文字识别小项目-调用百度api文字识别，并将结果存入txt文件

import os
import os.path
import sys
from aip import AipOcr
APP_ID = '10498120'
API_KEY = 'hwwISLbyb1en11SsjDyEu7tW'
SECRET_KEY = 'waOoWyci9GDlRw1CkWNtmfkHRNokwhca'
client = AipOcr(APP_ID, API_KEY, SECRET_KEY)

# 读取图片,返回路径的集合
def file_name(file_dir):
 pathSet = []
 FN = []
 for root, dirs, files in os.walk(file_dir):
 for file in files:
 FN.append(file)
 pathSet.append(os.path.join(root, file))
 return pathSet

# 打开文件 读取文件内容
def get_file_content(filePath):
 with open(filePath, 'rb') as fp:
 return fp.read()

# 返回文件的类型符号，如：最后.jpg
def file_extension(path):
 return os.path.splitext(path)[1]

file_dir = 'E:images_new'
pathSet = file_name(file_dir)
result = []

for filePath in pathSet:
 # 调用通用文字识别接口
 if (file_extension(filePath) == '.jpg'):
 result = client.basicGeneral(get_file_content(filePath))
 # {'log_id': 6775584000925260612, 'words_result_num': 1, 'words_result': [{'words': '20'}]}
 if 'words_result' in result:
 rest = result['words_result'][0]['words']
 else:
 break
 f = open('E:\images_new\result.txt', 'a', encoding='utf-8')
 f.write('
'+'/images_new/' + os.path.basename(filePath) + ' ' + rest)
 f.close()

# 如果图片是url 调用示例如下
#result = client.basicGeneral('http://www.xxxxxx.com/img.jpg')