Question

我有一个用于执行sql查询的python脚本。问题是我的VM仅具有512mbs的RAM，并且某些sql查询的RAM占用过多，因此内核会自动终止该脚本。如何使此代码的RAM效率更高？一种想法是更积极地将数据写到磁盘上，而不是将其存储在RAM中。有谁知道一个简单的实现吗？非常感谢您的帮助！

代码

from __future__ import print_function

try:
    import psycopg2
except ImportError:
    raise ImportError('\n\033[33mpsycopg2 library missing. pip install psycopg2\033[1;m\n')
    sys.exit(1)


import re
import sys
import json
import pprint
import time

outfilepath = "crtsh_output/crtsh_flat_file"

DB_HOST = 'crt.sh'
DB_NAME = 'certwatch'
DB_USER = 'guest'

# DELAY = 0


def connect_to_db():
    filepath = 'forager.txt'
    with open(filepath) as fp:
        unique_domains = ''
        try:
            conn = psycopg2.connect("dbname={0} user={1} host={2}".format(DB_NAME, DB_USER, DB_HOST))
            cursor = conn.cursor()
            for cnt, domain_name in enumerate(fp):
                print("Line {}: {}".format(cnt, domain_name))
                print(domain_name)
                domain_name = domain_name.rstrip()

                cursor.execute('''SELECT c.id, x509_commonName(c.certificate), x509_issuerName(c.certificate), x509_notBefore(c.certificate), x509_notAfter(c.certificate), x509_issuerName(c.certificate), x509_keyAlgorithm(c.certificate), x509_keySize(c.certificate), x509_publicKeyMD5(c.certificate), x509_publicKey(c.certificate), x509_rsaModulus(c.certificate), x509_serialNumber(c.certificate), x509_signatureHashAlgorithm(c.certificate), x509_signatureKeyAlgorithm(c.certificate), x509_subjectName(c.certificate), x509_name(c.certificate), x509_name_print(c.certificate), x509_commonName(c.certificate), x509_subjectKeyIdentifier(c.certificate), x509_extKeyUsages(c.certificate), x509_certPolicies(c.certificate), x509_canIssueCerts(c.certificate), x509_getPathLenConstraint(c.certificate), x509_altNames(c.certificate), x509_altNames_raw(c.certificate), x509_cRLDistributionPoints(c.certificate), x509_authorityInfoAccess(c.certificate), x509_print(c.certificate), x509_anyNamesWithNULs(c.certificate), x509_extensions(c.certificate), x509_tbscert_strip_ct_ext(c.certificate), x509_hasROCAFingerprint(c.certificate)
                FROM certificate c, certificate_identity ci WHERE
                c.id= ci.certificate_id AND ci.name_type = 'dNSName' AND lower(ci.name_value) =
                lower(%s) AND x509_notAfter(c.certificate) > statement_timestamp()''', (domain_name,))


                unique_domains = cursor.fetchall()

                pprint.pprint(unique_domains)

                outfilepath = "crtsh2" + ".json"
                with open(outfilepath, 'a') as outfile:
                        outfile.write(json.dumps(unique_domains, sort_keys=True, indent=4, default=str, ensure_ascii = False))
        #        time.sleep(DELAY)
        #        conn.rollback()


        except Exception as error:
        #    print("\n\033[1;31m[!] Unable to connect to the database\n\033[1;m")
        #    if tries < 3:
                time.sleep(1) # give the DB a bit to recover if you want
        #        connect_to_db(tries+1)
        #    else:
                raise error

if __name__ == "__main__":
    connect_to_db()

Answer 1

当您需要读取一个非常大的文件时，可以逐行读取它，而不是将整个文件加载到RAM中。

此处可以应用相同的逻辑。

您可以使用SQL TOP, LIMIT or ROWNUM Clause。另外，this thread可能会有帮助。

即使可以做到，处理整个表也可能要花费很多时间。这是一个权衡。

如何使查询sql数据库的python脚本的内存效率更高？

1 个答案: