Python3自动化_文件批量处理(文本、PDF、Excel；读取、筛选、导出)

利用Python3脚本语言的简练语法，高级语言的丰富类库，快速写了几个文件读取、筛选、导出的“脚本”。

这里简单总结一下关键功能。

 读取ini配置文件

检查ini文件是否存在；检查输入的key在ini文件里是否有定义。

 1 import configparser 
 2
 4 def getConfigInfo(_ini_nm):
 5 
 6     # Open Ini File
 7     config = configparser.ConfigParser()
 8     if not config.read(os.path.join(os.getcwd(),_ini_nm + r'.ini')):
 9         printLog(E',Read Ini file fail.)
10 
11     while True:
12         sysCode = input(rPlease input the system code : (Press [Enter] to quit):).strip()
13         if 0 == len(sysCode.strip()):
14             exit()
15 
16          Init ConnectionSettings
17         if sysCode in config.sections():
18             return dict(config[sysCode])
19         else:
20             print(Ini info of System [%s] is blank.\n' % sysCode)

 

多参数输入的获取

检查参数个数；检查参数合法性（长度，是否目录）；检查参数是否整个都是汉字。

 _main():
 2 
 3     path = ''
 4     keyWord =  7         para = input(rPlease input the PDF directory and Key Word: (Press [Enter] to quit):).strip().split()
 8 
 9          len(para):
10 11 
12         if 2 !=13             Two para -> [PDF directory and Key Word] is needed .' + \n14             continue
16         path = para[0]
17         keyWord = para[1]
18 
not os.path.exists(path):
input path is not a exists path.21             22 
23         flg = True
24         for char  keyWord.strip():
25             if char <= u\u4e00' or char >= u\u9fa526                 flg = False
27                 break
28          flg:
29             Please input the Chinese Key Word for search.(Such as \'物流\').30             31 
32         break

 

PostgreSQL数据库处理

根据ini文件定义的数据库连接信息，尝试连库；执行SQL文。

 psycopg2 
 4  traceback
 6  connDB(_cfg):
 7     try 8         conn = psycopg2.connect(database=_cfg[servicename], 9                                 user=_cfg[dbuser10                                 password=_cfg[dbpw11                                 host=_cfg[host12                                 port=_cfg[port])
 conn
14     except Exception:
15         printLog(Exception occur at DB Connection.' + traceback.format_exc())
16 
17  executeSql(_cfg,_sql):
18     19         conn = connDB(_cfg)
20         cur = conn.cursor()
21         cur.execute(_sql)
23         results = cur.fetchall()
return list(map(lambda x: x[0],results))
25     26         printLog(Exception occur at Execute SQL.27     finally28         cur.close()
29         conn.rollback()
30         conn.close()

  

日志处理

定义输出日志的级别；异常级别时，处理结束。

 1 logging.basicConfig(filename=log_' + datetime.now().strftime(%Y%m%d') + .txt,1)"> 2                     level=logging.INFO,1)"> 3                     format= %(asctime)s - %(levelname)s - %(message)s 4 
 5 logLevel = {D: logging.DEBUG,1)"> 6             I: logging.INFO,1)"> 7             W: logging.WARNING,1)"> 8             : logging.ERROR,1)"> 9             C: logging.CRITICAL}
11  printLog(_lvl,_msg):
12     logging.log(logLevel[_lvl],_msg)
13     if logging.ERROR == logLevel[_lvl]:
14         print(_msg)
15         exit()
17 
18 printLog(srcpath is not a exists path.19 printLog(Get Src Path : %s' % srcPath)

  

MAP函数运用

列表元素批量处理，按第二个下划线字符截取字符串。

1  getPreOfNm(x):
2     if 1 < x.count(_):
3         return x[0:x.find(') + 1)]
4     5          x
6 
7  Get prefix of CRUD object name
8 prefixObjNm = list(set(map(getPreOfNm,lstTb)))
9 prefixObjNm.sort()

  

目录处理

目录/文件判断；目录的路径分割；完整路径的文件名取得；

 Check the srcPath
 2 fullFilePaths = []
 3 if os.path.isdir(srcPath):
 4     for folderName,subFolders,fileNames  os.walk(srcPath):
 5         if os.path.split(folderName)[1] in [tcsdoc']:  6         for fn  fileNames:
 7              Get src file
 8             mObj = fileNmReg.search(fn)
 9              mObj:
                fullFilePaths.append(os.path.join(folderName,fn))
elif os.path.isfile(srcPath):
12     13     fn = os.path.basename(os.path.realpath(srcPath))
14     mObj =15     16         fullFilePaths.append(srcPath)

  

PDF文件读取

来源：https://www.cnblogs.com/alexzhang92/p/11488949.html

from pdfminer.converter  TextConverter
 2 from pdfminer.layout  LAParams
from pdfminer.pdfinterp  PDFResourceManager,process_pdf
 os
 6 
 7  read_pdf(pdf):
 resource manager
 9     rsrcmgr = PDFResourceManager()
10     retstr = StringIO()
11     laparams = LAParams()
 device
13     device = TextConverter(rsrcmgr,retstr,laparams=laparams)
    process_pdf(rsrcmgr,device,pdf)
    device.close()
16     content = retstr.getvalue()
    retstr.close()
 获取所有行
19     contents = str(content).split(""20 
21     return contents

 

CSV文件导出

 Init result file
2 rstFile = open(os.path.join(srcPath,1)">[CRUD]%Y%m%d%H%M%S.csv'),1)">w''3 rstWtr = csv.writer(rstFile,delimiter=\t4  Write head
5 rstWtr.writerow([TYPECIENCODELINE NUMCRUDTABLE NMFULL PATH'])

 

Excel文件读写

利用openpyxl读写xlsx，不支持xls；

获取工作簿、工作表、单元格（直接定位及相对位置）；

单元格赋值。

 os,openpyxl
 Init file path
 4 srcPath = r.\newDocs'
 Start Search
 9     for fileName 11         filePath = os.path.join(folderName,fileName)
12 
14             wb_WorkBook = openpyxl.load_workbook(filePath)
15          openpyxl.utils.exceptions.InvalidFileException:
16             print(fileName + xls read failed            wb_WorkBook.close()
19 
20          _履歴
21         st_Rireki = wb_WorkBook[_履歴22         if None is st_Rireki:
23             _履歴　is not exist24             25 
26         cl_Version = st_Rireki[AQ1027         28             is cl_Version.value or \
29                0 == len(str(cl_Version.value).strip()):
30                 cl_Version.value = 1.0.2.032                 cl_JobNo = st_Rireki.cell(row=cl_Version.row - 1,column=cl_Version.column)
33                 cl_JobNo.value = 12334  
35                 wb_WorkBook.save(filePath)
36 
37                 38 
39             40                 cl_Version = st_Rireki.cell(row=cl_Version.row + 5,1)">41 
42         wb_WorkBook.close()

 

 

转载请注明原文链接，谢谢。