Python循环代码，几乎都有解决方案
我需要一些python代码的帮助。如果可能的话，请告诉我 下面是notepad中4050.log数据文件在执行代码之前的一个示例-Python循环代码，几乎都有解决方案,python,parsing,loops,text,notepad,Python,Parsing,Loops,Text,Notepad,我需要一些python代码的帮助。如果可能的话，请告诉我 下面是notepad中4050.log数据文件在执行代码之前的一个示例- port=4050 SOH= hostname=BlueVectorEMA uptime=N/A SHTSOT=N/A iCenter=N/A start=51808152 stop=518083AA cycles=0.0 tagCnt=23 C1Gen1=0.0.0.0 C1Gen2=0.0.0.0 STX= 00045512=119,59,55,60,50,C,
port=4050
SOH=
hostname=BlueVectorEMA
uptime=N/A
SHTSOT=N/A
iCenter=N/A
start=51808152
stop=518083AA
cycles=0.0
tagCnt=23
C1Gen1=0.0.0.0
C1Gen2=0.0.0.0
STX=
00045512=119,59,55,60,50,C,00,N/A
00052450=120,60,44,60,43,C,00,N/A
00042260=113,54,51,59,43,C,00,N/A
00046999=114,56,46,58,42,C,00,N/A
00043166=117,58,46,59,42,C,00,N/A
00052651=113,55,48,58,42,C,00,N/A
00050594=118,59,43,59,43,C,00,N/A
00051774=120,60,44,60,42,C,00,N/A
00056767=119,59,43,60,42,C,00,N/A
00043181=109,51,56,58,45,C,00,N/A
00033333=115,56,55,59,43,C,00,N/A
00031475=115,57,43,58,45,C,00,N/A
00042817=118,59,48,59,50,C,00,N/A
00054245=118,58,45,60,41,C,00,N/A
00043589=118,58,46,60,43,C,00,N/A
00053037=116,57,54,59,48,C,00,N/A
00053636=114,55,45,59,42,C,00,N/A
00045642=116,57,49,59,42,C,00,N/A
00045591=118,59,46,59,45,C,00,N/A
00033114=116,58,46,58,44,C,00,N/A
00042075=114,56,54,58,48,C,00,N/A
00044491=113,55,42,58,43,C,00,N/A
00000587=18,0,999,18,46,T,403/002,0030H/3.0
ETX=
EOT=
timestamp=5180a211
logdir=2013-05
Wed May 1 00:03:13 2013
--------------------------------------------------------------------------------
port=4050
SOH=
hostname=BlueVectorEMA
uptime=N/A
SHTSOT=N/A
iCenter=N/A
start=518083AA
stop=51808602
cycles=0.0
tagCnt=23
C1Gen1=0.0.0.0
C1Gen2=0.0.0.0
STX=
00053636=119,59,44,60,41,C,00,N/A
00043181=107,48,56,59,45,C,00,N/A
00046999=116,57,46,59,42,C,00,N/A
00031475=117,58,43,59,45,C,00,N/A
00053037=115,55,54,60,48,C,00,N/A
00052651=117,58,47,59,42,C,00,N/A
00042075=117,57,54,60,48,C,00,N/A
00050594=118,59,43,59,43,C,00,N/A
00045512=115,55,55,60,50,C,00,N/A
00044491=113,55,42,58,43,C,00,N/A
00033114=115,57,46,58,44,C,00,N/A
00045591=117,58,46,59,46,C,00,N/A
00052450=117,58,44,59,43,C,00,N/A
00042260=114,56,51,58,42,C,00,N/A
00043166=116,58,47,58,42,C,00,N/A
00042817=117,59,48,58,50,C,00,N/A
00056767=119,59,43,60,42,C,00,N/A
00054245=119,59,45,60,41,C,00,N/A
00043589=117,57,46,60,43,C,00,N/A
00051774=118,59,44,59,42,C,00,N/A
00045642=113,55,50,58,42,C,00,N/A
00033333=111,53,55,58,44,C,00,N/A
00000587=7,0,999,7,47,T,402/202,0028H/2.5
ETX=
EOT=
timestamp=5180a469
logdir=2013-05
Wed May 1 00:13:13 2013
--------------------------------------------------------------------------------
00052450|120|60|44|60|43|C|00|N/A|4050|BlueVectorEMA|05/01/2013 00:03:13
00042260|113|54|51|59|43|C|00|N/A|4050|BlueVectorEMA|05/01/2013 00:03:13
00046999|114|56|46|58|42|C|00|N/A|4050|BlueVectorEMA|05/01/2013 00:03:13
00043166|117|58|46|59|42|C|00|N/A|4050|BlueVectorEMA|05/01/2013 00:03:13
00052651|113|55|48|58|42|C|00|N/A|4050|BlueVectorEMA|05/01/2013 00:03:13
00050594|118|59|43|59|43|C|00|N/A|4050|BlueVectorEMA|05/01/2013 00:03:13
00051774|120|60|44|60|42|C|00|N/A|4050|BlueVectorEMA|05/01/2013 00:03:13
00056767|119|59|43|60|42|C|00|N/A|4050|BlueVectorEMA|05/01/2013 00:03:13
伙计们，有什么想法吗？这里有几件事你应该做，让代码更可读a，b让事情更理智，我想 所以你有你的日志文件，如果你仔细想想，它本质上是一个字典的集合，每个日期一个 因此，首先，将您的文件拆分为以下每个部分 大概是这样的：
from datetime import datetime
logFile, temp = [], []
with open("4050.log") as f:
for line in f:
if "------------------" in line:
logFile.append(temp[:])
temp = []
else:
temp.append(line)
logDict = {}
for log in logFile:
tempDict = {}
for line in log:
if "=" in line:
line = line.split("=")
tempDict[line[0]] = line[1].strip()
logDict[log[-1].strip()] = tempDict.copy()
keysWeDontWant = "port SOH hostname hostname SHTSOT iCenter start stop cycles tagCnt C1Gen1 C1Gen2 STX ETX EOT timestamp logdir uptime".split()
for logDate, log in logDict.items():
for key, value in log.items():
if key not in keysWeDontWant and not key.startswith("00000"):
dateTimeString = datetime.strptime(logDate, "%a %B %d %H:%M:%S %Y").strftime("%M/%d/%Y %H:%M:%S")
print key + "|" + value.replace(",","|") + "|4050|%s|%s" % (log["hostname"], dateTimeString)
做这项工作，而且更干净一点。但它仍然不是很好，需要知道日志文件的规范才能很好地完成它。而且我要睡觉了 您可以做几件事：
- 使用函数（它们可以让您将工作单元分解为易于理解的部分）
- 使用（它们将大大简化模式匹配）
- 使用（它们将帮助您一次性完成所有工作）
import collections
import re
DATA_LINE = re.compile("(\d{8})=(.*)")
DATE = re.compile("""
(?P<month>\w+) # Match one or more alpha-numeric characters
# (store match as "month")
\s+ # followed by one or more whitespace characters
(?P<day>\d{1,2}) # followed by one or two numbers
# (store match as "day")
\s+ # followed by one or more whitespace characters
(?P<time>\d{2}:\d{2}:\d{2})
# followed by two numbers, a colon, two numbers,
# another colon, and two more numbers
# (store match as "time")
\s+ # followed by one or more whitespace characters
(?P<year>\d{4}) # followed by for numbers
# (store match as "year")
""", re.VERBOSE)
def interesting_lines(logfile_path):
"""Yield lines of interest in tuples of
``(processed_line, is_date)``."""
# First, ensure that we will close the file
# no matter what happens
with open(logfile_path) as file_object:
# Loop over all the lines (files are iterators too)
for line in file_object:
data = DATA_LINE.match(line)
if data:
# If this line has data, get the matched data
# (the number before the equals sign and everything after it)
# pass it on as a list of strings with a flag that marks
# this lineas a data line
yield ",".join(data.groups()).split(","), False
elif DATE.search(line):
# Otherwise, if the line is the date
# pass on the re-formatted string and a flag that marks
# this line as the date line
yield datetime.strptime(line, "%a %B %d %H:%M:%S %Y") \
.strftime("%M/%d/%Y %H:%M:%S"), True
def combine_with_date(lines):
buffer = collections.deque()
for line, is_date in lines:
buffer.append(line)
if is_date:
current_date = line
for line in buffer:
line.append(current_date)
yield line
buffer.clear()
def write_to_file(iterable_of_lines):
# TODO: Create CSV writer with pipe-delimited dialect
# and write to file
if __name__ == "__main__":
file_path = raw_input("Please provide a file path:")
line_generator = interesting_lines(file_path)
processed_lines = combine_with_date(line_generator)
write_to_file(processed_lines)
导入集合
进口稀土
数据行=重新编译（（\d{8}）=（.*））
日期=重新编译（“”）
（？P\w+）#匹配一个或多个字母数字字符
#（存储匹配为“月”）
\s+#后跟一个或多个空格字符
（？P\d{1,2}）#后跟一个或两个数字
#（将匹配存储为“日”）
\s+#后跟一个或多个空格字符
（？P\d{2}:\d{2}:\d{2}）
#后跟两个数字，一个冒号，两个数字，
#另一个冒号，还有两个数字
#（将匹配存储为“时间”）
\s+#后跟一个或多个空格字符
（？P\d{4}）#后跟for数字
#（存储匹配为“年”）
“”，re.VERBOSE）
def有趣的\u行（日志文件\u路径）：
“以元组表示的感兴趣的产量线”
``（已处理的行，是日期）`.”
#首先，确保我们将关闭该文件
#不管发生什么事
打开（日志文件路径）作为文件对象：
#循环所有行（文件也是迭代器）
对于文件\u对象中的行：
数据=数据线。匹配（线）
如果数据：
#如果此行有数据，则获取匹配的数据
#（等号前的数字及其后的所有内容）
#将其作为字符串列表传递，其中带有标记
#这是一条数据线
yield“，”.join（data.groups（））.split（“，”），False
elif日期搜索（行）：
#否则，如果行是日期
#传递重新格式化的字符串和标记
#此行作为日期行
生成datetime.strTime（第行，“%a%B%d%H:%M:%S%Y”）\
.strftime（“%M/%d/%Y%H:%M:%S”），True
def组合_与_日期（行）：
buffer=collections.deque（）
对于第行，日期是否为第行：
buffer.append（行）
如果是(日期):
当前日期=行
对于缓冲区中的行：
行。追加（当前_日期）
生产线
buffer.clear（）
def写入文件（可编辑的行数）：
#TODO:使用管道分隔方言创建CSV编写器
#并写入文件
如果名称=“\uuuuu main\uuuuuuuu”：
文件路径=原始输入（“请提供文件路径：”）
行生成器=感兴趣的行（文件路径）
已处理的\u行=将\u与\u日期合并（行\u生成器）
将\u写入\u文件（已处理的\u行）
from datetime import datetime
logFile, temp = [], []
with open("4050.log") as f:
for line in f:
if "------------------" in line:
logFile.append(temp[:])
temp = []
else:
temp.append(line)
logDict = {}
for log in logFile:
tempDict = {}
for line in log:
if "=" in line:
line = line.split("=")
tempDict[line[0]] = line[1].strip()
logDict[log[-1].strip()] = tempDict.copy()
keysWeDontWant = "port SOH hostname hostname SHTSOT iCenter start stop cycles tagCnt C1Gen1 C1Gen2 STX ETX EOT timestamp logdir uptime".split()
for logDate, log in logDict.items():
for key, value in log.items():
if key not in keysWeDontWant and not key.startswith("00000"):
dateTimeString = datetime.strptime(logDate, "%a %B %d %H:%M:%S %Y").strftime("%M/%d/%Y %H:%M:%S")
print key + "|" + value.replace(",","|") + "|4050|%s|%s" % (log["hostname"], dateTimeString)
import collections
import re
DATA_LINE = re.compile("(\d{8})=(.*)")
DATE = re.compile("""
(?P<month>\w+) # Match one or more alpha-numeric characters
# (store match as "month")
\s+ # followed by one or more whitespace characters
(?P<day>\d{1,2}) # followed by one or two numbers
# (store match as "day")
\s+ # followed by one or more whitespace characters
(?P<time>\d{2}:\d{2}:\d{2})
# followed by two numbers, a colon, two numbers,
# another colon, and two more numbers
# (store match as "time")
\s+ # followed by one or more whitespace characters
(?P<year>\d{4}) # followed by for numbers
# (store match as "year")
""", re.VERBOSE)
def interesting_lines(logfile_path):
"""Yield lines of interest in tuples of
``(processed_line, is_date)``."""
# First, ensure that we will close the file
# no matter what happens
with open(logfile_path) as file_object:
# Loop over all the lines (files are iterators too)
for line in file_object:
data = DATA_LINE.match(line)
if data:
# If this line has data, get the matched data
# (the number before the equals sign and everything after it)
# pass it on as a list of strings with a flag that marks
# this lineas a data line
yield ",".join(data.groups()).split(","), False
elif DATE.search(line):
# Otherwise, if the line is the date
# pass on the re-formatted string and a flag that marks
# this line as the date line
yield datetime.strptime(line, "%a %B %d %H:%M:%S %Y") \
.strftime("%M/%d/%Y %H:%M:%S"), True
def combine_with_date(lines):
buffer = collections.deque()
for line, is_date in lines:
buffer.append(line)
if is_date:
current_date = line
for line in buffer:
line.append(current_date)
yield line
buffer.clear()
def write_to_file(iterable_of_lines):
# TODO: Create CSV writer with pipe-delimited dialect
# and write to file
if __name__ == "__main__":
file_path = raw_input("Please provide a file path:")
line_generator = interesting_lines(file_path)
processed_lines = combine_with_date(line_generator)
write_to_file(processed_lines)