def export_ditie_img_to_txt(import_path, export_path='.'):
"""
扫描该路径将所有地铁png图片转为txt
:param import_path: 扫描的文件夹路径
:param export_path:输出的文件夹路径
:return: 如果成功，为True，如果失败为False
"""
rst = False
# pdf识别路径
img_files = file_operate.get_files_by_extension(import_path,
extension_name='png')
if img_files == []:
print("文件夹没有文img文件")
logging.warning('文件夹没有img文件')
return False
for img in img_files:
try:
txtname = os.path.join(
export_path, f'{file_operate.split_path(img)[1]}ditie.txt')
export_txtfile(img, txtname)
rst = True
except Exception as e:
print(e)
traceback.print_exc(file=open('log.txt', 'w+', encoding='utf-8'))
return rst
def export_pdf_to_txt(import_path, export_path='.'):
"""
扫描该路径将所有pdf文件转为txt
:param import_path: 扫描的文件夹路径
:param export_path:输出的文件夹路径
:return: 如果成功，为True，如果失败为False
"""
rst = False
# pdf识别路径
pdf_files = file_operate.get_files_by_extension(import_path,
extension_name='pdf')
if pdf_files == []:
print("文件夹没有文pdf件")
logging.warning('文件夹没有pdf文件')
return False
for pdf in pdf_files:
try:
pdf2text(pdf, export_path)
rst = True
except Exception as e:
print(e)
traceback.print_exc(file=open('log.txt', 'w+', encoding='utf-8'))
return rst
except:
print("ditie_starttime或ditie_endtime或maildownload_endtime或maildownload_starttime格式错误")
#清空以前下载内容
for file in os.listdir(maildownloadfolder):
os.remove(os.path.join(maildownloadfolder,file))
# for folder in exportfolder,importfolder,maildownloadfolder:
# '' if os.path.exists(folder) else os.mkdir(folder)
# # 将滴滴附件和地铁附件件从邮箱下载到文件夹内
mailprocess.get_baoxiao_info(maildownload_starttime,maildownload_endtime,maildownloadfolder)
#地铁截图输出的文档信息路径
dite_data=[]
filelist=[]
if ImageReconize.export_ditie_img_to_txt(importfolder, exportfolder):
filelist=file_operate.get_files_by_extension(exportfolder,'txt')
for filepath in filelist:
i=file_operate.split_path(filepath)[1].find("ditie")
if i<0:
continue
tmp=dataprocess.ditie_data_process(filepath,reason,ditie_starttime,ditie_endtime)
if not len(tmp):
print(f'文件路径：{filepath} 无法获取报销信息')
continue
if not len(dite_data):
dite_data=tmp
continue
dite_data=np.vstack((dite_data,tmp))
#pdf信息提取---------------------------------------------------
didi_data=[]
if srt<0:
break
end=txt.find('\n',srt)
if end<0:
print(txt[srt:])
break
data=txt[srt:end].split(" ")
if len(data)!=9:
break
data=[data[1],data[5],data[6],"出租车",reason,"","","","",data[8]]
inf.append(data)
srt=txt.find("快车",end)
return inf
# ------------------------填写的信息--------------------------
REASON="检查样机进度"
filelist=file_operate.get_files_by_extension(r'C:\Users\123456\PycharmProjects\报销自动化\pdf识别','txt')
inf = get_excel_dididatas(filelist,REASON)
print(inf)
print(len(inf[0]))
#---------------------------excel操作---------------------------
SRT_ROW=11
END_ROW=11
excel=win32.gencache.EnsureDispatch('Excel.Application')
wb=excel.Workbooks.Open(r'C:\Users\123456\PycharmProjects\报销自动化\表格处理\交通费报销表昆山3.xlsx')
excel.Visible=True
ws=wb.Worksheets(1)
for data in inf:
cell_range=f'B{SRT_ROW}:K{END_ROW}'
print(cell_range)
print(data)
ws.Range(cell_range).Value=tuple(data)
import sys
sys.path.append(r'C:\Users\123456\PycharmProjects\usermodules')
from file_operate import file_operate
from MyException import MyException
from MyException.MyException import FILE_ERROR_INFOR
import fitz
import os
import traceback
print(fitz.__doc__)
print(fitz.version)
# pdf识别路径
pdf_file = file_operate.get_files_by_extension(extension_name='pdf')
def pdf2text(file_path, output_path='.'):
"""
:param filename: 文件路径
:return: filename.txt
"""
if not file_operate.exist_file(file_path):
raise MyException.FileErrorException(
FILE_ERROR_INFOR['FILE_NOT_FOUNT'])
if not file_operate.check_extension(file_path):
raise MyException.FileErrorException(
FILE_ERROR_INFOR['FILE_EXTESION_ERROR'])
pdf_file = fitz.open(file_path)
page1 = pdf_file[0]
text = page1.getText('text')