Convert PDF to .txt file with Google Cloud Storage - pdf

Question

I have this code for Python on a local file system.
What is the equivalent Python object API for os.getcwd(), os.listdir?
I want this code to work using files from GCS?
In order to use GCS folders, I include this code
from google.cloud import storage
client = storage.Client()
bucket = client.bucket('my-bucket')
pdfDir = bucket.get_blob('uploads/pdf/')
txtDir = bucket.get_blob('uploads/txt/')
from cStringIO import StringIO
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
import os
import sys, getopt
#converts pdf, returns its text content as a string
def convert(fname, pages=None):
if not pages:
pagenums = set()
else:
pagenums = set(pages)
output = StringIO()
manager = PDFResourceManager()
converter = TextConverter(manager, output, laparams=LAParams())
interpreter = PDFPageInterpreter(manager, converter)
infile = file(fname, 'rb')
for page in PDFPage.get_pages(infile, pagenums):
interpreter.process_page(page)
infile.close()
converter.close()
text = output.getvalue()
output.close
return text
#converts all pdfs in directory pdfDir, saves all resulting txt files to
txtdir
def PDF2txt(pdfDir, txtDir):
if pdfDir == "": pdfDir = os.getcwd() + "\\" #if no pdfDir passed in
for pdf in os.listdir(pdfDir): #iterate through pdfs in pdf directory
fileExtension = pdf.split(".")[-1]
if fileExtension == "pdf":
pdfFilename = pdfDir + pdf
text = convert(pdfFilename) #get string of text content of pdf
textFilename = txtDir + pdf + ".txt"
textFile = open(textFilename, "w") #make text file
textFile.write(text) #write text to text file
pdfDir = "C:/pdftotxt/pdfs/"
txtDir = "C:/pdftotxt/txt/"
PDF2txt(pdfDir, txtDir)

Answer 1

I assume that what you want is to list objects in a bucket and objects in particular folders inside a bucket. For doing that you can use directly the Python Client Libraries that Google Cloud Storage provide. Use bucket.list_blobs() for listing the whole bucket and bucket.list_blobs(prefix=prefix, delimiter=delimiter) for listing a particular folder or object.
A more detailed documentation can be found here [1] and the Git repository containing the whole libraries here [2].