Binary file parsing with Python
$begingroup$
Please, can anyone advice how to rise python script speed. I know that the best way to encrease performance is to write this on C or C++, but what about Python.
The script parses Bitcoin database (blkXXXXX.dat) files directly from raw binary to txt human readable view. And I think about how to encrease the speed of processing.
Example cut from code (full code avaible here):
import os
import hashlib
def reverse(input):
L = len(input)
if (L % 2) != 0:
return None
else:
Res = ''
L = L // 2
for i in range(L):
T = input[i*2] + input[i*2+1]
Res = T + Res
T = ''
return (Res);
f = open('blk01234.dat','rb')
tmpHex = ''
fSize = os.path.getsize(t)
while f.tell() != fSize:
for j in range(4):
b = f.read(1)
b = b.encode('hex').upper()
tmpHex = b + tmpHex
tmpHex = ''
for j in range(4):
b = f.read(1)
b = b.encode('hex').upper()
tmpHex = b + tmpHex
resList.append('Block size = ' + tmpHex)
tmpHex = ''
tmpPos3 = f.tell()
while f.tell() != tmpPos3 + 80:
b = f.read(1)
b = b.encode('hex').upper()
tmpHex = tmpHex + b
tmpHex = tmpHex.decode('hex')
tmpHex = hashlib.new('sha256', tmpHex).digest()
tmpHex = hashlib.new('sha256', tmpHex).digest()
tmpHex = tmpHex.encode('hex')
tmpHex = tmpHex.upper()
tmpHex = reverse(tmpHex)
resList.append('SHA256 hash of the current block hash = ' + tmpHex)
f.seek(tmpPos3,0)
tmpHex = ''
for j in range(4):
b = f.read(1)
b = b.encode('hex').upper()
tmpHex = b + tmpHex
resList.append('Version number = ' + tmpHex)
tmpHex = ''
#.....next part of code
f.close()
f = open('blk01234.txt','w')
for j in resList:
f.write(j + 'n')
f.close()
Is this style of programming is good?
performance
New contributor
$endgroup$
add a comment |
$begingroup$
Please, can anyone advice how to rise python script speed. I know that the best way to encrease performance is to write this on C or C++, but what about Python.
The script parses Bitcoin database (blkXXXXX.dat) files directly from raw binary to txt human readable view. And I think about how to encrease the speed of processing.
Example cut from code (full code avaible here):
import os
import hashlib
def reverse(input):
L = len(input)
if (L % 2) != 0:
return None
else:
Res = ''
L = L // 2
for i in range(L):
T = input[i*2] + input[i*2+1]
Res = T + Res
T = ''
return (Res);
f = open('blk01234.dat','rb')
tmpHex = ''
fSize = os.path.getsize(t)
while f.tell() != fSize:
for j in range(4):
b = f.read(1)
b = b.encode('hex').upper()
tmpHex = b + tmpHex
tmpHex = ''
for j in range(4):
b = f.read(1)
b = b.encode('hex').upper()
tmpHex = b + tmpHex
resList.append('Block size = ' + tmpHex)
tmpHex = ''
tmpPos3 = f.tell()
while f.tell() != tmpPos3 + 80:
b = f.read(1)
b = b.encode('hex').upper()
tmpHex = tmpHex + b
tmpHex = tmpHex.decode('hex')
tmpHex = hashlib.new('sha256', tmpHex).digest()
tmpHex = hashlib.new('sha256', tmpHex).digest()
tmpHex = tmpHex.encode('hex')
tmpHex = tmpHex.upper()
tmpHex = reverse(tmpHex)
resList.append('SHA256 hash of the current block hash = ' + tmpHex)
f.seek(tmpPos3,0)
tmpHex = ''
for j in range(4):
b = f.read(1)
b = b.encode('hex').upper()
tmpHex = b + tmpHex
resList.append('Version number = ' + tmpHex)
tmpHex = ''
#.....next part of code
f.close()
f = open('blk01234.txt','w')
for j in resList:
f.write(j + 'n')
f.close()
Is this style of programming is good?
performance
New contributor
$endgroup$
add a comment |
$begingroup$
Please, can anyone advice how to rise python script speed. I know that the best way to encrease performance is to write this on C or C++, but what about Python.
The script parses Bitcoin database (blkXXXXX.dat) files directly from raw binary to txt human readable view. And I think about how to encrease the speed of processing.
Example cut from code (full code avaible here):
import os
import hashlib
def reverse(input):
L = len(input)
if (L % 2) != 0:
return None
else:
Res = ''
L = L // 2
for i in range(L):
T = input[i*2] + input[i*2+1]
Res = T + Res
T = ''
return (Res);
f = open('blk01234.dat','rb')
tmpHex = ''
fSize = os.path.getsize(t)
while f.tell() != fSize:
for j in range(4):
b = f.read(1)
b = b.encode('hex').upper()
tmpHex = b + tmpHex
tmpHex = ''
for j in range(4):
b = f.read(1)
b = b.encode('hex').upper()
tmpHex = b + tmpHex
resList.append('Block size = ' + tmpHex)
tmpHex = ''
tmpPos3 = f.tell()
while f.tell() != tmpPos3 + 80:
b = f.read(1)
b = b.encode('hex').upper()
tmpHex = tmpHex + b
tmpHex = tmpHex.decode('hex')
tmpHex = hashlib.new('sha256', tmpHex).digest()
tmpHex = hashlib.new('sha256', tmpHex).digest()
tmpHex = tmpHex.encode('hex')
tmpHex = tmpHex.upper()
tmpHex = reverse(tmpHex)
resList.append('SHA256 hash of the current block hash = ' + tmpHex)
f.seek(tmpPos3,0)
tmpHex = ''
for j in range(4):
b = f.read(1)
b = b.encode('hex').upper()
tmpHex = b + tmpHex
resList.append('Version number = ' + tmpHex)
tmpHex = ''
#.....next part of code
f.close()
f = open('blk01234.txt','w')
for j in resList:
f.write(j + 'n')
f.close()
Is this style of programming is good?
performance
New contributor
$endgroup$
Please, can anyone advice how to rise python script speed. I know that the best way to encrease performance is to write this on C or C++, but what about Python.
The script parses Bitcoin database (blkXXXXX.dat) files directly from raw binary to txt human readable view. And I think about how to encrease the speed of processing.
Example cut from code (full code avaible here):
import os
import hashlib
def reverse(input):
L = len(input)
if (L % 2) != 0:
return None
else:
Res = ''
L = L // 2
for i in range(L):
T = input[i*2] + input[i*2+1]
Res = T + Res
T = ''
return (Res);
f = open('blk01234.dat','rb')
tmpHex = ''
fSize = os.path.getsize(t)
while f.tell() != fSize:
for j in range(4):
b = f.read(1)
b = b.encode('hex').upper()
tmpHex = b + tmpHex
tmpHex = ''
for j in range(4):
b = f.read(1)
b = b.encode('hex').upper()
tmpHex = b + tmpHex
resList.append('Block size = ' + tmpHex)
tmpHex = ''
tmpPos3 = f.tell()
while f.tell() != tmpPos3 + 80:
b = f.read(1)
b = b.encode('hex').upper()
tmpHex = tmpHex + b
tmpHex = tmpHex.decode('hex')
tmpHex = hashlib.new('sha256', tmpHex).digest()
tmpHex = hashlib.new('sha256', tmpHex).digest()
tmpHex = tmpHex.encode('hex')
tmpHex = tmpHex.upper()
tmpHex = reverse(tmpHex)
resList.append('SHA256 hash of the current block hash = ' + tmpHex)
f.seek(tmpPos3,0)
tmpHex = ''
for j in range(4):
b = f.read(1)
b = b.encode('hex').upper()
tmpHex = b + tmpHex
resList.append('Version number = ' + tmpHex)
tmpHex = ''
#.....next part of code
f.close()
f = open('blk01234.txt','w')
for j in resList:
f.write(j + 'n')
f.close()
Is this style of programming is good?
performance
performance
New contributor
New contributor
New contributor
asked 3 mins ago
Norman VoltNorman Volt
1011
1011
New contributor
New contributor
add a comment |
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function () {
return StackExchange.using("mathjaxEditing", function () {
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["\$", "\$"]]);
});
});
}, "mathjax-editing");
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "196"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
Norman Volt is a new contributor. Be nice, and check out our Code of Conduct.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fcodereview.stackexchange.com%2fquestions%2f213494%2fbinary-file-parsing-with-python%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
Norman Volt is a new contributor. Be nice, and check out our Code of Conduct.
Norman Volt is a new contributor. Be nice, and check out our Code of Conduct.
Norman Volt is a new contributor. Be nice, and check out our Code of Conduct.
Norman Volt is a new contributor. Be nice, and check out our Code of Conduct.
Thanks for contributing an answer to Code Review Stack Exchange!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fcodereview.stackexchange.com%2fquestions%2f213494%2fbinary-file-parsing-with-python%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown