID96rMeho9uQiqjRvCI8C3f6esstjMjFZi",
"3toZ7RmtlSv9EA0f8LNJ6i6MOYXHoQr5")
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile('TC3-HMAC-SHA256')
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-guangzhou", clientProfile)
req = models.GeneralHandwritingOCRRequest()
params = '{"ImageBase64":"' + pic_base64 + '"}'
req.from_json_string(params)
resp = client.GeneralHandwritingOCR(req)
resp = json.loads(resp.to_json_string())
if not resp.get('TextDetections'):
return {'status': False, 'msg': '识别失败'}
data = []
for v in resp['TextDetections']:
data.append(v['DetectedText'])
return {'status': True, 'msg': 'success', 'data': data}
except FileNotFoundError as err_file:
return {'status': False, 'msg': err_file.strerror}
except TencentCloudSDKException as err:
return {'status': False, 'msg': err.get_message()}
def OcrBase64(Base64,SecretId,SecretKey):
try:
cred = credential.Credential(SecretId, SecretKey)
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-guangzhou", clientProfile)
req = models.GeneralBasicOCRRequest()
params = '{\"ImageBase64\":\"+' Base64 '+\"}'
req.from_json_string(params)
resp = client.GeneralBasicOCR(req)
jsonstr = json.loads(resp.to_json_string())
array = jsonstr['TextDetections']
s = ''
for i in array:
s = s + i['DetectedText']
return s
# f = open('C:\\Users\\hasee\\Documents\\UiPath\\Play\\1.txt','w')
# f.write(s)
# return '1'
except TencentCloudSDKException as err:
print(err)
def Tencent_OCR_IDCard(pic_str, flag_side, flag_piccut, flag_porcut):
cred = credential.Credential("Your ID", "Your Secret")
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-beijing", clientProfile)
req = models.IDCardOCRRequest()
params_1 = r'{"ImageBase64":"'
if flag_side:
params_2 = r'","CardSide":"BACK","Config":"{\"CropIdCard\":'
else:
params_2 = r'","CardSide":"FRONT","Config":"{\"CropIdCard\":'
if flag_piccut:
params_3 = r'false,\"CropPortrait\":'
else:
params_3 = r'true,\"CropPortrait\":'
if flag_porcut:
params_4 = r'false}"}'
else:
params_4 = r'true}"}'
params = params_1 + pic_str + params_2 + params_3 + params_4
#params = '{"ImageBase64":"pic_str","CardSide":"FRONT","Config":"{\\"CropIdCard\\":true,\\"CropPortrait\\":true}"}'
req.from_json_string(params)
resp = client.IDCardOCR(req)
text = resp.to_json_string()
return text
def tx_ocr(filePath, fileName):
# 实例化一个认证对象，入参需要传入腾讯云账户secretId，secretKey
cred = credential.Credential("AKIDoPltlNQxwfdPxFP5h7qwFLCojSvDC5f3",
"5wsZ5L1Vq0zlHYeV6yfGdkcFdmjTxCG6")
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-guangzhou", clientProfile)
req = models.TableOCRRequest()
path = filePath
with open(path, "rb") as f: #转为二进制格式
base64_data = base64.b64encode(f.read()) #使用base64进行加密
params = base64_data.decode('utf-8')
req.ImageBase64 = str(params)
resp = client.TableOCR(req)
data = base64.b64decode(resp.Data)
path = './res_xlsx/' + fileName + '.xlsx'
with open(path, "wb") as f:
f.write(data)
f.close
print('xlsx successed')
def get_tencent_biz(img_file_dir):
secret_id = "AKIDXjfVfZDDySfx1OHKt63lCNIwUBhxhceR"
secret_key = "g5LPDUVdV8XfYHju87oEOJyMTfcJkupW"
try:
with open(img_file_dir, 'rb') as f:
img_data = f.read()
img_base64 = base64.b64encode(img_data)
params = '{"ImageBase64":"' + str(img_base64, 'utf-8') + '"}'
cred = credential.Credential(secret_id, secret_key)
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-shanghai", clientProfile)
req = models.BizLicenseOCRRequest()
req.from_json_string(params)
resp = client.BizLicenseOCR(req)
return resp.Name, resp.Address
except TencentCloudSDKException as err:
print(err)
return '', ''
def ocr(file):
try:
idcardfile_base64 = str(base64.b64encode(file), 'utf-8')
cred = credential.Credential(config.tencent['general']['secretid'],
config.tencent['general']['secretkey'])
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile('TC3-HMAC-SHA256')
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-guangzhou", clientProfile)
req = models.GeneralAccurateOCRRequest()
params = {
'ImageBase64': idcardfile_base64,
}
params_json = json.dumps(params)
req.from_json_string(params_json)
resp = client.GeneralAccurateOCR(req)
resp = json.loads(resp.to_json_string())
if not resp.get('TextDetections'):
return {'status': False, 'msg': '识别失败'}
data = []
for v in resp['TextDetections']:
data.append(v['DetectedText'])
return {'status': True, 'msg': 'success', 'data': data}
except FileNotFoundError as err_file:
return {'status': False, 'msg': err_file.strerror}
except TencentCloudSDKException as err:
return {'status': False, 'msg': err.get_message()}
def img_to_excel(self, image_path, secret_id, secret_key):
# 实例化一个认证对象，入参需要传入腾讯云账户secretId，secretKey
cred = credential.Credential(secret_id, secret_key)
# 实例化client对象
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
clientProfile.signMethod = "TC3-HMAC-SHA256"
client = ocr_client.OcrClient(cred, "ap-guangzhou", clientProfile)
# 实例化一个请求对象
req = models.GeneralFastOCRRequest()
# 读取图片数据，使用Base64编码
with open(image_path, 'rb') as f:
image = f.read()
image_base64 = str(base64.b64encode(image), encoding='utf-8')
req.ImageBase64 = image_base64
# 通过client对象调用访问接口，传入请求对象
resp = client.TableOCR(req)
# 获取返回数据（Data为Base64编码后的Excel数据）
data = resp.Data
# 转换为Excel
path_excel = image_path + ".xlsx"
with open(path_excel, 'wb') as f:
f.write(base64.b64decode(data))
return path_excel
def get_json(path):
try:
cred = credential.Credential("", "")
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-beijing", clientProfile)
req = models.QrcodeOCRRequest()
# with open(file=img_path, mode='rb') as file:
# base64_data = base64.b64encode(file.read())
# 对本地图片进行base64转码【本地图片解析需要先转成base64编码】
# img = cv2.imread(path)
# imshow(img)
with open(path, 'rb') as f:
# base64_data = base64.b64encode(f.read())
# s = base64_data.decode()
# ImageBase64_value = 'data:image/jpeg;base64,%s'%s
# #params是字符串，以下进行拼接
# params = '{"ImageBase64":"' + ImageBase64_value + '"}' #以图片Base64编码发送请求
base64data = base64.b64encode(f.read()) # 得到 byte 编码的数据
base64data = str(base64data, 'utf-8') # 重新编码数据
params = '{"ImageBase64":"' + base64data + '"}'
req.from_json_string(params)
resp = client.QrcodeOCR(req)
print(f"腾讯值:{resp.to_json_string()}")
except TencentCloudSDKException as err:
print(err)
def tencentOCR(src, format):
try:
cred = credential.Credential("AKIDqUBfvwgZCan9Ppq93kEVgcHM4QY24Z9U",
"IqSTZUQ7nJSPzsxnOo34rQOFsIlx1tcI")
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-guangzhou", clientProfile)
req = models.GeneralBasicOCRRequest()
params = '{"ImageBase64":"data:image/' + format + ';base64,' + src + '"}'
req.from_json_string(params)
resp = client.GeneralBasicOCR(req)
recv = resp.to_json_string()
except TencentCloudSDKException as err:
print(err)
str = json.loads(recv)
DetectedText = jsonpath.jsonpath(str, "$..DetectedText")
parseDetect = ""
for msg in DetectedText:
print(msg)
parseDetect += msg + '\n'
return parseDetect
def picocr(self):
ocrarea = ImageGrab.grab(bbox=(p.left, p.top, p.right, p.bottom))
ocrarea.save(fp.ocr_area)
with open(fp.ocr_area, 'rb') as f:
base64_data = base64.b64encode(f.read())
s = base64_data.decode()
ImageBase64_value = 'data:image/jpeg;base64,%s'%s
try:
cred = credential.Credential(k.SECRET_ID, k.SECRET_KEY)
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.ap-guangzhou.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-guangzhou", clientProfile)
req = models.GeneralBasicOCRRequest()
params = '{"ImageBase64":"' + ImageBase64_value + '"}'
req.from_json_string(params)
resp = client.GeneralBasicOCR(req)
Orecognition.ocrresult = resp.to_json_string()
with open(fp.txt_ocr_path,"w", encoding='utf-8') as f:
transjson = json.loads(ocrresult)
for item in transjson['TextDetections']:
line = item['DetectedText']
f.write("%s\n" %(line))
except TencentCloudSDKException as err:
print(err)
def englishOCR(cls, bs, action="ImageBase64", region="ap-shanghai"):
bs = str(bs, encoding="utf-8")
try:
cred = credential.Credential(cls._secretId, cls._secretKey)
httpProfile = HttpProfile()
httpProfile.endpoint = cls._endpoint
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, region, clientProfile)
req = models.EnglishOCRRequest()
params = {action: bs}
req.from_json_string(json.dumps(params))
resp = client.EnglishOCR(req)
texts = resp.TextDetections
total = len(texts)
actual = 0
res = []
for ele in texts:
text = ele.DetectedText
text = text.strip()
if not text:
continue
actual += 1
res.append(text)
return {"data": res, "total": total, "actual": actual}, None
except Exception as e:
return None, e
def getCodeFromImg(res, imgUrl):
response = res.get(imgUrl, verify=False) # 将这个图片保存在内存
# 得到这个图片的base64编码
imgCode = str(base64.b64encode(BytesIO(response.content).read()),
encoding='utf-8')
# print(imgCode)
try:
cred = credential.Credential(Utils.getYmlConfig()['SecretId'],
Utils.getYmlConfig()['SecretKey'])
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-beijing", clientProfile)
req = models.GeneralBasicOCRRequest()
params = {"ImageBase64": imgCode}
req.from_json_string(json.dumps(params))
resp = client.GeneralBasicOCR(req)
codeArray = json.loads(resp.to_json_string())['TextDetections']
code = ''
for item in codeArray:
code += item['DetectedText'].replace(' ', '')
if len(code) == 4:
return code
else:
return Utils.getCodeFromImg(res, imgUrl)
except TencentCloudSDKException as err:
raise Exception('验证码识别出现问题了' + str(err.message))
def run(SecretId, SecretKey, files):
''' 行业文档识别-表格识别, 使用本地图片转换为ImageBase64格式. '''
try:
cred = credential.Credential(SecretId, SecretKey)
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "", clientProfile)
# 调用接口
req = models.TableOCRRequest()
for img_file in files:
image_base64 = encode_image(img_file)
params = '{"ImageBase64":"{}"}'.format(image_base64)
print(params)
req.from_json_string(params)
resp = client.TableOCR(req)
base64_res = resp["Response"][
"Data"] # String, Base64 编码后的 Excel 数据
destine_file = 'output/' + ".".join(
img_file.split(".")[0:-1]) + ".xlsx"
write_res2file(base64_res, destine_file)
except TencentCloudSDKException as err:
print(err)
def recognition():
try:
# 生成证书
cred = credential.Credential("AKIDwdGfopwkR6VYO04bXCbia4IJD43wOCH7", "XcXAWcSWaFl0yhYDdnLdeQXquiHYT8Yl")
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
# 初始化客户端实例
clientProfile = ClientProfile("TC3-HMAC-SHA256")
# 按就近的使用，所以我用的是ap-shanghai
client = ocr_client.OcrClient(cred, "ap-shanghai", clientProfile)
req = models.GeneralAccurateOCRRequest()
with open("../images/t_2.jpeg", 'rb') as f:
base64_data = base64.b64encode(f.read())
s = base64_data
params = '{"ImageBase64":"' + str(s, 'utf-8') + '"}'
req.from_json_string(params)
resp = client.GeneralAccurateOCR(req)
result = resp.TextDetections
# 将官网文档里输出字符串格式的转换为字典，如果不需要可以直接print(resp)
return result
except TencentCloudSDKException as err:
print(err)
def postToOCR(image_path):
try:
# Using own SecretID and SecretKey from tencent cloud
cred = credential.Credential("", "")
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
# Using prefer region
client = ocr_client.OcrClient(cred, "na-toronto", clientProfile)
req = models.GeneralBasicOCRRequest()
base64 = ct.convertToBase64(image_path)
params = {"ImageBase64": base64}
req.from_json_string(json.dumps(params))
resp = client.GeneralBasicOCR(req)
#convert to json format
resp = json.loads(resp.to_json_string())
with open('static/respondJson/respond.json', 'w') as outfile:
json.dump(resp, outfile)
# with open('static/respondJson/respond.json', 'r') as fp:
# resp = json.load(fp)
print(type(resp))
return resp
except TencentCloudSDKException as err:
print(err)
def get_tencent_reg(img_file_dir):
secret_id = "AKIDXjfVfZDDySfx1OHKt63lCNIwUBhxhceR"
secret_key = "g5LPDUVdV8XfYHju87oEOJyMTfcJkupW"
try:
with open(img_file_dir, 'rb') as f:
img_data = f.read()
img_base64 = base64.b64encode(img_data)
params = '{"ImageBase64":"' + str(img_base64, 'utf-8') + '"}'
cred = credential.Credential(secret_id, secret_key)
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-shanghai", clientProfile)
req = models.GeneralBasicOCRRequest()
req.from_json_string(params)
resp = client.GeneralBasicOCR(req).to_json_string()
ret_list = re.findall(r'"DetectedText": "(.*?)"', resp)
return ret_list
except TencentCloudSDKException as err:
print(err)
return []
def __init__(self, secret_id, secret_key):
cred = credential.Credential(secret_id, secret_key)
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
self.client = ocr_client.OcrClient(cred, "ap-guangzhou", clientProfile)
def ocr(file, side='front'):
idcardfile_base64 = str(base64.b64encode(file), 'utf-8')
try:
api_config = global_dict.get_value("api_config")
cred = credential.Credential(api_config['appid'],
api_config['appsecret'])
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile('TC3-HMAC-SHA256')
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-guangzhou", clientProfile)
req = models.IDCardOCRRequest()
params = {
'ImageBase64':
idcardfile_base64,
'CardSide':
'FRONT' if side == 'front' else 'BACK',
'Config':
'{"CopyWarn":true,"BorderCheckWarn":true,"ReshootWarn":true,"DetectPsWarn":true,"TempIdWarn":true,"InvalidDateWarn":true}'
}
params_json = json.dumps(params)
req.from_json_string(params_json)
resp = client.IDCardOCR(req)
resp = json.loads(resp.to_json_string())
warns = ";".join(get_warns(resp))
if not resp.get('Name') and not resp.get('Authority'):
err_msg = "身份证识别错误;" + warns
return {'status': False, 'msg': err_msg}
msg = '读取成功;' + warns
if side == 'front':
return {
'status': True,
'msg': msg,
'data': {
'name': resp['Name'],
'gender': resp['Sex'],
'nation': resp['Nation'],
'birth': resp['Birth'].replace('/', '-'),
'address': resp['Address'],
'idnum': resp['IdNum'],
}
}
else:
return {
'status': True,
'msg': msg,
'data': {
'authority': resp['Authority'],
'validity': resp['ValidDate'],
}
}
except TencentCloudSDKException as err:
return {'status': False, 'msg': err.get_message()}
def Tencent_car_api(img_base64):
APP_config_ini = ConfigObj(APP_config_file, encoding='UTF8')
car = dict()
try:
cred = credential.Credential(APP_config_ini['tencent_sdk']['api_id'],
APP_config_ini['tencent_sdk']['api_key'])
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(
cred, APP_config_ini['tencent_sdk']['api_area'], clientProfile)
req = models.LicensePlateOCRRequest()
params = '{\"ImageBase64\":\"' + img_base64 + '\"}'
req.from_json_string(params)
resp = client.LicensePlateOCR(req)
# print(resp.to_json_string())
# {"Number": "渝AN7968", "Confidence": 99, "RequestId": "bc9f8509-1d4b-4990-9557-03b0f17e7eba"}
_json_data_text = resp.to_json_string() # json格式化的文本字符串
_json_data_dict = json.loads(_json_data_text) # 将腾讯json字符串转换为字典
car['number'] = _json_data_dict['Number']
car['confidence'] = _json_data_dict['Confidence']
car['requestId'] = _json_data_dict['RequestId']
car['code'] = 1
car['data'] = '识别成功'
car['error'] = ''
car['car_code_service'] = '1.0' # 该字段将作为E4A APP校验内容是否是所需的json格式返回
except TencentCloudSDKException as err:
car['code'] = 0
car['data'] = '识别出错'
car['car_code_service'] = '1.0' # 该字段将作为E4A APP校验内容是否是所需的json格式返回
error = str(err)
print(error)
if 'FailedOperation.DownLoadError' in error:
car['error'] = '文件下载失败'
if 'FailedOperation.ImageDecodeFailed' in error:
car['error'] = '图片解码失败'
if 'FailedOperation.OcrFailed' in error:
car['error'] = 'OCR识别失败'
if 'FailedOperation.UnKnowError' in error:
car['error'] = '未知错误'
if 'FailedOperation.UnOpenError' in error:
car['error'] = '服务未开通'
if 'LimitExceeded.TooLargeFileError' in error:
car['error'] = '文件内容太大'
if 'ResourcesSoldOut.ChargeStatusException' in error:
car['error'] = '云识别系统计费状态异常'
if 'secret id should not be none' in error:
car['error'] = '云识别系统未配置'
return car
def ocrFiles():
try:
resourceList = []
for filename in os.listdir(r"./resources"):
if 'JPG' in filename.upper():
resourceList.append(filename)
print("总图片数: ", len(resourceList))
cred = credential.Credential(os.environ.get("TENCENTCLOUD_SECRET_ID"),
os.environ.get("TENCENTCLOUD_SECRET_KEY"))
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-shanghai", clientProfile)
for filename in resourceList:
postDict = {
'filename': filename,
'ocrStatus': False,
'postKey': ''
}
try:
with open("./resources/%s" % filename, 'rb') as file:
req = models.GeneralEfficientOCRRequest()
content = file.read()
b64 = str(base64.b64encode(content), 'utf-8')
req.ImageBase64 = b64
resp = client.GeneralEfficientOCR(req)
data = json.loads(resp.to_json_string())
# print(resp.to_json_string())
for index, value in enumerate(data['TextDetections']):
if '投票地址' in value[
'DetectedText'] or 'senbatsu' in value[
'DetectedText']:
targetItem1 = data['TextDetections'][
index + 1]['DetectedText'].replace(' ', '')
targetItem2 = data['TextDetections'][
index + 2]['DetectedText'].replace(' ', '')
if isContainChinese(targetItem1):
postDict['postKey'] = targetItem2
else:
postDict['postKey'] = targetItem1
except Exception as e:
pass
if postDict['postKey']:
postDict['ocrStatus'] = True
print(postDict)
yield (postDict)
except TencentCloudSDKException as err:
print(err)
def main_handler(event, context):
logger.info("start main handler")
if "requestContext" not in event.keys():
return {"code": 410, "errorMsg": "event is not come from api gateway"}
if "body" not in event.keys():
return {
"isBase64Encoded": False,
"statusCode": 200,
"headers": {
"Content-Type": "text",
"Access-Control-Allow-Origin": "*"
},
"body": "there is no file from api gateway"
}
#从网关上传的图片格式已经做过Base64，在event['body']里可以直接获取
logger.info("Start to detection")
try:
secret_id = os.environ.get('TENCENTCLOUD_SECRETID')
secret_key = os.environ.get('TENCENTCLOUD_SECRETKEY')
token = os.environ.get('TENCENTCLOUD_SESSIONTOKEN')
cred = credential.Credential(secret_id, secret_key, token)
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-beijing", clientProfile)
req = models.GeneralBasicOCRRequest()
params = '{"ImageBase64":"%s"}' % event['body']
req.from_json_string(params)
resp = client.GeneralBasicOCR(req)
res_ai = json.loads(resp.to_json_string())
res_text = " "
print(len(res_ai["TextDetections"]))
for i in range(len(res_ai["TextDetections"])):
res_text = res_text + str(
res_ai["TextDetections"][i]["DetectedText"])
except TencentCloudSDKException as err:
print(err)
print(res_text)
response = {
"isBase64Encoded": False,
"statusCode": 200,
"headers": {
"Content-Type": "text",
"Access-Control-Allow-Origin": "*"
},
"body": res_text
}
return response
def dataFromPictures(picture, SecretId, SecretKey):
resp = None
# try:
with open(picture, "rb") as f:
img_data = f.read()
img_base64 = base64.b64encode(img_data)
cred = credential.Credential(SecretId, SecretKey) # Secret ID and Key
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-shanghai", clientProfile)
req = models.TableOCRRequest()
# params = '{"ImageBase64":"' + str(img_base64) + '"}'
params = '{"ImageBase64":"' + str(img_base64, 'utf-8') + '"}'
req.from_json_string(params)
resp = client.TableOCR(req)
# print(resp.to_json_string())
# except TencentCloudSDKException as err:
# print(err)
## load resp to json
result1 = json.loads(resp.to_json_string())
rowIndex = []
colIndex = []
content = []
for item in result1['TextDetections']:
rowIndex.append(item['RowTl'])
colIndex.append(item['ColTl'])
content.append(item['Text'])
rowIndex = pd.Series(rowIndex)
colIndex = pd.Series(colIndex)
index = rowIndex.unique()
index.sort()
columns = colIndex.unique()
columns.sort()
data = pd.DataFrame(index=index, columns=columns)
for i in range(len(rowIndex)):
data.loc[rowIndex[i], colIndex[i]] = re.sub(" ", "", content[i])
return result1, data
def excelFromPictures(picture, SecretId, SecretKey):
rowIndex = []
colIndex = []
content = []
try:
with open(picture, "rb") as f:
img_data = f.read()
img_base64 = base64.b64encode(img_data)
cred = credential.Credential(SecretId, SecretKey) #ID和Secret从腾讯云申请
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-shanghai", clientProfile)
req = models.TableOCRRequest()
params = '{"ImageBase64":"' + str(img_base64, 'utf-8') + '"}'
req.from_json_string(params)
resp = client.TableOCR(req)
# print(resp.to_json_string())
##提取识别出的数据，并且生成json
result1 = json.loads(resp.to_json_string())
for item in result1['TextDetections']:
rowIndex.append(item['RowTl'])
colIndex.append(item['ColTl'])
content.append(item['Text'])
except TencentCloudSDKException as err:
print(err)
##导出Excel
##ExcelWriter方案
rowIndex = pd.Series(rowIndex)
colIndex = pd.Series(colIndex)
index = rowIndex.unique()
index.sort()
columns = colIndex.unique()
columns.sort()
data = pd.DataFrame(index=index, columns=columns)
for i in range(len(rowIndex)):
data.loc[rowIndex[i], colIndex[i]] = re.sub(" ", "", content[i])
writer = pd.ExcelWriter("." + re.match(".*\.", f.name).group() + "xlsx",
engine='xlsxwriter')
data.to_excel(writer, sheet_name='Sheet1', index=False, header=False)
writer.save()
def tencentcloud(self, img_and_txt_paths):
"""tencentcloud
Args:
img_and_txt_paths:
Returns:
txt_dirname:
"""
for path in img_and_txt_paths:
img_path = path[0]
txt_save_path = path[1]
save_dir = os.path.split(txt_save_path)[0]
# 循环消除重名txt文件
while (os.path.exists(txt_save_path)):
txt_save_path = self.eliminate_dup_name(
txt_save_path, save_dir)
try:
cred = credential.Credential(
os.environ.get("TENCENTCLOUD_SECRET_ID"),
os.environ.get("TENCENTCLOUD_SECRET_KEY"))
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-shanghai",
clientProfile)
# 识别模型
req = models.GeneralAccurateOCRRequest()
# 将图片转化为base64编码格式
with open(img_path, "rb") as rf:
base64_data = base64.b64encode(rf.read())
req.ImageBase64 = str(base64_data, 'utf-8')
resp = client.GeneralAccurateOCR(req)
results = resp.TextDetections
if results != None:
with open(txt_save_path, "wt", encoding="gbk") as wf:
for line in results:
wf.write(str(line.DetectedText))
except TencentCloudSDKException as err:
print(err.get_code(), err.get_message())
return os.path.dirname(txt_save_path)
def tencent_image2str_url(uuid_url_dict, types="characters"):
from tencentcloud.common import credential
from tencentcloud.common.profile.client_profile import ClientProfile
from tencentcloud.common.profile.http_profile import HttpProfile
from tencentcloud.common.exception.tencent_cloud_sdk_exception import TencentCloudSDKException
from tencentcloud.ocr.v20181119 import ocr_client, models
uuid_text_dict = {}
try:
cred = credential.Credential(Tencent_API_KEY, Tencent_SECRET_KEY)
http_profile = HttpProfile()
http_profile.endpoint = "ocr.ap-chengdu.tencentcloudapi.com"
client_profile = ClientProfile()
client_profile.httpProfile = http_profile
client = ocr_client.OcrClient(cred, "ap-beijing",
client_profile) # create a connection
req = None
if types == "questions":
req = models.EduPaperOCRRequest() # questions model
elif types == "characters":
req = models.GeneralBasicOCRRequest() # characters model
for uuid, url in uuid_url_dict.items():
params = {}
params = '{\"ImageUrl\":\"url\"}'.replace("url", url)
print("OCR resolving %s" % url)
req.from_json_string(params)
ret = ''
try:
if types == "questions":
resp = client.EduPaperOCR(req)
for questionsblock in resp.QuestionBlockInfos:
for textblock in questionsblock.QuestionArr:
ret = ret + textblock.QuestionText + '\n'
elif types == "characters":
resp = client.GeneralBasicOCR(req)
for textblock in resp.TextDetections:
if textblock.Confidence >= 85:
ret = ret + textblock.DetectedText + '\n'
uuid_text_dict[uuid] = ret
except TencentCloudSDKException as err:
print(err)
print("OCR failed! URL:%s, set text empty" % url)
uuid_text_dict[uuid] = ''
return uuid_text_dict
except TencentCloudSDKException as err:
print(err)
return uuid_text_dict
def Tencent_OCR_Summary(pic_str, mode):
try:
cred = credential.Credential("Your ID", "Your Secret")
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-beijing", clientProfile)
if mode == '11': #11:通用印刷体识别
return Tencent_OCR_Basic_Print(pic_str, client)
elif mode == '12': #12:通用印刷体识别（高速版）
return Tencent_OCR_Basic_Print_Fast(pic_str, client)
elif mode == '13': #13:通用印刷体识别（高精度版）
return Tencent_OCR_Basic_Print_HighAccurate(pic_str, client)
elif mode == '14': #14:通用手写体识别
return Tencent_OCR_Handwriting(pic_str, client)
elif mode == '15': #15:英文识别
return Tencent_OCR_English(pic_str, client)
elif mode == '21': #21:身份证识别
return # 废弃
elif mode == '22': #22:营业执照识别
return Tencent_OCR_BizLicense(pic_str, client)
elif mode == '23': #23:银行卡识别
return Tencent_OCR_BankCard(pic_str, client)
elif mode == '24': #24:名片识别
return # 废弃
elif mode == '31': #31:增值税发票识别
return Tencent_OCR_VatInvoice(pic_str, client)
elif mode == '32': #32：运单识别
return Tencent_OCR_Waybill(pic_str, client)
elif mode == '41': #41:驾驶证识别
return Tencent_OCR_DriverLicense(pic_str, client)
elif mode == '42': #42：车牌识别
return Tencent_OCR_LicensePlate(pic_str, client)
elif mode == '43': #43：车辆VIN码识别
return Tencent_OCR_Vin(pic_str, client)
elif mode == '44': #44：行驶证识别
return # 废弃
elif mode == '51': #51:算式识别
return Tencent_OCR_Arithmetic(pic_str, client)
elif mode == '52': #52：表格识别
return Tencent_OCR_Table(pic_str, client)
else:
return Tencent_OCR_Basic_Print(pic_str, client)
except TencentCloudSDKException as err:
print(err)
def excelFromPictures(path, picture):
SecretId = ""
SecretKey = ""
with open(picture, "rb") as f:
img_data = f.read()
img_base64 = b64encode(img_data)
cred = credential.Credential(SecretId, SecretKey) #ID和Secret从腾讯云申请
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-shanghai", clientProfile)
req = models.VatInvoiceOCRRequest()
params = '{"ImageBase64":"' + str(img_base64, 'utf-8') + '"}'
req.from_json_string(params)
# false=0
try:
resp = client.VatInvoiceOCR(req)
# print(resp.to_json_string())
except TencentCloudSDKException as err:
print("识别", picture, "错误[", err, "]\n可重试")
##提取识别出的数据，并且生成json
result1 = loads(resp.to_json_string())
# print(result1)
# print(resp.to_json_string())
invoicedf = DataFrame(zeros(5).reshape(1, 5),
columns=["发票代码", "发票号码", "开票日期", "合计金额", "小写金额"])
for item in result1['VatInvoiceInfos']:
if item["Name"] in ["发票代码", "发票号码", "开票日期", "合计金额", "小写金额"]:
invoicedf[item["Name"]] = item["Value"]
#
# writer = ExcelWriter(path+"/tables/" +re.match(".*\.",f.name).group()+"xlsx", engine='xlsxwriter')
# data.to_excel(writer,sheet_name = 'Sheet1', index=False,header = False)
# writer.save()
#
print("已经完成[" + f.name + "]的识别")
return invoicedf
def ocr(file):
try:
api_config = global_dict.get_value("api_config")
invoicefile_base64 = str(base64.b64encode(file), 'utf-8')
cred = credential.Credential(api_config['appid'],
api_config['appsecret'])
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile('TC3-HMAC-SHA256')
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-guangzhou", clientProfile)
req = models.VatInvoiceOCRRequest()
params = {
'ImageBase64': invoicefile_base64,
}
params_json = json.dumps(params)
req.from_json_string(params_json)
resp = client.VatInvoiceOCR(req)
resp = json.loads(resp.to_json_string())
if not resp.get('VatInvoiceInfos'):
return {'status': False, 'msg': '发票识别失败'}
data = {}
for v in resp['VatInvoiceInfos']:
if v['Name'] == '货物或应税劳务、服务名称':
data['goods_name'] = v['Value']
if v['Name'] == '购买方名称':
data['payer_name'] = v['Value']
if v['Name'] == '数量':
data['goods_num'] = v['Value']
if v['Name'] == '单位':
data['goods_unit'] = v['Value']
if v['Name'] == '开票日期':
data['issue_date'] = v['Value']
if v['Name'] == '发票号码':
data['invoice_number'] = v['Value']
if v['Name'] == '金额':
data['invoice_amount'] = v['Value']
if v['Name'] == '单价':
data['invoice_unit_price'] = v['Value']
return {'status': True, 'data': data}
except TencentCloudSDKException as err:
return {'status': False, 'msg': str(err)}
def get_text(image_code):
try:
cred = credential.Credential("XXXXX", "XXXXX")
httpProfile = HttpProfile()
httpProfile.endpoint = "ocr.tencentcloudapi.com"
clientProfile = ClientProfile()
clientProfile.httpProfile = httpProfile
client = ocr_client.OcrClient(cred, "ap-guangzhou", clientProfile)
req = models.GeneralBasicOCRRequest()
params = '{"ImageBase64":"' + image_code + '"}'
req.from_json_string(params)
resp = client.GeneralBasicOCR(req)
return resp.to_json_string()
except TencentCloudSDKException as err:
print(err)
def ocr_text(img_base):
try:
cred = credential.Credential("AKIDnQq0uYw4vVoqa3GDtIRKxKQFo56rNhml", "rcASVIp54mDNHuHF0UjjTxCbkdFaeRzI")
http_profile = HttpProfile()
http_profile.endpoint = "ocr.tencentcloudapi.com"
client_profile = ClientProfile()
client_profile.httpProfile = http_profile
client = ocr_client.OcrClient(cred, "ap-beijing", client_profile)
req = models.GeneralHandwritingOCRRequest()
params = {
"ImageBase64": img_base
}
req.from_json_string(json.dumps(params))
resp = client.GeneralHandwritingOCR(req)
print("read_text========", resp.to_json_string())
return resp.TextDetections
except TencentCloudSDKException as err:
print("read_text=======", err)