def FindDuplicatesFilesInFolder(path):
shatab = []
total = 0
small_count, dup_count, error_count = 0, 0, 0
pngdir = path
if not os.path.exists(path):
sg.MsgBox('Duplicate Finder', '** Folder doesn\'t exist***', path)
return
pngfiles = os.listdir(pngdir)
total_files = len(pngfiles)
for idx, f in enumerate(pngfiles):
if not sg.EasyProgressMeter('Counting Duplicates', idx + 1,
total_files, 'Counting Duplicate Files'):
break
total += 1
fname = os.path.join(pngdir, f)
if os.path.isdir(fname):
continue
x = open(fname, "rb").read()
m = hashlib.sha256()
m.update(x)
f_sha = m.digest()
if f_sha in shatab:
# uncomment next line to remove duplicate files
# os.remove(fname)
dup_count += 1
# sg.Print(f'Duplicate file - {f}') # cannot current use sg.Print with Progress Meter
continue
shatab.append(f_sha)
msg = f'{total} Files processed\n'\
f'{dup_count} Duplicates found\n'
sg.MsgBox('Duplicate Finder Ended', msg)
def EasyProgressMeter():
"""
Easy Progress Meter
This recipe shows just how easy it is to add a progress meter to your code.
"""
import PySimpleGUI as sg
for i in range(1000):
sg.EasyProgressMeter('Easy Meter Example', i+1, 1000)
raise SystemExit()
t0 = mytime() # set start timer
doc = fitz.open()
width, height = fitz.PaperSize("a4")
rect = fitz.Rect(0, 0, width, height) + (36, 36, -36, -36)
imglist = os.listdir(imgdir)
imgcount = len(imglist)
for i, f in enumerate(imglist):
path = os.path.join(imgdir, f)
if not os.path.isfile(path):
print("skipping non-file '%s'!" % f)
continue
if str is not bytes:
psg.EasyProgressMeter("Embedding Files", i + 1, imgcount,
"dir: " + imgdir, "file: " + f)
else:
print("embedding file '%s', (%i / %i)" % (f, i + 1, imgcount))
img = open(path, "rb").read()
doc.embeddedFileAdd(img, f, filename=f, ufilename=f, desc=f)
page = doc.newPage() # every doc needs at least one page
doc.save("all-my-pics-embedded.pdf")
t1 = mytime()
print("%g" % (t1 - t0), "sec processing time")
doc = fitz.open() # PDF with the pictures
imglist = os.listdir(imgdir) # list of them
imgcount = len(imglist) # pic count
for i, f in enumerate(imglist):
path = os.path.join(imgdir, f)
if not os.path.isfile(path):
print("skipping non-file '%s'!" % f)
continue
if str is not bytes:
psg.EasyProgressMeter(
"Inserting Images", # show our progress
i + 1,
imgcount,
"dir: " + imgdir,
"file: " + f)
else:
print("inserting file '%s', (%i / %i)" % (f, i + 1, imgcount))
try:
img = fitz.open(os.path.join(imgdir, f)) # open pic as document
rect = img[0].rect # pic dimension
pdfbytes = img.convertToPDF() # make a PDF stream
img.close() # no longer needed
imgPDF = fitz.open("pdf", pdfbytes) # open stream as PDF
page = doc.newPage(
width=rect.width, # new page with ...
height=rect.height) # pic dimension
page.showPDFpage(rect, imgPDF, 0) # image fills the page
# we may need to adjust something for CMYK pixmaps here:
return getimage(pix)
t0 = time.time()
fname = sys.argv[1]
doc = fitz.open(fname)
page_count = len(doc) # number of pages
xreflist = []
imglist = []
for pno in range(page_count):
psg.EasyProgressMeter(
"Extract Images", # show our progress
pno + 1,
page_count,
"*** Scanning Pages ***")
il = doc.getPageImageList(pno)
imglist.extend([x[0] for x in il])
for img in il:
xref = img[0]
if xref in xreflist:
continue
width = img[2]
height = img[3]
if min(width, height) <= dimlimit:
continue
pix = recoverpix(doc, img)
if type(pix) is dict: # we got a raw image
# insert header and footer
page.insertText(rect.tl, text)
page.insertText(rect.bl, "Page %i of %i" % (pno, pages))
point = rect.tl + (0, 20) # insertion point of first symbol
for i, f in enumerate(imglist):
path = os.path.join(imgdir,f)
if not os.path.isfile(path):
print("skipping non-file '%s'!" % f)
continue
if str is not bytes: # show progress meter if Python v3
psg.EasyProgressMeter("Attaching Files",
i+1, imgcount,
"dir: " + imgdir,
"file: " + f)
else:
print("attaching file '%s', (%i / %i)" % (f, i+1, imgcount))
img = open(path, "rb").read() # file content
page.addFileAnnot(point, img, filename=f) # add as attachment
point += (25, 0) # position of next symbol
if point.x >= rect.width: # beyond right limit?
point = fitz.Point(rect.x0, point.y + 35) # start next line
if point.y >= rect.height and i < imgcount -1: # beyond bottom limit?
# prepare another page
page = doc.newPage(width = width, height = height)
pno += 1
page.insertText(rect.tl, text)
def ProgressMeter():
for i in range(1, 1000):
if not sg.EasyProgressMeter('My Meter', i + 1, 1000, orientation='h'):
break
time.sleep(.01)
import PySimpleGUI as sg
import time
for i in range(1, 10):
sg.EasyProgressMeter("Test Results Meter", i+1, 10, "Test Results Meter")
time.sleep(i)
# display some file info
print("")
print(__file__,
"PDF: %s, pages: %i, objects: %i" % (fname, len(doc), lenXREF - 1))
t0 = time.time() # start the timer
smasks = [] # stores xrefs of /SMask objects
#------------------------------------------------------------------------------
# loop through PDF images
#------------------------------------------------------------------------------
for xref in range(1, lenXREF): # scan through all PDF objects
psg.EasyProgressMeter(
"Extract Images", # show our progress
xref,
lenXREF,
"*** Scanning Cross Reference ***")
if xref in smasks: # ignore smasks
continue
imgdict = doc.extractImage(xref)
if not imgdict: # not an image
continue
img_icnt += 1 # increase read images counter
smask = imgdict["smask"]
if smask > 0: # store /SMask xref
