文件倒读
In [1]: cat /tmp/1.txt
a
b
c
d
In [2]: ll /tmp/1.txt 应该是有8个字符，每个字符后边都有一个换行符号\n,加上换行符共8个字节。
-rw-r--r-- 1 admin wheel 8 7 3 15:18 /tmp/1.txt
In [3]: f = open('/tmp/1.txt')
In [4]: f.tell() 指针位置：0 在文件的开头
Out[4]: 0
In [5]: f.read(1) 读一个字符
Out[5]: 'a'
In [6]: f.tell() 指针位置：1
Out[6]: 1
In [13]: f.read(1) 读一个字符
Out[13]: '\n'
In [14]: f.tell() 指针位置：2
Out[14]: 2
In [15]: f.read(2) 读2个字节，b和\n
Out[15]: 'b\n'
In [16]: f.tell() 指针位置：4
Out[16]: 4
In [17]: f.read(100)
Out[17]: 'c\nd\n'
In [18]: f.tell()
Out[18]: 8
In [30]: help(f.seek)
Help on built-in function seek:
seek(...)
seek(offset[, whence]) -> None. Move to new file position.
Argument offset is a byte count. Optional argument whence defaults to
0 (offset from start of file, offset should be >= 0); other values are 1
(move relative to current position, positive or negative), and 2 (move
relative to end of file, usually negative, although many platforms allow
seeking beyond the end of a file). If the file is opened in text mode,
only offsets returned by tell() are legal. Use of other offsets causes
undefined behavior.
Note that not all file objects are seekable.
0 从开头指针位置移动
In [45]: f.seek(2)
In [46]: f.tell()
Out[46]: 2
In [10]: f.seek(0,0) 移动指针到开头，从开头向后移动0位
In [11]: f.tell()
Out[11]: 0
1 从当前指针位置移动
f.tell()
Out[42]: 5
In [43]: f.seek(-2,1)
In [44]: f.tell()
Out[44]: 3
2 从结尾的指针位置开始移动move relative to end of file
In [8]: f.seek(3,2) 8+3=11从结尾8向后移动三位，
In [9]: f.tell()
Out[9]: 11
In [12]: f.seek(0,2) 把指针移动到最后
In [13]: f.tell()
Out[13]: 8
admindeMacBook-Air-62:~ admin$ cat /tmp/1.txt
a
b
c
d
#!/usr/bin/env python
f = open('/tmp/1.txt')
f.seek(0,2)
while True:
if f.tell() == 1:
break
else:
f.seek(-2,1)
c = f.read(1)
print c,
python seek.py
d
c
b
a
#!/usr/bin/env python
#encoding:utf8
import sys
f = open('/etc/hosts')
f.seek(0,2)
line = ''
while True:
if f.tell() == 1:
print line #打印1a的条件
break
else:
f.seek(-2,1)
c = f.read(1)
if c != '\n':
line = c + line #空＋d＝d，4+d＝4d
else:
print line
line = '' #重置line＝空
python seek3.py
221.228.208.76 dmp.chinadep.com admin.chinadep.com
文件倒读
In [1]: cat /tmp/1.txt
a
b
c
d
In [2]: ll /tmp/1.txt 应该是有8个字符，每个字符后边都有一个换行符号\n,加上换行符共8个字节。
-rw-r--r-- 1 admin wheel 8 7 3 15:18 /tmp/1.txt
In [3]: f = open('/tmp/1.txt')
In [4]: f.tell() 指针位置：0 在文件的开头
Out[4]: 0
In [5]: f.read(1) 读一个字符
Out[5]: 'a'
In [6]: f.tell() 指针位置：1
Out[6]: 1
In [13]: f.read(1) 读一个字符
Out[13]: '\n'
In [14]: f.tell() 指针位置：2
Out[14]: 2
In [15]: f.read(2) 读2个字节，b和\n
Out[15]: 'b\n'
In [16]: f.tell() 指针位置：4
Out[16]: 4
In [17]: f.read(100)
Out[17]: 'c\nd\n'
In [18]: f.tell()
Out[18]: 8
In [30]: help(f.seek)
Help on built-in function seek:
seek(...)
seek(offset[, whence]) -> None. Move to new file position.
Argument offset is a byte count. Optional argument whence defaults to
0 (offset from start of file, offset should be >= 0); other values are 1
(move relative to current position, positive or negative), and 2 (move
relative to end of file, usually negative, although many platforms allow
seeking beyond the end of a file). If the file is opened in text mode,
only offsets returned by tell() are legal. Use of other offsets causes
undefined behavior.
Note that not all file objects are seekable.
0 从开头指针位置移动
In [45]: f.seek(2)
In [46]: f.tell()
Out[46]: 2
In [10]: f.seek(0,0) 移动指针到开头，从开头向后移动0位
In [11]: f.tell()
Out[11]: 0
1 从当前指针位置移动
f.tell()
Out[42]: 5
In [43]: f.seek(-2,1)
In [44]: f.tell()
Out[44]: 3
2 从结尾的指针位置开始移动move relative to end of file
In [8]: f.seek(3,2) 8+3=11从结尾8向后移动三位，
In [9]: f.tell()
Out[9]: 11
In [12]: f.seek(0,2) 把指针移动到最后
In [13]: f.tell()
Out[13]: 8
admindeMacBook-Air-62:~ admin$ cat /tmp/1.txt
a
b
c
d
#!/usr/bin/env python
f = open('/tmp/1.txt')
f.seek(0,2)
while True:
if f.tell() == 1:
break
else:
f.seek(-2,1)
c = f.read(1)
print c,
python seek.py
d
c
b
a
#!/usr/bin/env python
#encoding:utf8
import sys
f = open('/etc/hosts')
f.seek(0,2)
line = ''
while True:
if f.tell() == 1:
print line #打印1a的条件
break
else:
f.seek(-2,1)
c = f.read(1)
if c != '\n':
line = c + line #空＋d＝d，4+d＝4d
else:
print line
line = '' #重置line＝空
python seek3.py
221.228.208.76 dmp.chinadep.com admin.chinadep.com
admindeMacBook-Air-62:~ admin$ cat /tmp/1.txt
1aA
2bB
3cC
4dD
vim seek5.py
#!/usr/bin/env python
#encoding:utf8
import sys
def filerev(fn):
f = open(fn)
f.seek(0,2)
line = ''
while True:
if f.tell() == 1: #把最前面的一个字符读出来f.read()=1,f.tell()由0->1，打印第一行
yield line #打印1a的条件
break
else:
f.seek(-2,1)
c = f.read(1)
if c != '\n':
line = c + line #空＋d＝d，4+d＝4d
else:
yield line
line = '' #重置line＝空
f.close()
a = filerev('/tmp/1.txt') #a只是一个生成器对象，没有值，遍历才有值
for i in a :
print i
4dD
3cC
2bB
1aA
vim seek6.py
#!/usr/bin/env python
#encoding:utf8
import sys
def filerev(fn):
buffer = 256 #定义一个buffer256字节
f = open(fn)
f.seek(0,2)
size = f.tell() #所有子节包括\n
rem = size % buffer #文件不可能被buffer整整除，肯定有一些剩下的部分，rem是求余数
offset =max(0, size - (buffer + rem))#取最大值，0 > 一个负数，偏移量，如果buffer小于文件大小，将指针移动到最后一个buffer前面，如果size>buffer(256子节)此时指针的位置是buffer＋rem
line = ''
while True:
if offset < 0: #把最前面的一个字符读出来f.read()=1,f.tell()由0->1，打印第一行
yield line #打印1a的条件
break
else:
f.seek(offset)
d = f.read(buffer + rem)
rem = 0 #第一次读rem，以后rem都是0，以后只读一个buffer
offset -= buffer
#print d #d = 1aA 2bB 3cC 4dD
if '\n' in d: # d = 1aA 2bB 3cC 4dD
for c in reversed(d):#判断读出来的内容是否包含换行符\n,如果有的话，所有字节反转，判断\n,
#print c # D d 4 C c 3 B b 2 A a 1
if c != '\n': # c = \n
line = c + line #D+空＝D，d+D＝dD, 4+dD=4dD
#print line
else:
if line: #\n=\n,yes,yield=4dD,置空line
yield line
line = '' # 重置line＝空
else:
line = d + line
f.close()
a = filerev('/etc/passwd') #a只是一个生成器对象，没有值，遍历才有值
for i in a :
print
_wwwproxy:*:252:252:WWW Proxy:/var/empty:/usr/bin/false
_xserverdocs:*:251:251:OS X Server Documents Service:/var/empty:/usr/bin/false
_ondemand:*:249:249:On Demand Resource Daemon:/var/db/ondemand:/usr/bin/false
_mbsetupuser:*:248:248:Setup User:/var/setup:/bin/bash
_gamecontrollerd:*:247:247:Game Controller Daemon:/var/empty:/usr/bin/false
_krbfast:*:246:-2:Kerberos FAST Account:/var/empty:/usr/bin/false
_astris:*:245:245:Astris Services:/var/db/astris:/usr/bin/false
统计apache日志
#!/usr/bin/env python
#encoding:utf8
import sys
import socket
import datetime
#日志格式，取时间： 116.236.168.138 - - [29/Sep/2017:02:20:36 +0800] "GET /render/?width=586&height=308&_salt=1499170697.335 HTTP/1.1" 200 1147
MONTH = {
'Jan': 1,
'Feb': 2,
'Mar': 3,
'Apr': 4,
'May': 5,
'Jun': 6,
'Jul': 7,
'Aug': 8,
'Sep': 9,
'Oct': 10,
'Dec': 11,
'Oct': 12
}
def parseLogtime(s):
day,month,yearandtime = s.split('/')
#print day,month,yearandtime #日志默认格式，日，月，年，时分秒，29 Sep 2017:02:13:04
year,hour,minute,second = [int(i) for i in yearandtime.split(':')]
#print datetime.datetime(year,MONTH[month],int(day),hour,minute,second) #月MONTH[month],打印年月日，时分秒2017-09-29 01:55:46
return datetime.datetime(year,MONTH[month],int(day),hour,minute,second) #月Jun对应数字6，MONTH(month)
def countDict(k,d): # 统计字典，定义函数，解析日志每一行，往字典中添加元素
if k in d: # 判断k是不是在字典中，k如果在字典中，字典的k对应的value加1
d[k] +=1
else: # 判断k是不是在字典中，k如果不在字典中，新建字典元素k，value＝1
d[k] = 1
def parseLogfile(f):#key是时间戳，value是日志出现的次数（日志文件被访问的次数）
dic = {}
with open(f) as fd:
for line in fd: # 日志原文，116.236.168.138 - - [29/Sep/2017:02:20:36 +0800] 空为分隔符，切割后，3表示取第4个，line.split()[3]＝[29/Sep/2017:02:20:36
timestr = line.split()[3][1:] # 切片操作timestr = line.split()[3][1:] ＝ 29/Sep/2017:02:20:36 ［1: ］把中括号去掉
logtime = parseLogtime(timestr) # timestr经过parseLogtime（）函数的处理，就会返回年月日时分秒的格式的时间了，logtime = 2017,9,29,2,20,36
#print logtime
countDict(logtime,dic) # logtime时间戳最为字典dic的key，value=1,2,3,出现多一次，次数加1
#print dic #{datetime.datetime(2017, 7, 8, 10, 33, 24): 3, datetime.datetime(2017, 12, 2, 16, 13, 12): 3, datetime.datetime(2017, 12, 1, 9, 58, 58): 4, datetime.datetime(2017, 12, 2, 1, 30, 17): 1, datetime.datetime(2017, 12, 1, 8, 45, 39): 1, datetime.datetime(2017, 12, 2, 1, 4, 6): 1, datetime.datetime(2017, 12, 1, 10, 20, 51): 1, datetime.datetime(2017, 12, 2, 6, 28, 7): 1, datetime.datetime(2017, 12, 1, 8, 13, 54): 2, datetime.datetime(2017, 12, 1, 4, 51, 8): 1, datetime.datetime(2017, 12, 2, 16, 25, 37): 1, datetime.datetime(2017, 12, 2, 16, 13, 10): 1, datetime.datetime(2017, 7, 8, 10, 28, 4): 1, datetime.datetime(2017, 12, 2, 16, 23, 48): 2, datetime.datetime(2017, 7, 8, 10, 27, 35): 5, datetime.datetime(2017, 12, 2, 16, 13, 20): 1, datetime.datetime(2017, 7, 8, 10, 33, 29): 1, datetime.datetime(2017, 7, 8, 10, 28, 3): 1, datetime.datetime(2017, 12, 1, 9, 58, 55): 5, datetime.datetime(2017, 12, 1, 9, 58, 56): 1, datetime.datetime(2017, 12, 1, 8, 45, 18): 1, datetime.datetime(2017, 7, 8, 10, 27, 58): 4, datetime.datetime(2017, 12, 1, 8, 45, 43): 1, datetime.datetime(2017, 12, 1, 8, 13, 58): 1, datetime.datetime(2017, 12, 2, 6, 28, 5): 1, datetime.datetime(2017, 12, 2, 6, 28, 12): 1, datetime.datetime(2017, 12, 2, 6, 27, 59): 1, datetime.datetime(2017, 12, 1, 8, 13, 51): 2, datetime.datetime(2017, 7, 8, 10, 33, 26): 1, datetime.datetime(2017, 12, 1, 20, 58, 19): 2, datetime.datetime(2017, 12, 2, 16, 23, 50): 2, datetime.datetime(2017, 7, 8, 10, 33, 34): 5, datetime.datetime(2017, 12, 1, 8, 13, 52): 2, datetime.datetime(2017, 12, 1, 10, 20, 46): 1, datetime.datetime(2017, 12, 1, 10, 20, 56): 1, datetime.datetime(2017, 7, 8, 10, 28, 49): 1, datetime.datetime(2017, 12, 2, 11, 8, 34): 1, datetime.datetime(2017, 12, 1, 12, 19, 37): 1, datetime.datetime(2017, 12, 1, 9, 58, 51): 10, datetime.datetime(2017, 12, 2, 16, 25, 35): 2, datetime.datetime(2017, 12, 2, 16, 13, 8): 2, datetime.datetime(2017, 12, 1, 4, 51, 13): 1, datetime.datetime(2017, 7, 8, 10, 28, 46): 3, datetime.datetime(2017, 12, 1, 8, 45, 41): 1, datetime.datetime(2017, 7, 8, 10, 36, 16): 1, datetime.datetime(2017, 12, 2, 6, 28, 9): 2, datetime.datetime(2017, 12, 1, 9, 58, 53): 14, datetime.datetime(2017, 12, 1, 18, 50, 43): 1, datetime.datetime(2017, 7, 8, 10, 43, 59): 1, datetime.datetime(2017, 12, 1, 10, 20, 55): 1, datetime.datetime(2017, 12, 2, 12, 40, 1): 1, datetime.datetime(2017, 12, 1, 8, 13, 49): 2, datetime.datetime(2017, 12, 1, 12, 19, 36): 1, datetime.datetime(2017, 12, 2, 16, 23, 52): 1, datetime.datetime(2017, 12, 1, 4, 18, 49): 1, datetime.datetime(2017, 12, 2, 16, 25, 38): 4, datetime.datetime(2017, 12, 1, 9, 59, 5): 1, datetime.datetime(2017, 7, 8, 10, 33, 36): 7, datetime.datetime(2017, 12, 1, 20, 58, 24): 21, datetime.datetime(2017, 12, 2, 16, 13, 50): 1, datetime.datetime(2017, 12, 2, 6, 40, 54): 1, datetime.datetime(2017, 12, 2, 16, 13, 14): 4, datetime.datetime(2017, 12, 1, 7, 28, 18): 1, datetime.datetime(2017, 12, 1, 5, 31, 27): 1, datetime.datetime(2017, 12, 1, 9, 59): 1, datetime.datetime(2017, 12, 1, 9, 58, 50): 1, datetime.datetime(2017, 12, 1, 8, 45, 47): 1, datetime.datetime(2017, 12, 2, 16, 26, 20): 5, datetime.datetime(2017, 12, 1, 8, 45, 32): 2, datetime.datetime(2017, 12, 1, 9, 58, 59): 1, datetime.datetime(2017, 12, 1, 8, 45, 29): 3, datetime.datetime(2017, 12, 1, 8, 45, 22): 7, datetime.datetime(2017, 12, 2, 12, 1, 21): 2, datetime.datetime(2017, 7, 8, 10, 33, 25): 2, datetime.datetime(2017, 12, 1, 10, 20, 53): 1, datetime.datetime(2017, 12, 1, 20, 58, 23): 11, datetime.datetime(2017, 12, 2, 16, 13, 41): 1, datetime.datetime(2017, 12, 1, 8, 13, 55): 2, datetime.datetime(2017, 12, 1, 14, 42, 34): 1, datetime.datetime(2017, 12, 2, 11, 8, 35): 1, datetime.datetime(2017, 12, 1, 9, 59, 2): 1, datetime.datetime(2017, 12, 1, 16, 36, 35): 1, datetime.datetime(2017, 12, 2, 13, 12, 41): 1, datetime.datetime(2017, 12, 2, 16, 25, 36): 3, datetime.datetime(2017, 12, 1, 7, 21, 55): 1, datetime.datetime(2017, 12, 2, 14, 37, 24): 1, datetime.datetime(2017, 12, 1, 12, 30, 10): 1, datetime.datetime(2017, 12, 1, 11, 56, 50): 2, datetime.datetime(2017, 7, 8, 10, 27, 22): 5, datetime.datetime(2017, 7, 8, 10, 33, 27): 1, datetime.datetime(2017, 12, 1, 8, 45, 45): 1, datetime.datetime(2017, 12, 1, 8, 45, 20): 2, datetime.datetime(2017, 7, 8, 10, 27, 59): 1, datetime.datetime(2017, 12, 1, 9, 58, 57): 2, datetime.datetime(2017, 12, 1, 8, 13, 53): 1, datetime.datetime(2017, 12, 1, 20, 25, 12): 1, datetime.datetime(2017, 7, 8, 10, 36, 14): 5, datetime.datetime(2017, 12, 1, 10, 20, 48): 1, datetime.datetime(2017, 7, 8, 10, 27, 24): 5, datetime.datetime(2017, 7, 8, 10, 43, 58): 5, datetime.datetime(2017, 7, 8, 10, 28, 48): 1, datetime.datetime(2017, 12, 2, 16, 23, 49): 1, datetime.datetime(2017, 12, 1, 20, 58, 21): 8, datetime.datetime(2017, 12, 1, 10, 20, 59): 2, datetime.datetime(2017, 7, 8, 10, 28, 47): 2, datetime.datetime(2017, 12, 2, 16, 13, 47): 1, datetime.datetime(2017, 7, 8, 10, 33, 30): 1, datetime.datetime(2017, 12, 1, 10, 0, 45): 1, datetime.datetime(2017, 12, 1, 20, 58, 18): 1, datetime.datetime(2017, 12, 2, 16, 13, 21): 3, datetime.datetime(2017, 12, 1, 4, 51, 11): 1, datetime.datetime(2017, 12, 2, 16, 25, 34): 3, datetime.datetime(2017, 12, 2, 16, 13, 18): 1, datetime.datetime(2017, 7, 8, 10, 27, 34): 1, datetime.datetime(2017, 12, 1, 10, 21, 3): 1, datetime.datetime(2017, 12, 2, 6, 28, 10): 1, datetime.datetime(2017, 12, 2, 12, 1, 22): 1, datetime.datetime(2017, 12, 1, 8, 13, 57): 2, datetime.datetime(2017, 12, 2, 6, 28, 3): 1, datetime.datetime(2017, 12, 1, 9, 13, 38): 1, datetime.datetime(2017, 12, 2, 6, 25, 5): 1, datetime.datetime(2017, 12, 1, 10, 20, 54): 1, datetime.datetime(2017, 7, 8, 10, 28): 1, datetime.datetime(2017, 12, 1, 10, 20, 57): 1, datetime.datetime(2017, 12, 1, 8, 13, 50): 3, datetime.datetime(2017, 12, 1, 10, 20, 47): 1, datetime.datetime(2017, 12, 2, 16, 13, 6): 3, datetime.datetime(2017, 12, 2, 16, 13, 16): 5, datetime.datetime(2017, 12, 2, 16, 13, 9): 2, datetime.datetime(2017, 7, 8, 10, 27, 33): 4, datetime.datetime(2017, 7, 8, 10, 33, 37): 2, datetime.datetime(2017, 12, 2, 16, 23, 51): 2, datetime.datetime(2017, 12, 1, 17, 14, 23): 1, datetime.datetime(2017, 12, 1, 10, 21, 4): 1, datetime.datetime(2017, 12, 1, 8, 45, 30): 4, datetime.datetime(2017, 12, 2, 16, 23, 47): 1, datetime.datetime(2017, 12, 1, 4, 16, 26): 1, datetime.datetime(2017, 12, 1, 9, 58, 52): 18, datetime.datetime(2017, 12, 1, 8, 45, 23): 25, datetime.datetime(2017, 12, 1, 8, 45, 33): 1, datetime.datetime(2017, 12, 1, 8, 45, 40): 1, datetime.datetime(2017, 12, 1, 21, 14, 59): 3, datetime.datetime(2017, 12, 1, 7, 32, 9): 1, datetime.datetime(2017, 12, 2, 6, 28, 1): 1, datetime.datetime(2017, 7, 8, 10, 33, 35): 3, datetime.datetime(2017, 12, 1, 3, 59, 15): 1, datetime.datetime(2017, 12, 2, 1, 56, 13): 1, datetime.datetime(2017, 12, 1, 10, 20, 52): 1, datetime.datetime(2017, 7, 8, 10, 28, 2): 1, datetime.datetime(2017, 12, 2, 16, 13, 40): 1, datetime.datetime(2017, 12, 2, 11, 8, 33): 1, datetime.datetime(2017, 12, 1, 9, 59, 1): 1, datetime.datetime(2017, 12, 2, 16, 13, 22): 2, datetime.datetime(2017, 12, 1, 9, 12, 2): 1, datetime.datetime(2017, 12, 1, 21, 15): 2, datetime.datetime(2017, 12, 1, 8, 45, 21): 9, datetime.datetime(2017, 12, 1, 8, 45, 28): 2, datetime.datetime(2017, 7, 8, 10, 27, 37): 1, datetime.datetime(2017, 12, 2, 12, 0, 35): 1, datetime.datetime(2017, 12, 1, 17, 9, 56): 1}
return dic
#if __name__ == '__main__':
# print parseLogfile('/tmp/graphite-web-access.log')
def send_graphite(dic):
sock = socket.socket()
host = '112.65.140.132'
port = 2003
sock.connect((host, port))
#print s
key = "httpd.count"
for k, v in dic.items(): #key时间戳，value是时间戳的次数
s = "%s %d %s\n" % (key, v, k.strftime('%s'))
print s
sock.send(s)
if __name__ == '__main__':
try:
logfile = '/tmp/graphite-web-access.log'
except IndexError:
print "%s follow a argument" % __file__
sys.exit()
data = parseLogfile(logfile)
#print data
send_graphite(data)
#[root@client ~]# netstat -lnp
#Active Internet connections (only servers)
#Proto Recv-Q Send-Q Local Address Foreign Address State PID/Program name
#tcp 0 0 127.0.0.1:6379 0.0.0.0:* LISTEN 2414/redis-server 1
#tcp 0 0 0.0.0.0:9391 0.0.0.0:* LISTEN 863/openvassd
#tcp 0 0 0.0.0.0:111 0.0.0.0:* LISTEN 1212/rpcbind
#tcp 0 0 0.0.0.0:2003 0.0.0.0:* LISTEN 6212/python2.6
#tcp 0 0 0.0.0.0:2004 0.0.0.0:* LISTEN 6212/python2.6
执行结果：
/System/Library/Frameworks/Python.framework/Versions/2.7/bin/python2.7 /Users/admin/Desktop/project/graphite/apache_log.py
httpd.count 3 1499481204
httpd.count 3 1512202392
httpd.count 1 1512187235
httpd.count 1 1512119396
Process finished with exit code 0
[root@client whisper]# pwd /var/lib/carbon/whisper [root@client whisper]# ll 总用量 16 drwxr-xr-x 3 carbon carbon 4096 9月 5 2017 carbon drwxr-xr-x 2 carbon carbon 4096 7月 8 11:42 httpd drwxr-xr-x 2 carbon carbon 4096 9月 7 2017 interface drwxr-xr-x 2 carbon carbon 4096 9月 6 2017 test [root@client whisper]# ll httpd/ 总用量 20 -rw-r--r-- 1 carbon carbon 17308 7月 8 11:46 count.wsp