I got this file with this info pattern:
# Query 1: 204.60k QPS, 230.79x concurrency, ID XXXXXXXXXX at byte 19XXX9318
# This item is included in the report because it matches --limit.
# Scores: V/M = 0.00
# Time range: 2020-01-29 18:18:59.073995 to 18:18:59.074005
# Attribute pct total min max avg 95% stddev median
# ============ === ======= ======= ======= ======= ======= ======= =======
# Count 7 2
# Exec time 10 2ms 1ms 1ms 1ms 1ms 12us 1ms
# Rows affecte 0 0 0 0 0 0 0 0
# Query size 7 74 37 37 37 37 0 37
# Warning coun 0 0 0 0 0 0 0 0
# String:
# Hosts 10.1.1.5 (1/50%), 10.8.0.2 (1/50%)
# Query_time distribution
# 1us
# 10us
# 100us
# 1ms ################################################################
# 10ms
# 100ms
# 1s
# 10s+
SHOW SESSION STATUS LIKE 'XXXXX'\G
\n break line
repeat
I want to run a script in python to get only some information from that file. There will be multiple querys.
Currently Im trying something like this:
#!/usr/bin/python
file = open("/etc/openvpn/logs/log-2020_01_29_06_20_PM.txt", "r")
read = file.read()
removeChar = read.replace("#", "")
for item in removeChar.split("\n"):
if "Hosts" and "Time range" in item:
print item.strip()
The output is:
Time range: 2020-01-29 18:18:59.073995 to 18:18:59.074005
Time range: 2020-01-29 18:18:58.489162 to 18:18:59.188582
Time range: 2020-01-29 18:18:58.666020 to 18:18:58.666028
I want it to be something like this:
['Query 1, 2020-01-29 18:18:59, 10.1.1.5, 10.8.0.2, SHOW SESSION STATUS LIKE 'XXXXX'\G']
['Query 2, 2020-01-29 18:19:59, 10.1.1.5, 10.8.0.2, SHOW FROM BLA * LIKE 'BLA'\G']
Im tired of trying to find how to do this, also I'm learning python because it is a good language to learn! :)
Thanks.
You could try without regex, using string manipulation only:
data = '''# Query 1: 204.60k QPS, 230.79x concurrency, ID XXXXXXXXXX at byte 19XXX9318
# This item is included in the report because it matches --limit.
# Scores: V/M = 0.00
# Time range: 2020-01-29 18:18:59.073995 to 18:18:59.074005
# Attribute pct total min max avg 95% stddev median
# ============ === ======= ======= ======= ======= ======= ======= =======
# Count 7 2
# Exec time 10 2ms 1ms 1ms 1ms 1ms 12us 1ms
# Rows affecte 0 0 0 0 0 0 0 0
# Query size 7 74 37 37 37 37 0 37
# Warning coun 0 0 0 0 0 0 0 0
# String:
# Hosts 10.1.1.5 (1/50%), 10.8.0.2 (1/50%)
# Query_time distribution
# 1us
# 10us
# 100us
# 1ms ################################################################
# 10ms
# 100ms
# 1s
# 10s+
SHOW SESSION STATUS LIKE 'XXXXX'\G
\n break line
repeat
'''
data = data.split('\n')
all_results = []
result = []
for row in data:
if row.startswith('# Query ') and not row.startswith('# Query size'):
row = row.split(':')[0].split('# ')[1]
result.append(row)
elif row.startswith('# Hosts'):
row = row.replace('# Hosts', '').replace(' ', '').split(',')
result.append(row[0].split('(')[0])
result.append(row[1].split('(')[0])
elif row.startswith('# Time range:'):
row = row.replace('# Time range:', '').split('.')[0].strip()
result.append(row)
elif row.startswith('SHOW') and row.endswith('\G'):
result.append(row)
result = ', '.join(result)
all_results.append(result)
result = []
print(all_results)
# output: "Query 1, 2020-01-29 18:18:59, 10.1.1.5, 10.8.0.2, SHOW SESSION STATUS LIKE 'XXXXX'\\G"
If you want to use regex and hardcode, here is an example:
import re
file_path = 'file.txt'
query_pattern = r'Query \d+'
date_time_pattern = r'\d\d\d\d-(0?[1-9]|1[0-2])-(0?[1-9]|[12][0-9]|3[01]) ' \
r'(00|[0-9]|1[0-9]|2[0-3]):([0-9]|[0-5][0-9]):([0-5][0-9]|[0-9])'
hosts_pattern = r'\d+\.\d+\.\d\.\d+'
final_pattern = r"SHOW.+\\G"
result = ''
with open(file_path, 'r', encoding='utf-8') as f:
try:
text = f.read()
result += '{}, '.format(str(re.search(query_pattern, text)[0]))
result += '{}, '.format(str(re.search(date_time_pattern, text)[0]))
hosts = re.findall(hosts_pattern, text)
result += '{}, {}, '.format(hosts[0], hosts[1])
result += re.search(final_pattern, text)[0]
print('Done!')
except Exception as e:
print('Error: \n{}'.format(e))
print(result)
Output:
Query 1, 2020-01-29 18:18:59, 10.1.1.5, 10.8.0.2, SHOW SESSION STATUS LIKE 'XXXXX'\G
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.