コード例 #1
0
def scrape_all_users(mongo, quick=False):
    """
    Scrape all existing users
    and insert/update their entries in Accounts collection.
    """
    steem = Steem()
    s = Settings(mongo)
    quick = False  # TODO: remove temporary override

    account_checkpoint = s.account_checkpoint(quick)
    if account_checkpoint:
        usernames = list(get_usernames_batch(account_checkpoint, steem))
    else:
        usernames = list(get_usernames_batch(steem))

    for username in usernames:
        update_account(mongo, username, load_extras=quick)
        if not quick:
            update_account_ops(mongo, username)
        s.set_account_checkpoint(username, quick)
        log.info('Updated @%s' % username)

    # this was the last batch
    if account_checkpoint and len(usernames) < 1000:
        s.set_account_checkpoint(-1, quick)
コード例 #2
0
def scrape_all_users(mongo, quick=False):
    """
    Scrape all existing users
    and insert/update their entries in Accounts collection.

    Ideally, this would only need to run once, because "scrape_accounts"
    takes care of accounts that need to be updated in each block.
    """
    steem = Steem()
    indexer = Indexer(mongo)

    account_checkpoint = indexer.get_checkpoint('accounts')
    usernames = myAccounts()
    # if account_checkpoint:
    #     usernames = list(get_usernames_batch(account_checkpoint, steem))
    # else:
    #     usernames = list(get_usernames_batch(steem))

    for username in usernames:
        log.info('Updating @%s' % username)
        update_account(mongo, username, load_extras=True)
        if quick:
            update_account_ops_quick(mongo, username)
        else:
            update_account_ops(mongo, username)
        indexer.set_checkpoint('accounts', username)
        log.info('Updated @%s' % username)

    # this was the last batch
    if account_checkpoint and len(usernames) < 1000:
        indexer.set_checkpoint('accounts', -1)
コード例 #3
0
ファイル: tasks.py プロジェクト: svk31/steemdata-mongo
def batch_update_async(batch_items: dict):
    # todo break this batch into posts and account updates

    # if we're lagging by a large margin, don't bother updating accounts
    lag = time_delta(find_latest_item(mongo, 'Posts', 'created'))
    if lag > 1000:
        return

    if use_multi_threading:
        with log_exceptions():
            thread_multi(
                fn=update_account,
                fn_args=[mongo, None],
                dep_args=batch_items['accounts_light'],
                fn_kwargs=dict(load_extras=False),
                max_workers=num_threads,
            )
            thread_multi(
                fn=update_account_ops_quick,
                fn_args=[mongo, None],
                dep_args=batch_items['accounts_light'],
                fn_kwargs=None,
                max_workers=num_threads,
            )
    else:
        for account_name in batch_items['accounts_light']:
            with log_exceptions():
                update_account(mongo, account_name, load_extras=False)
                update_account_ops_quick(mongo, account_name)

    if use_multi_threading:
        with log_exceptions():
            thread_multi(
                fn=update_account,
                fn_args=[mongo, None],
                dep_args=batch_items['accounts'],
                fn_kwargs=dict(load_extras=True),
                max_workers=num_threads,
            )
            thread_multi(
                fn=update_account_ops_quick,
                fn_args=[mongo, None],
                dep_args=batch_items['accounts'],
                fn_kwargs=None,
                max_workers=num_threads,
            )
    else:
        for account_name in batch_items['accounts']:
            with log_exceptions():
                update_account(mongo, account_name, load_extras=True)
                update_account_ops_quick(mongo, account_name)
コード例 #4
0
def scrape_all_users(mongo, steem=None):
    """Scrape all existing users and insert/update their entries in Accounts collection."""
    s = Settings(mongo)

    account_checkpoint = s.account_checkpoint()
    if account_checkpoint:
        usernames = list(get_usernames_batch(account_checkpoint, steem))
    else:
        usernames = list(get_usernames_batch(steem))

    for username in usernames:
        update_account(mongo, steem, username, load_extras=True)
        update_account_ops(mongo, steem, username)
        s.set_account_checkpoint(username)
        print('Updated @%s' % username)

    # this was the last batch
    if account_checkpoint and len(usernames) < 1000:
        s.set_account_checkpoint(-1)
コード例 #5
0
ファイル: scraper.py プロジェクト: avral/golosdata-mongo
def scrape_all_users(mongo, quick=False):
    """Scrape all existing users and insert/update their entries in Accounts collection."""
    steem = Steem()
    s = Settings(mongo)

    account_checkpoint = s.account_checkpoint(quick)
    if account_checkpoint:
        usernames = list(get_usernames_batch(account_checkpoint, steem))
    else:
        usernames = list(get_usernames_batch(steem))

    for username in usernames:
        # Some errors in golos blockchain
        with suppress(AccountDoesNotExistsException):
            update_account(mongo, username, load_extras=quick)
            if not quick:
                update_account_ops(mongo, username)
            s.set_account_checkpoint(username, quick)
            log.info('Updated @%s' % username)

    # this was the last batch
    if account_checkpoint and len(usernames) < 1000:
        s.set_account_checkpoint(-1, quick)
コード例 #6
0
ファイル: tasks.py プロジェクト: avral/golosdata-mongo
def batch_update_async(batch_items: dict):
    # todo break this batch into posts and account updates
    lag = time_delta(find_latest_item(mongo, 'Posts', 'created'))

    if lag > 1000:
        return

    for identifier in batch_items['comments']:
        with log_exceptions():
            upsert_comment_chain(mongo, identifier, recursive=True)

    # if we're lagging by a large margin, don't bother updating accounts
    if lag > 500:
        return

    for account_name in batch_items['accounts_light']:
        with log_exceptions():
            update_account(mongo, account_name, load_extras=False)
            update_account_ops_quick(mongo, account_name)
    for account_name in batch_items['accounts']:
        with log_exceptions():
            update_account(mongo, account_name,
                           load_extras=True)  # should be True
            update_account_ops_quick(mongo, account_name)
コード例 #7
0
ファイル: parser.py プロジェクト: d-trip/dtrip-mongo
def stream(BLOCK_NUM=None):
    if BLOCK_NUM is None:
        BLOCK_NUM = get_check_point('last_block') or get_current_block_num()

    print(f'START STREAMING FROM BLOCK: {BLOCK_NUM}')
    for op in blockchain.stream(start_block=BLOCK_NUM):
        op_type = op['type']

        def construct_identifier():
            return '@%s/%s' % (
                op.get('author', op.get('comment_author')),
                op.get('permlink', op.get('comment_permlink')),
            )

        if op_type in ['account_create',
                       'create_claimed_account',
                       'account_create_with_delegation']:
            update_account(op['creator'])
            update_account(op['new_account_name'])

        elif op_type in ['author_reward', 'comment']:
            update_account(op['author'])

            if op_type == 'comment':
                swm_tag = get_swm_tag(op['body'])

                if swm_tag:
                    try:
                        update_swm_post(construct_identifier(), swm_tag)
                    except NoSWMTag:
                        logging.exception('Update swm in parser err')

        elif op_type == 'account_update':
            update_account(op['account'])

        # Update state
        if op['block_num'] != BLOCK_NUM:
            set_check_point('last_block', op['block_num'])
            BLOCK_NUM = op['block_num']
コード例 #8
0
def test():
    m = MongoStorage()
    with timeit():
        update_account(m, Steem(), 'furion', load_extras=False)
コード例 #9
0
ファイル: tasks.py プロジェクト: bue-twitter/steemdata-mongo
def update_account_async(account_name):
    update_account(mongo, stm, account_name, load_extras=False)
    update_account_ops_quick(mongo, stm, account_name)