findDuplicateSector.py

# This script reads a reference sector from the partition, and then starting at
# startSector looks for an identical sector. If one isn't found by the time it
# gets to lastSector it will give up.
#
# This script is really slow (though gets close to my HDD's maximum transfer
# rate, so at least it's efficient), if you have any idea where the copied
# sector might be, use that information and save yourself some time!

partitionName = "/dev/sda3" # <- Partition to probe                EDIT THIS!
refSector      = 1685403600 # <- Reference sector absolute offset  EDIT THIS!
startSector    = 1685403601 # <- Abs. offset to start comparison   EDIT THIS!
endSector      = 2000000000 # <- Abs. offset to end comparison     EDIT THIS!

compareSector = startSector

bytesPerSector = 512

# Open the partition in binary, read only mode
partition=open(partitionName,'rb')

# Read data in refSector
partition.seek(refSector*bytesPerSector,0)
refData=partition.read(1*bytesPerSector)
print("Data in reference sector is:\n\n" + refData + "\n\n")

# Read data at startSector
partition.seek(startSector*512,0)
compareData=partition.read(1*bytesPerSector)

print("Starting comparison with offset: " + str(startSector))

# Loop through until we find an identical sector or we get to endSector
while ((refData != compareData) and (compareSector <= endSector)):
    compareSector += 1
    compareData = partition.read(512)
    if (( compareSector % 2097152) == 0):
        print("Offset: " + str(compareSector/2097152) + " GiB, current sector: " + str(compareSector))

# Close the 'file'
partition.close()

# Tell the user the outcome...
if (compareSector == (endSector+1)):
    print("Couldn't find any sector matching reference sector :(.")
else:
    print("Sector with absolute offset " + str(compareSector-1) + " matches the reference sector! Yay!")