如何解决我的代码很难看:只从文件列表中提取我想要的文件
我的代码完成了工作,但它很丑,太长而且很笨拙。我必须处理数千个文件,这些文件分为 4 组,我只想要一种特定类型
我想要: '.docx'
我不想: “.pdf”、“SS.docx”或“ss.docx”
我尝试了几个 if not
,但它们并没有真正奏效。最后,我建立了所有文件类型的列表,并将它们一个接一个地反连接到完整列表中,以便只保留我感兴趣的文件。
问题:
是否可以简化我的 if elif 块?可以用更少的行来直接访问我需要的文件吗?
是否可以将 df 生成打包到一个循环中,而不必手动为每个生成?
#List all dirs under given dirs and subdirs
import os
import pandas as pd
import glob
import docx
from docx.api import Document
#fixed variable
location = 'C:\\Data_analysis\\N_TRACKING'
#all lists
dirs_in_dir = []
SS_files_in_dir = []
ss_files_in_dir = []
pdfs_in_dir = []
targets_in_dir = []
all_files = []
#active mapping of the directory tree and the files in it : List all dirs under given dirs and subdirs and add to list dirs_in_dirs
# r=>root,d=>directories,f=>files
for r,d,f in os.walk(location):
for item in d:
if '' in item:
dirs_in_dir.append(os.path.join(r,item))
for r,f in os.walk(location):
for item in f:
if '' in item:
all_files.append(os.path.join(r,item))
#active mapping: list all pdfs and add to list pdfs_in_dir,#list all SS containing files and add to list files_in_dir,#list all.docx files and add to list targets_in_dir
# r=>root,f in os.walk(location):
for item in f:
if '.pdf' in item:
pdfs_in_dir.append(os.path.join(r,item))
elif 'SS' in item:
SS_files_in_dir.append(os.path.join(r,item))
elif 'ss' in item:
ss_files_in_dir.append(os.path.join(r,item))
elif '.docx' in item:
targets_in_dir.append(os.path.join(r,item))
#antijoin: step one creating df
SS_files_df = pd.DataFrame(SS_files_in_dir)
ss_files_df = pd.DataFrame(ss_files_in_dir)
pdfs_df = pd.DataFrame(pdfs_in_dir)
all_files_df = pd.DataFrame(all_files)
all_files_df.columns=['Files']
SS_files_df.columns=['Files']
ss_files_df.columns=['Files']
pdfs_df.columns=['Files']
all_files_df.columns=['Files']
#antijoin: step 2 subtract all other df from all_files_df
#remove pdf df
no_pdfs = all_files_df.merge(pdfs_df,on='Files',how='left',indicator=True)
index_names = no_pdfs[no_pdfs['_merge'] == 'both'].index
# drop these row indexes
# from dataFrame
no_pdfs.drop(index_names,inplace = True)
no_pdfs.drop(['_merge'],axis = 1,inplace = True)
no_ss = no_pdfs
#remove ss_files
no_ss = no_ss.merge(ss_files_df,indicator=True)
index_names = no_ss[no_ss['_merge'] == 'both'].index
# drop these row indexes
# from dataFrame
no_ss.drop(index_names,inplace = True)
no_ss.drop(['_merge'],inplace = True)
no_SS = no_ss
#remove SS_files
no_SS = no_SS.merge(SS_files_df,indicator=True)
index_names = no_SS[no_SS['_merge'] == 'both'].index
# drop these row indexes
# from dataFrame
no_SS.drop(index_names,inplace = True)
no_SS.drop(['_merge'],inplace = True)
解决方法
因为你:
- 只需要“.docx”(即由后缀决定)
- 不要:'.pdf'、'SS.docx' 或 'ss.docx'(即符合这些结尾)
这可以更简单地完成,如下所示。
代码--使用 str 结尾的选项 1
import os
def find_docx(location):
all_files = [] # Will contain found files
# Walk top-down through directory tree
for (root,dirs,files) in os.walk(location,topdown=True):
for f in files:
f = f.lower() # Make conditional case insensitive
if f.endswith('.pdf'):
continue # Skipping pdf
if f.endswith('ss.docx'):
continue # Skipping ss.docx or SS.docx
if f.endswith('.docx'):
# Desired docx (undesired docx has been filtered out by previous conditional)
all_files.append(os.path.join(root,f))
return all_files
代码--使用正则表达式的选项 2
def find_docx(location):
desired = re.compile(r".*?docx$",re.IGNORECASE) # .docx suffix
undesired = re.compile(r".*?(.pdf|ss.docx)$",flags = re.IGNORECASE) # pdf and ss.docx suffix
all_files = [] # Will contain found files
# Walk top-down through directory tree
for (root,topdown=True):
for f in files:
if desired.match(f) and not undesired.match(f):
# Matches desired and doesn't match undesired
all_files.append(os.path.join(root,f))
return all_files
使用
使用上述任一 find_docx 函数。
location = r'C:\Data_analysis\N_TRACKING'
all_files = find_docx(location)
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。