python - 如何在 postgresql 中进行分页？

Question

我有一个 python 脚本，我正在使用它来进行 sql 查询。问题是我的虚拟机只有 2GB 的 RAM，一些 sql 查询的 RAM 太密集，因此内核会自动终止脚本。我怎样才能使这段代码更有效地使用 RAM？我想在我的 postgres sql 代码中实现分页。我该怎么做？有谁知道一个简单的实现吗？非常感谢您的帮助!

更新代码

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():
    start = 0
    offset = 10
    flag = True
    while flag:
        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()
                cursor.itersize = 10000
                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,))


                # query db with start and offset
                unique_domains = cursor.fetchall()
                if not unique_domains:
                    flag = False
                else:
                        # do processing with your data

                    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))
                    offset += limit


            except Exception as error:
                print(str(error))

if __name__ == "__main__":
    connect_to_db()

Answer 1

可能是这样的:

limit = 10
offset = 0
flag = True
while flag:
    # query db with start and offset, example: select * from domains limit %start% offset %offset%
    unique_domains = cursor.fetchall()
    if not unique_domains:
        flag = False
    else:
        # do processing with your data
        offset += limit