Question

我有一个应该执行SQL查询的python脚本。但是，脚本未写入JSON文件，当我打开JSON文件时，该脚本为空。但是，脚本运行时我没有出现任何错误。我尝试修复此错误无济于事。非常感谢您的帮助！我添加了certificate_store = cursor.fetchall（），但即使添加也似乎无法修复我的代码。

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
import psycopg2.extras

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'
        print('am i stuck')
        with open(filepath, "at+") as fp, open(outfilepath, "wt+") as outfile:
            try:
                for cnt, domain_name in enumerate(fp):
                    print("Line {}: {}".format(cnt, domain_name))
                    print(domain_name)
                    domain_name = domain_name.rstrip()

                    SQL = '''
                        SELECT c.id, x509_commonName(c.certificate) as common_name,
                              x509_issuerName(c.certificate) as issuer_name,
                              x509_notBefore(c.certificate) as not_before,
                              x509_notAfter(c.certificate) as not_after,
                              x509_keyAlgorithm(c.certificate) as key_algorithm,
                              x509_keySize(c.certificate) as key_size,
                              x509_serialNumber(c.certificate) as serial_number,
                              x509_signatureHashAlgorithm(c.certificate) as signature_hash_algorithm,
                              x509_signatureKeyAlgorithm(c.certificate) as signature_key_algorithm,
                              x509_subjectName(c.certificate) as subject_name,
                              x509_name(c.certificate) as name,
                              x509_altNames(c.certificate) as alt_names
                        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()
                        '''
                    with psycopg2.connect("dbname=certwatch user=guest host=crt.sh".format(DB_NAME, DB_USER, DB_HOST)) as conn:
                        cursor = conn.cursor(cursor_factory=psycopg2.extras.NamedTupleCursor)
                        cursor.execute(SQL, (domain_name,))

                        certificate_store = cursor.fetchall()
                        for certificate in certificate_store:
                            print(certificate.id)
                            print(certificate.common_name)
                            print(certificate.issuer_name)
                            outfile.write(json.dumps(certificate, sort_keys=True, indent=4, default=str, ensure_ascii=False))


                # 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)


                #        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

写入文件的行：

outfile.write(...)

受到if条件的保护：

if not unique_domains:
    flag = False                    
else:
    ....
    outfile.write(...)

因此unique_domains必须为True。

但是你的台词

unique_domains = cursor.fetchall()

不是不是在数据库with条件的块内：

with psycopg2.connect("dbname=certwatch user=guest host=crt.sh".format(DB_NAME, DB_USER, DB_HOST)) as conn:

您还已经获取了（并在打印后丢弃了）

中的记录

for certificate in cursor.fetchall():

因此，除非再次.execute查询，否则您将无法再次获取它们。一个更好的主意是将数据存储在第一次提取中。

我的python脚本中没有JSON文件的输出

1 个答案: