Background: I'm using cx_Freeze to compile a larger program into an EXE. The EXE works on my machine, but will not work on any other machine.
I believe I've isolated the problem to the file creation process within the program. Below is a simplified example of what I attempt to run:
file_name = '%s\\%s.txt' % (os.getcwd(), 5)
with open(file_name, 'wb') as f:
# do something
Again, this succesfully creates a file on my machine, however on all other machines I've tested, the following error occurs:
IOError: [Errno 22] invalid mode <'wb'> or filename: 'C:\\Users\\John G\\5.txt'
Initially I thought the double slashes (\) in the filepath were the root cause, but I no longer believe they are the issue because when I print file_name on the other machine, the output is normal: C:\Users\John G\5.txt
Can someone explain why this code runs successfully on my machine but fails on other machines? All machines are running Windows 10. One had Python installed and the other did not -- both failed.
EDIT: full code included below. The IO error occurs at with open(name_text) as f:
def main(file_path):
with open(file_path, 'rb') as pdf_file:
pdf_buffer = StringIO(pdf_file.read())
try:
input_pdf = pyPdf.PdfFileReader(pdf_buffer)
except:
input_pdf = pyPdf.PdfFileReader(decompress_pdf(pdf_buffer))
no_of_pages = input_pdf.getNumPages()
headers = []
row_list = []
text = []
count = 0
for i in range(no_of_pages):
writer = pyPdf.PdfFileWriter()
page = input_pdf.getPage(i)
writer.addPage(page)
file_name = '%s\\%s.pdf' % (os.getcwd(), count)
newFile = open(file_name,'wb')
writer.write(newFile)
newFile.close()
count += 1
try:
process = subprocess.call(['pdftotext', '-layout', file_name])
except:
print 'fail'
name_text = re.sub('.pdf$','.txt',file_name)
with open(name_text) as f:
for line in f:
line = line.decode('ascii','ignore').replace('\n','').replace(',','').replace(';','').strip()
if line != '':
text.append(line)
os.remove(name_text)
os.remove(file_name)
details_start = ''
details_end = ''
details_dict = {}
attribute_start = ''
details_bool = True
attributes_bool = False
for x,y in enumerate(text):
if 'DATABASE' in y:
details_start = int(x +1)
if 'PostingBody' in y:
details_end = int(x)
#print details_end
if 'Attributes' in y:
attribute_start = int(x)
attributes_bool = True
renewal_dates = []
for x in range(details_start, details_end):
if 'posting_renewal_dates' in text[x]:
n = 0
#print text[x].split(':')[1].strip()
if text[x].split(':')[1].strip() != 'n/a':
testbool = True
while testbool:
if not 'record_modified:' in text[x+n]:
if 'posting_renewal_dates:' in text[x+n]:
renewal_dates.append( text[x+n].split(': ')[1] )
else:
renewal_dates.append( text[x+n] )
n += 1
else:
testbool = False
elif not text[x][0].isupper():
#print text[x]
key = text[x].split(':')[0]
value = text[x].split(':')[1]
if key != '':
details_dict[key] = value
try:
xObject = page['/Resources']['/XObject'].getObject()
for obj in xObject:
if xObject[obj]['/Subtype'] == '/Image':
size = (xObject[obj]['/Width'], xObject[obj]['/Height'])
data = xObject[obj].getData()
mode = "RGB"
try:
if not os.path.exists('%s/%s' % (new_folder, details_dict['posting_id'])):
os.mkdir('%s/%s' % (new_folder, details_dict['posting_id'].strip(' ')))
img_dir = '%s/%s' % (new_folder, details_dict['posting_id'].strip(' '))
print 'Success -- ' + img_dir
else:
print "Directory already exists"
except:
print 'Directory %s already exists' % details_dict['posting_id']
#print xObject[obj]['/Filter']
#print xObject[obj]['/ColorSpace']
if xObject[obj]['/Filter'] == '/FlateDecode':
img = Image.frombytes(mode, size, data)
img.save(img_dir + '\\' + obj[1:] + ".jpg")
elif xObject[obj]['/Filter'] == '/DCTDecode':
img = open(obj[1:] + ".jpg", "wb")
img.write(data)
img.close()
elif xObject[obj]['/Filter'] == '/JPXDecode':
img = open(obj[1:] + ".jp2", "wb")
img.write(data)
img.close()
except:
print 'No images found for %s' % details_dict['posting_id']
body = ''
if attributes_bool:
for x in range(details_end+2, attribute_start):
body += text[x] + ' '
else:
for x in range(details_end+2, len(text)-1):
body += text[x] + ' '
attributes_dict = {}
if attributes_bool:
for x in range(attribute_start+2, len(text)-1):
try:
key = text[x].split(':')[0]
value = text[x].split(':')[1]
except:
pass
attributes_dict[key] = value
row = []
for x in details_dict:
if not x in headers:
headers.append(x)
row.append(details_dict[x])
if not 'body' in headers:
headers.append('body')
row.append(body)
row_list.append(row)
with open(filename, 'wb') as f:
csvwriter = csv.writer(f)
csvwriter.writerow(headers)
for x in row_list:
csvwriter.writerow(x)
