def extract_csv_column(input, output, column):
"""Extracts column from given CSV file. Deprecated - use extract_field."""
set_max_field_size_limit()
with smart_open(input, 'r') as input_file, smart_open(output, 'w') as output_file:
reader = csv.DictReader(input_file)
for row in reader:
output_file.write(row[column] + '\n')
def extract_csv_column_unique(input, output, column):
set_max_field_size_limit()
with smart_open(input, 'r') as input_file, smart_open(output, 'w') as output_file:
reader = csv.DictReader(input_file)
seen = set() # set for fast O(1) amortized lookup
for row in reader:
if row[column] in seen:
continue
seen.add(row[column])
output_file.write(row[column] + '\n')
def filter_items(input, output, predicate):
eval_environment = globals()
if 'datetime' in predicate:
import datetime
eval_environment['datetime'] = datetime
"""Filters given JSON lines file by predicate."""
# TODO: Add support for CSV
with smart_open(input, 'r') as input_file, smart_open(output,
'w') as output_file:
for line in input_file:
item = json.loads(line)
if eval(predicate, eval_environment, {'item': item}):
output_file.write(json.dumps(item) + '\n')
def export_contracts(batch_size,
receipts,
output,
max_workers,
provider_uri,
chain='ethereum'):
"""Exports contracts bytecode and sighashes."""
check_classic_provider_uri(chain, provider_uri)
with smart_open(receipts, 'r') as receipts_file:
contracts_iterable = (
{
"contract_address":
json.loads(receipt)["contract_address"].strip(),
"block_number": json.loads(receipt)["block_number"]
} for receipt in receipts_file
if json.loads(receipt)["contract_address"] is not None)
job = ExportContractsJob(
contracts_iterable=contracts_iterable,
batch_size=batch_size,
batch_web3_provider=ThreadLocalProxy(
lambda: get_provider_from_uri(provider_uri, batch=True)),
item_exporter=contracts_item_exporter(output),
max_workers=max_workers)
job.run()
def extract_tokens(contracts,
provider_uri,
output,
max_workers,
values_as_strings=False):
"""Extracts tokens from contracts file."""
set_max_field_size_limit()
with smart_open(contracts, 'r') as contracts_file:
if contracts.endswith('.json'):
contracts_iterable = (json.loads(line) for line in contracts_file)
else:
contracts_iterable = csv.DictReader(contracts_file)
converters = [
IntToStringItemConverter(keys=['decimals', 'total_supply'])
] if values_as_strings else []
job = ExtractTokensJob(
contracts_iterable=contracts_iterable,
web3=ThreadLocalProxy(
lambda: Web3(get_provider_from_uri(provider_uri))),
max_workers=max_workers,
item_exporter=tokens_item_exporter(output, converters))
job.run()
def get_block_range_for_date(provider_uri, date, output):
"""Outputs start and end blocks for given date."""
eos_rpc = EosRpc(provider_uri)
btc_service = BtcBlockRangeService(eos_rpc)
start_block, end_block = btc_service.get_block_range_for_date(date)
with smart_open(output, 'w') as output_file:
output_file.write('{},{}\n'.format(start_block, end_block))
def get_block_range_for_date(provider_uri, date, output, chain='ethereum'):
"""Outputs start and end blocks for given date."""
provider_uri = check_classic_provider_uri(chain, provider_uri)
provider = get_provider_from_uri(provider_uri)
web3 = Web3(provider)
eth_service = EthService(web3)
start_block, end_block = eth_service.get_block_range_for_date(date)
with smart_open(output, 'w') as output_file:
output_file.write('{},{}\n'.format(start_block, end_block))
def export_tokens(token_addresses, output, max_workers, provider_uri, chain='ethereum'):
"""Exports ERC20/ERC721 tokens."""
provider_uri = check_classic_provider_uri(chain, provider_uri)
with smart_open(token_addresses, 'r') as token_addresses_file:
job = ExportTokensJob(
token_addresses_iterable=(token_address.strip() for token_address in token_addresses_file),
web3=ThreadLocalProxy(lambda: Web3(get_provider_from_uri(provider_uri))),
item_exporter=tokens_item_exporter(output),
max_workers=max_workers)
job.run()
def get_block_range_for_date(provider_uri, date, start_hour, end_hour, output):
"""Outputs start and end blocks for given date."""
if start_hour > end_hour:
raise ValueError('end_hour should be greater than or equal to start_hour')
bitcoin_rpc = BitcoinRpc(provider_uri)
btc_service = BtcBlockRangeService(bitcoin_rpc)
start_block, end_block = btc_service.get_block_range_for_date(date, start_hour, end_hour)
with smart_open(output, 'w') as output_file:
output_file.write('{},{}\n'.format(start_block, end_block))
def export_contracts(batch_size, contract_addresses, output, max_workers, provider_uri, chain='ethereum'):
"""Exports contracts bytecode and sighashes."""
check_classic_provider_uri(chain, provider_uri)
with smart_open(contract_addresses, 'r') as contract_addresses_file:
contract_addresses = (contract_address.strip() for contract_address in contract_addresses_file
if contract_address.strip())
job = ExportContractsJob(
contract_addresses_iterable=contract_addresses,
batch_size=batch_size,
batch_web3_provider=ThreadLocalProxy(lambda: get_provider_from_uri(provider_uri, batch=True)),
item_exporter=contracts_item_exporter(output),
max_workers=max_workers)
job.run()
def extract_token_transfers(logs, batch_size, output, max_workers):
"""Extracts ERC20/ERC721 transfers from logs file."""
with smart_open(logs, 'r') as logs_file:
if logs.endswith('.json'):
logs_reader = (json.loads(line) for line in logs_file)
else:
logs_reader = csv.DictReader(logs_file)
job = ExtractTokenTransfersJob(
logs_iterable=logs_reader,
batch_size=batch_size,
max_workers=max_workers,
item_exporter=token_transfers_item_exporter(output))
job.run()
def extract_geth_traces(input, batch_size, output, max_workers):
"""Extracts geth traces from JSON lines file."""
with smart_open(input, 'r') as geth_traces_file:
if input.endswith('.json'):
traces_iterable = (json.loads(line) for line in geth_traces_file)
else:
traces_iterable = (trace
for trace in csv.DictReader(geth_traces_file))
job = ExtractGethTracesJob(traces_iterable=traces_iterable,
batch_size=batch_size,
max_workers=max_workers,
item_exporter=traces_item_exporter(output))
job.run()
def export_receipts_and_logs(batch_size, transactions, provider_uri, max_workers, receipts_output, logs_output,
chain='ethereum'):
"""Exports receipts and logs."""
provider_uri = check_classic_provider_uri(chain, provider_uri)
with smart_open(transactions, 'r') as transactions_file:
job = ExportReceiptsJob(
transaction_hashes_iterable=(json.loads(transaction)['hash'].strip() for transaction in transactions_file),
batch_size=batch_size,
batch_web3_provider=ThreadLocalProxy(lambda: get_provider_from_uri(provider_uri, batch=True)),
max_workers=max_workers,
item_exporter=receipts_and_logs_item_exporter(receipts_output, logs_output),
export_receipts=receipts_output is not None,
export_logs=logs_output is not None)
job.run()
def enrich_transactions(batch_size, provider_uri, max_workers,
transactions_input, transactions_output, chain):
"""Enrich transactions."""
with smart_open(transactions_input, 'r') as transactions_input_file:
job = EnrichTransactionsJob(
transactions_iterable=(json.loads(transaction)
for transaction in transactions_input_file),
batch_size=batch_size,
bitcoin_rpc=ThreadLocalProxy(lambda: BitcoinRpc(provider_uri)),
max_workers=max_workers,
item_exporter=blocks_and_transactions_item_exporter(
None, transactions_output),
chain=chain)
job.run()
def extract_token_transfers(logs, batch_size, output, max_workers, values_as_strings=False):
"""Extracts ERC20/ERC721 transfers from logs file."""
with smart_open(logs, 'r') as logs_file:
if logs.endswith('.json'):
logs_reader = (json.loads(line) for line in logs_file)
else:
logs_reader = csv.DictReader(logs_file)
converters = [IntToStringItemConverter(keys=['value'])] if values_as_strings else []
job = ExtractTokenTransfersJob(
logs_iterable=logs_reader,
batch_size=batch_size,
max_workers=max_workers,
item_exporter=token_transfers_item_exporter(output, converters=converters))
job.run()
def get_block_range_for_timestamps(provider_uri,
start_timestamp,
end_timestamp,
output,
chain='ethereum'):
"""Outputs start and end blocks for given timestamps."""
provider_uri = check_classic_provider_uri(chain, provider_uri)
provider = get_provider_from_uri(provider_uri)
web3 = Web3(provider)
web3.middleware_stack.inject(geth_poa_middleware, layer=0)
eth_service = EthService(web3)
start_block, end_block = eth_service.get_block_range_for_timestamps(
start_timestamp, end_timestamp)
with smart_open(output, 'w') as output_file:
output_file.write('{},{}\n'.format(start_block, end_block))
def extract_tokens(contracts, provider_uri, output, max_workers):
"""Extracts tokens from contracts file."""
set_max_field_size_limit()
with smart_open(contracts, 'r') as contracts_file:
if contracts.endswith('.json'):
contracts_iterable = (json.loads(line) for line in contracts_file)
else:
contracts_iterable = csv.DictReader(contracts_file)
job = ExtractTokensJob(
contracts_iterable=contracts_iterable,
web3=ThreadLocalProxy(lambda: Web3(get_provider_from_uri(provider_uri))),
max_workers=max_workers,
item_exporter=tokens_item_exporter(output))
job.run()
def extract_contracts(traces, batch_size, output, max_workers):
"""Extracts contracts from traces file."""
set_max_field_size_limit()
with smart_open(traces, 'r') as traces_file:
if traces.endswith('.json'):
traces_iterable = (json.loads(line) for line in traces_file)
else:
traces_iterable = csv.DictReader(traces_file)
job = ExtractContractsJob(
traces_iterable=traces_iterable,
batch_size=batch_size,
max_workers=max_workers,
item_exporter=contracts_item_exporter(output))
job.run()
def export_tokens(contracts,
output,
max_workers,
provider_uri,
chain='ethereum'):
"""Exports ERC20/ERC721 tokens."""
provider_uri = check_classic_provider_uri(chain, provider_uri)
web3 = Web3(get_provider_from_uri(provider_uri))
web3.middleware_stack.inject(geth_poa_middleware, layer=0)
with smart_open(contracts, 'r') as contracts_file:
tokens_iterable = ({
"contract_address": contract["address"].strip(),
"block_number": contract["block_number"]
} for contract in (json.loads(contract) for contract in contracts_file)
if contract["is_erc20"] or contract["is_erc721"])
job = ExportTokensJob(tokens_iterable=tokens_iterable,
web3=ThreadLocalProxy(lambda: web3),
item_exporter=tokens_item_exporter(output),
max_workers=max_workers)
job.run()
def read_last_synced_block(file):
with smart_open(file, 'r') as last_synced_block_file:
return int(last_synced_block_file.read())
def extract_field(input_file, output_file, field):
with get_item_iterable(input_file) as item_iterable, smart_open(output_file, 'w') as output:
for item in item_iterable:
output.write(item[field] + '\n')
def write_to_file(file, content):
with smart_open(file, 'w') as file_handle:
file_handle.write(content)
def export_all_common(partitions, output_dir, provider_uri, max_workers,
batch_size):
for batch_start_block, batch_end_block, partition_dir in partitions:
# # # start # # #
start_time = time()
padded_batch_start_block = str(batch_start_block).zfill(8)
padded_batch_end_block = str(batch_end_block).zfill(8)
block_range = '{padded_batch_start_block}-{padded_batch_end_block}'.format(
padded_batch_start_block=padded_batch_start_block,
padded_batch_end_block=padded_batch_end_block,
)
file_name_suffix = '{padded_batch_start_block}_{padded_batch_end_block}'.format(
padded_batch_start_block=padded_batch_start_block,
padded_batch_end_block=padded_batch_end_block,
)
# # # blocks_and_transactions # # #
blocks_output_dir = '{output_dir}/blocks{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(blocks_output_dir), exist_ok=True)
transactions_output_dir = '{output_dir}/transactions{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(transactions_output_dir), exist_ok=True)
blocks_file = '{blocks_output_dir}/blocks_{file_name_suffix}.csv'.format(
blocks_output_dir=blocks_output_dir,
file_name_suffix=file_name_suffix,
)
transactions_file = '{transactions_output_dir}/transactions_{file_name_suffix}.csv'.format(
transactions_output_dir=transactions_output_dir,
file_name_suffix=file_name_suffix,
)
logger.info('Exporting blocks {block_range} to {blocks_file}'.format(
block_range=block_range,
blocks_file=blocks_file,
))
logger.info(
'Exporting transactions from blocks {block_range} to {transactions_file}'
.format(
block_range=block_range,
transactions_file=transactions_file,
))
job = ExportBlocksJob(
start_block=batch_start_block,
end_block=batch_end_block,
batch_size=batch_size,
batch_web3_provider=ThreadLocalProxy(
lambda: get_provider_from_uri(provider_uri, batch=True)),
max_workers=max_workers,
item_exporter=blocks_and_transactions_item_exporter(
blocks_file, transactions_file),
export_blocks=blocks_file is not None,
export_transactions=transactions_file is not None)
job.run()
# # # token_transfers # # #
token_transfers_file = None
if is_log_filter_supported(provider_uri):
token_transfers_output_dir = '{output_dir}/token_transfers{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(token_transfers_output_dir),
exist_ok=True)
token_transfers_file = '{token_transfers_output_dir}/token_transfers_{file_name_suffix}.csv'.format(
token_transfers_output_dir=token_transfers_output_dir,
file_name_suffix=file_name_suffix,
)
logger.info(
'Exporting ERC20 transfers from blocks {block_range} to {token_transfers_file}'
.format(
block_range=block_range,
token_transfers_file=token_transfers_file,
))
job = ExportTokenTransfersJob(
start_block=batch_start_block,
end_block=batch_end_block,
batch_size=batch_size,
web3=ThreadLocalProxy(
lambda: Web3(get_provider_from_uri(provider_uri))),
item_exporter=token_transfers_item_exporter(
token_transfers_file),
max_workers=max_workers)
job.run()
# # # receipts_and_logs # # #
cache_output_dir = '{output_dir}/.tmp{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(cache_output_dir), exist_ok=True)
transaction_hashes_file = '{cache_output_dir}/transaction_hashes_{file_name_suffix}.csv'.format(
cache_output_dir=cache_output_dir,
file_name_suffix=file_name_suffix,
)
logger.info(
'Extracting hash column from transaction file {transactions_file}'.
format(transactions_file=transactions_file, ))
extract_csv_column_unique(transactions_file, transaction_hashes_file,
'hash')
receipts_output_dir = '{output_dir}/receipts{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(receipts_output_dir), exist_ok=True)
logs_output_dir = '{output_dir}/logs{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(logs_output_dir), exist_ok=True)
receipts_file = '{receipts_output_dir}/receipts_{file_name_suffix}.csv'.format(
receipts_output_dir=receipts_output_dir,
file_name_suffix=file_name_suffix,
)
logs_file = '{logs_output_dir}/logs_{file_name_suffix}.csv'.format(
logs_output_dir=logs_output_dir,
file_name_suffix=file_name_suffix,
)
logger.info(
'Exporting receipts and logs from blocks {block_range} to {receipts_file} and {logs_file}'
.format(
block_range=block_range,
receipts_file=receipts_file,
logs_file=logs_file,
))
with smart_open(transaction_hashes_file, 'r') as transaction_hashes:
job = ExportReceiptsJob(
transaction_hashes_iterable=(
transaction_hash.strip()
for transaction_hash in transaction_hashes),
batch_size=batch_size,
batch_web3_provider=ThreadLocalProxy(
lambda: get_provider_from_uri(provider_uri, batch=True)),
max_workers=max_workers,
item_exporter=receipts_and_logs_item_exporter(
receipts_file, logs_file),
export_receipts=receipts_file is not None,
export_logs=logs_file is not None)
job.run()
# # # contracts # # #
contract_addresses_file = '{cache_output_dir}/contract_addresses_{file_name_suffix}.csv'.format(
cache_output_dir=cache_output_dir,
file_name_suffix=file_name_suffix,
)
logger.info(
'Extracting contract_address from receipt file {receipts_file}'.
format(receipts_file=receipts_file))
extract_csv_column_unique(receipts_file, contract_addresses_file,
'contract_address')
contracts_output_dir = '{output_dir}/contracts{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(contracts_output_dir), exist_ok=True)
contracts_file = '{contracts_output_dir}/contracts_{file_name_suffix}.csv'.format(
contracts_output_dir=contracts_output_dir,
file_name_suffix=file_name_suffix,
)
logger.info(
'Exporting contracts from blocks {block_range} to {contracts_file}'
.format(
block_range=block_range,
contracts_file=contracts_file,
))
with smart_open(contract_addresses_file,
'r') as contract_addresses_file:
contract_addresses = (
contract_address.strip()
for contract_address in contract_addresses_file
if contract_address.strip())
job = ExportContractsJob(
contract_addresses_iterable=contract_addresses,
batch_size=batch_size,
batch_web3_provider=ThreadLocalProxy(
lambda: get_provider_from_uri(provider_uri, batch=True)),
item_exporter=contracts_item_exporter(contracts_file),
max_workers=max_workers)
job.run()
# # # tokens # # #
if token_transfers_file is not None:
token_addresses_file = '{cache_output_dir}/token_addresses_{file_name_suffix}'.format(
cache_output_dir=cache_output_dir,
file_name_suffix=file_name_suffix,
)
logger.info(
'Extracting token_address from token_transfers file {token_transfers_file}'
.format(token_transfers_file=token_transfers_file, ))
extract_csv_column_unique(token_transfers_file,
token_addresses_file, 'token_address')
tokens_output_dir = '{output_dir}/tokens{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(tokens_output_dir), exist_ok=True)
tokens_file = '{tokens_output_dir}/tokens_{file_name_suffix}.csv'.format(
tokens_output_dir=tokens_output_dir,
file_name_suffix=file_name_suffix,
)
logger.info(
'Exporting tokens from blocks {block_range} to {tokens_file}'.
format(
block_range=block_range,
tokens_file=tokens_file,
))
with smart_open(token_addresses_file, 'r') as token_addresses:
job = ExportTokensJob(
token_addresses_iterable=(
token_address.strip()
for token_address in token_addresses),
web3=ThreadLocalProxy(
lambda: Web3(get_provider_from_uri(provider_uri))),
item_exporter=tokens_item_exporter(tokens_file),
max_workers=max_workers)
job.run()
# # # finish # # #
shutil.rmtree(os.path.dirname(cache_output_dir))
end_time = time()
time_diff = round(end_time - start_time, 5)
logger.info(
'Exporting blocks {block_range} took {time_diff} seconds'.format(
block_range=block_range,
time_diff=time_diff,
))
def export_all(chain, partitions, output_dir, provider_uri, max_workers,
batch_size, enrich):
for batch_start_block, batch_end_block, partition_dir, *args in partitions:
# # # start # # #
start_time = time()
padded_batch_start_block = str(batch_start_block).zfill(8)
padded_batch_end_block = str(batch_end_block).zfill(8)
block_range = '{padded_batch_start_block}-{padded_batch_end_block}'.format(
padded_batch_start_block=padded_batch_start_block,
padded_batch_end_block=padded_batch_end_block,
)
file_name_suffix = '{padded_batch_start_block}_{padded_batch_end_block}'.format(
padded_batch_start_block=padded_batch_start_block,
padded_batch_end_block=padded_batch_end_block,
)
# # # blocks_and_transactions # # #
blocks_output_dir = '{output_dir}/blocks{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(blocks_output_dir), exist_ok=True)
transactions_output_dir = '{output_dir}/transactions{partition_dir}'.format(
output_dir=output_dir,
partition_dir=partition_dir,
)
os.makedirs(os.path.dirname(transactions_output_dir), exist_ok=True)
blocks_file = '{blocks_output_dir}/blocks_{file_name_suffix}.json'.format(
blocks_output_dir=blocks_output_dir,
file_name_suffix=file_name_suffix,
)
transactions_file = '{transactions_output_dir}/transactions_{file_name_suffix}.json'.format(
transactions_output_dir=transactions_output_dir,
file_name_suffix=file_name_suffix,
)
enriched_transactions_file = '{transactions_output_dir}/enriched_transactions_{file_name_suffix}.json'.format(
transactions_output_dir=transactions_output_dir,
file_name_suffix=file_name_suffix,
)
logger.info('Exporting blocks {block_range} to {blocks_file}'.format(
block_range=block_range,
blocks_file=blocks_file,
))
logger.info(
'Exporting transactions from blocks {block_range} to {transactions_file}'
.format(
block_range=block_range,
transactions_file=transactions_file,
))
job = ExportBlocksJob(
chain=chain,
start_block=batch_start_block,
end_block=batch_end_block,
batch_size=batch_size,
bitcoin_rpc=ThreadLocalProxy(lambda: BitcoinRpc(provider_uri)),
max_workers=max_workers,
item_exporter=blocks_and_transactions_item_exporter(
blocks_file, transactions_file),
export_blocks=blocks_file is not None,
export_transactions=transactions_file is not None)
job.run()
if enrich == True:
with smart_open(transactions_file, 'r') as transactions_file:
job = EnrichTransactionsJob(
transactions_iterable=(
json.loads(transaction)
for transaction in transactions_file),
batch_size=batch_size,
bitcoin_rpc=ThreadLocalProxy(
lambda: BitcoinRpc(provider_uri)),
max_workers=max_workers,
item_exporter=blocks_and_transactions_item_exporter(
None, enriched_transactions_file),
chain=chain)
job.run()
if args is not None and len(args) > 0:
date = args[0]
logger.info('Filtering blocks {blocks_file} by date {date}'.format(
blocks_file=blocks_file,
date=date,
))
def filter_by_date(item, field):
return datetime.datetime.fromtimestamp(item[field]).astimezone(datetime.timezone.utc) \
.strftime('%Y-%m-%d') == date.strftime('%Y-%m-%d')
filtered_blocks_file = blocks_file + '.filtered'
filter_items(blocks_file, filtered_blocks_file,
lambda item: filter_by_date(item, 'timestamp'))
shutil.move(filtered_blocks_file, blocks_file)
logger.info(
'Filtering transactions {transactions_file} by date {date}'.
format(
transactions_file=transactions_file,
date=date,
))
filtered_transactions_file = transactions_file + '.filtered'
filter_items(transactions_file, filtered_transactions_file,
lambda item: filter_by_date(item, 'block_timestamp'))
shutil.move(filtered_transactions_file, transactions_file)
# # # finish # # #
end_time = time()
time_diff = round(end_time - start_time, 5)
logger.info(
'Exporting blocks {block_range} took {time_diff} seconds'.format(
block_range=block_range,
time_diff=time_diff,
))
def get_keccak_hash(input_string, output):
"""Outputs 32-byte Keccak hash of given string."""
hash = keccak(text=input_string)
with smart_open(output, 'w') as output_file:
output_file.write('0x{}\n'.format(hash.hex()))
def write_last_synced_block(file, last_synced_block):
with smart_open(file, 'w') as last_synced_block_file:
return last_synced_block_file.write(str(last_synced_block) + '\n')
