我有一个数据框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()
，其中包含一个名为（“ A”）的300万行的列，看起来像：
"df"我要寻找的是在数据框中追加一个新列（C），其中将包含col（A）的第一个字符串，例如：
+--------------------+
| A |
+--------------------+
|down::string... ... |
|down::string... ... |
|up::string......... |
|up::string......... |
|right::string...... |
我使用+--------------------+
| C |
+--------------------+
|down |
|down |
|up |
|up |
|right |
如下：
.withColumn但这不起作用
答案 0 :(得分：-2)
一种实现此目的的方法是使用Spark UDF如下所示
import org.apache.spark.sql.functions._
import sparkSession.sqlContext.implicits._
val df = Seq("down::string... ...", "up::string.........", "right::string......").toDF("A")
df.show
val myUDF = udf {
(input: String) => {
input.split("::")(0)
}
}
val newDF = df.withColumn("C", myUDF(df("A")))
newDF.show()
输出将是
+-------------------+
| A|
+-------------------+
|down::string... ...|
|up::string.........|
|right::string......|
+-------------------+
+-------------------+-----+
| A| C|
+-------------------+-----+
|down::string... ...| down|
|up::string.........| up|
|right::string......|right|
+-------------------+-----+