This is my solution for the problem. It comes with the feature of also checking in sub-directories, as well as being able to handle multiple file types. It is also quite easy to add support for other ones. The downside is of course that it's quite chunky code. But let me know what you think.
import os
import docx2txt
from pptx import Presentation
import pdfplumber
def findFiles(strings, dir, subDirs, fileContent, fileExtensions):
# Finds all the files in 'dir' that contain one string from 'strings'.
# Additional parameters:
# 'subDirs': True/False : Look in sub-directories of your folder
# 'fileContent': True/False :Also look for the strings in the file content of every file
# 'fileExtensions': True/False : Look for a specific file extension -> 'fileContent' is ignored
filesInDir = []
foundFiles = []
filesFound = 0
if not subDirs:
for filename in os.listdir(dir):
if os.path.isfile(os.path.join(dir, filename).replace("\\", "/")):
filesInDir.append(os.path.join(dir, filename).replace("\\", "/"))
else:
for root, subdirs, files in os.walk(dir):
for f in files:
if not os.path.isdir(os.path.join(root, f).replace("\\", "/")):
filesInDir.append(os.path.join(root, f).replace("\\", "/"))
print(filesInDir)
# Find files that contain the keyword
if filesInDir:
for file in filesInDir:
print("Current file: "+file)
# Define what is to be searched in
filename, extension = os.path.splitext(file)
if fileExtensions:
fileText = extension
else:
fileText = os.path.basename(filename).lower()
if fileContent:
fileText += getFileContent(file).lower()
# Check for translations
for string in strings:
print(string)
if string in fileText:
foundFiles.append(file)
filesFound += 1
break
return foundFiles
def getFileContent(filename):
'''Returns the content of a file of a supported type (list: supportedTypes)'''
if filename.partition(".")[2] in supportedTypes:
if filename.endswith(".pdf"):
content = ""
with pdfplumber.open(filename) as pdf:
for x in range(0, len(pdf.pages)):
page = pdf.pages[x]
content = content + page.extract_text()
return content
elif filename.endswith(".txt"):
with open(filename, 'r') as f:
content = ""
lines = f.readlines()
for x in lines:
content = content + x
f.close()
return content
elif filename.endswith(".docx"):
content = docx2txt.process(filename)
return content
elif filename.endswith(".pptx"):
content = ""
prs = Presentation(filename)
for slide in prs.slides:
for shape in slide.shapes:
if hasattr(shape, "text"):
content = content+shape.text
return content
else:
return ""
supportedTypes = ["txt", "docx", "pdf", "pptx"]
print(findFiles(strings=["buch"], dir="C:/Users/User/Desktop/", subDirs=True, fileContent=True, fileExtensions=False))