Extract genesis block raw TX data

Question

RPC does not return the raw transaction for the genesis block. I need to get this data for other coins to be able to add them to ABE.

https://github.com/bitcoin-abe/bitcoin-abe/blob/master/Abe/genesis_tx.py

As the RPC does not return it I presume that I need to somehow parse the actual blockchain files to extract it but have no idea how.

Any advice on getting the raw hex TX for any coin?

Answer 1

1. take genesis block
2. skip first 80 bytes
3. convert rest bytes to hex
4. that's all

Answer 2

Of course you can :) Bitcoin full node keeps a blockchain database in local machine.
Here is a step-by-step instruction to get the genesis transaction information.

Find block data file.s In mac, it locates at "~/Library/Application Support/Bitcoin/blocks/blkxxxxx.dat"

Use the given following code to decode the genesis block

Now got every detail about the genesis block and the coinbase transaction in genesis block, including tx_version, tx_input_num, tx_prev_output, script_length, scriptsig, sequence, tx_output_num ...

import struct # make conversation between Python values and C structsrepresented as Python strings
import StringIO # Reads and writes a string buffer
import mmap # mutable string

class BCDataStream(object):
  def __init__(self):
    self.input = None
    self.read_cursor = 0

  def clear(self):
    self.input = None
    self.read_cursor = 0

  def write(self, bytes):  # Initialize with string of bytes
    if self.input is None:
      self.input = bytes
    else:
      self.input += bytes

  def map_file(self, file, start):  # Initialize with bytes from file
    self.input = mmap.mmap(file.fileno(), 0, access=mmap.ACCESS_READ)
    self.read_cursor = start
  def seek_file(self, position):
    self.read_cursor = position
  def close_file(self):
    self.input.close()

  def read_string(self):
    # Strings are encoded depending on length:
    # 0 to 252 :  1-byte-length followed by bytes (if any)
    # 253 to 65,535 : byte'253' 2-byte-length followed by bytes
    # 65,536 to 4,294,967,295 : byte '254' 4-byte-length followed by bytes
    # ... and the Bitcoin client is coded to understand:
    # greater than 4,294,967,295 : byte '255' 8-byte-length followed by bytes of string
    # ... but I don't think it actually handles any strings that big.
    if self.input is None:
      raise SerializationError("call write(bytes) before trying to deserialize")

    try:
      length = self.read_compact_size()
    except IndexError:
      raise SerializationError("attempt to read past end of buffer")

    return self.read_bytes(length)

  def write_string(self, string):
    # Length-encoded as with read-string
    self.write_compact_size(len(string))
    self.write(string)

  def read_bytes(self, length):
    try:
      result = self.input[self.read_cursor:self.read_cursor+length]
      self.read_cursor += length
      return result
    except IndexError:
      raise SerializationError("attempt to read past end of buffer")

    return ''

  def read_boolean(self): return self.read_bytes(1)[0] != chr(0)
  def read_int16  (self): return self._read_num('<h')
  def read_uint16 (self): return self._read_num('<H')
  def read_int32  (self): return self._read_num('<i')
  def read_uint32 (self): return self._read_num('<I')
  def read_int64  (self): return self._read_num('<q')
  def read_uint64 (self): return self._read_num('<Q')

  def write_boolean(self, val): return self.write(chr(1) if val else chr(0))
  def write_int16  (self, val): return self._write_num('<h', val)
  def write_uint16 (self, val): return self._write_num('<H', val)
  def write_int32  (self, val): return self._write_num('<i', val)
  def write_uint32 (self, val): return self._write_num('<I', val)
  def write_int64  (self, val): return self._write_num('<q', val)
  def write_uint64 (self, val): return self._write_num('<Q', val)

  def read_compact_size(self):
    size = ord(self.input[self.read_cursor])
    self.read_cursor += 1
    if size == 253:
      size = self._read_num('<H')
    elif size == 254:
      size = self._read_num('<I')
    elif size == 255:
      size = self._read_num('<Q')
    return size

  def write_compact_size(self, size):
    if size < 0:
      raise SerializationError("attempt to write size < 0")
    elif size < 253:
       self.write(chr(size))
    elif size < 2**16:
      self.write('\xfd')
      self._write_num('<H', size)
    elif size < 2**32:
      self.write('\xfe')
      self._write_num('<I', size)
    elif size < 2**64:
      self.write('\xff')
      self._write_num('<Q', size)

  def _read_num(self, format):
    (i,) = struct.unpack_from(format, self.input, self.read_cursor)
    self.read_cursor += struct.calcsize(format)
    return i

  def _write_num(self, format, num):
    s = struct.pack(format, num)
    self.write(s)


def import_blkdat():
    pass



ds = BCDataStream()
file = open("/Users/junton/Library/Application Support/Bitcoin/blocks/blk00000.dat", "rb")
ds.map_file(file, 0)

# Read file
# https://bitcoin.org/en/developer-reference#block-headers
# https://en.bitcoin.it/wiki/Protocol_specification#block
magic            = ds.read_bytes(4).encode('hex')
block_size       = int(ds.read_bytes(4).encode('hex'), 16)
version          = ds.read_bytes(4).encode('hex')
prev_header_hash = ds.read_bytes(32).encode('hex')
merkle_root_hash = ds.read_bytes(32).encode('hex')
timestamp        = ds.read_bytes(4).encode('hex')
nBits            = ds.read_bytes(4).encode('hex')
nonce            = ds.read_bytes(4).encode('hex')

num_of_transaction = ds.read_bytes(1).encode('hex')
tx_version         = ds.read_bytes(4).encode('hex')
tx_input           = ds.read_bytes(1).encode('hex')
tx_prev_output     = ds.read_bytes(36).encode('hex')
script_length      = ds.read_bytes(1).encode('hex')
scriptsig          = ds.read_bytes(int((script_length), 16)).encode('hex')
sequence           = ds.read_bytes(4).encode('hex')
tx_output          = ds.read_bytes(1).encode('hex')
BTC_num            = ds.read_bytes(8).encode('hex')
pk_script_len      = ds.read_bytes(1).encode('hex')
pk_script          = ds.read_bytes(int(pk_script_len, 16)).encode('hex')
lock_time          = ds.read_bytes(4).encode('hex')


print 'magic: '       + magic
print 'block_size: '  + str(block_size)
print 'version: '     + version
print 'prevHash: '    + prev_header_hash
print 'merkle_root: ' + merkle_root_hash
print 'timestamp: '   + timestamp
print 'nBits: '       + nBits
print 'nonce: '       + nonce

print '--------------------- Transaction Details: ---------------------'
print 'num_of_transaction: ' + num_of_transaction
print 'tx_version: ' + tx_version
print 'tx_input_num: ' + tx_input
print 'tx_prev_output: ' + tx_prev_output
print 'script_length: ' + script_length
print 'scriptsig: ' + scriptsig
print 'sequence: ' + sequence
print 'tx_ouput_num: ' + tx_output
print 'BTC_num: ' + BTC_num
print 'pk_script_len: ' + pk_script_len
print 'pk_script: ' + pk_script
print 'lock_time: ' + lock_time

ds.close_file()

Answer 3

The Genesis Block and it's related transaction are generated by the Bitcoin Core client using this section of code. I do not know if it is actually stored on disk.

I also have it recreated in JSON form on Github

/**
 * Build the genesis block. Note that the output of its generation
 * transaction cannot be spent since it did not originally exist in the
 * database.
 *
 * CBlock(hash=000000000019d6, ver=1, hashPrevBlock=00000000000000, hashMerkleRoot=4a5e1e, nTime=1231006505, nBits=1d00ffff, nNonce=2083236893, vtx=1)
 *   CTransaction(hash=4a5e1e, ver=1, vin.size=1, vout.size=1, nLockTime=0)
 *     CTxIn(COutPoint(000000, -1), coinbase 04ffff001d0104455468652054696d65732030332f4a616e2f32303039204368616e63656c6c6f72206f6e206272696e6b206f66207365636f6e64206261696c6f757420666f722062616e6b73)
 *     CTxOut(nValue=50.00000000, scriptPubKey=0x5F1DF16B2B704C8A578D0B)
 *   vMerkleTree: 4a5e1e
 */
const char* pszTimestamp = "The Times 03/Jan/2009 Chancellor on brink of second bailout for banks";
CMutableTransaction txNew;
txNew.vin.resize(1);
txNew.vout.resize(1);
txNew.vin[0].scriptSig = CScript() << 486604799 << CScriptNum(4) << vector<unsigned char>((const unsigned char*)pszTimestamp, (const unsigned char*)pszTimestamp + strlen(pszTimestamp));
txNew.vout[0].nValue = 50 * COIN;
txNew.vout[0].scriptPubKey = CScript() << ParseHex("04678afdb0fe5548271967f1a67130b7105cd6a828e03909a67962e0ea1f61deb649f6bc3f4cef38c4f35504e51ec112de5c384df7ba0b8d578a4c702b6bf11d5f") << OP_CHECKSIG;
genesis.vtx.push_back(txNew);
genesis.hashPrevBlock.SetNull();
genesis.hashMerkleRoot = genesis.BuildMerkleTree();
genesis.nVersion = 1;
genesis.nTime    = 1231006505;
genesis.nBits    = 0x1d00ffff;
genesis.nNonce   = 2083236893;

consensus.hashGenesisBlock = genesis.GetHash();
assert(consensus.hashGenesisBlock == uint256S("0x000000000019d6689c085ae165831e934ff763ae46a2a6c172b3f1b60a8ce26f"));
assert(genesis.hashMerkleRoot == uint256S("0x4a5e1e4baab89f3a32518a88c31bc87f618f76673e2cc77ab2127b7afdeda33b"));