def timestr2secs_utc(timestr):
"""
Convert a timestring to UTC (=GMT) seconds.
The format is either one of these two:
'20020702100000 CDT'
'200209080000 +0100'
"""
# This is either something like 'EDT', or '+1'
try:
tval, tz = timestr.split()
except ValueError:
tval = timestr
tz = str(-time.timezone / 3600)
if tz == 'CET':
tz = '+1'
# Is it the '+1' format?
if tz[0] == '+' or tz[0] == '-':
tmTuple = (int(tval[0:4]), int(tval[4:6]), int(tval[6:8]),
int(tval[8:10]), int(tval[10:12]), 0, -1, -1, -1)
secs = calendar.timegm(tmTuple)
adj_neg = int(tz) >= 0
try:
min = int(tz[3:5])
except ValueError:
# sometimes the mins are missing :-(
min = 0
adj_secs = int(tz[1:3]) * 3600 + min * 60
if adj_neg:
secs -= adj_secs
else:
secs += adj_secs
else:
# No, use the regular conversion
## WARNING! BUG HERE!
# The line below is incorrect; the strptime.strptime function doesn't
# handle time zones. There is no obvious function that does. Therefore
# this bug is left in for someone else to solve.
try:
secs = time.mktime(strptime.strptime(timestr, xmltv.date_format))
except ValueError:
timestr = timestr.replace('EST', '')
secs = time.mktime(strptime.strptime(timestr, xmltv.date_format))
return secs
def getRunTimeFILE(fname):
Load(Filename=fname,OutputWorkspace='Dummy')
wksp=mtd['Dummy']
#[date_ini,time_ini]=
ini=wksp.getRun(). get('run_start').value
#[date_fin,time_fin]=
fin=wksp.getRun(). get('run_end').value
try:
strptime = time.strptime
except AttributeError:
from strptime import strptime
#print strptime("31 Nov 00", "%d %b %y")
#print strptime("1 Jan 70 1:30pm", "%d %b %y %I:%M%p")
return (time.mktime(strptime(fin, "%Y-%m-%dT%H:%M:%S"))-time.mktime(strptime(ini, "%Y-%m-%dT%H:%M:%S")))/3600
def get_runtime_file(fname):
load(Filename=fname, OutputWorkspace='Dummy')
wksp = mtd['Dummy']
# [date_ini,time_ini]=
ini = wksp.getRun().get('run_start').value
# [date_fin,time_fin]=
fin = wksp.getRun().get('run_end').value
try:
strptime = time.strptime
except AttributeError:
from strptime import strptime
# print strptime("31 Nov 00", "%d %b %y")
# print strptime("1 Jan 70 1:30pm", "%d %b %y %I:%M%p")
return (time.mktime(strptime(fin, "%Y-%m-%dT%H:%M:%S")) -
time.mktime(strptime(ini, "%Y-%m-%dT%H:%M:%S"))) / 3600
def getRunTime(instrument='HRPD', runno=0):
inst=instrument[0:3]
cycle=rawpath(str(runno), inst=inst)
fname=cycle+'/'+inst+str(runno)+'.raw'
Load(Filename=fname,OutputWorkspace='Dummy')
wksp=mtd['Dummy']
#[date_ini,time_ini]=
ini=wksp.getRun(). get('run_start').value
#[date_fin,time_fin]=
fin=wksp.getRun(). get('run_end').value
try:
strptime = time.strptime
except AttributeError:
from strptime import strptime
#print strptime("31 Nov 00", "%d %b %y")
#print strptime("1 Jan 70 1:30pm", "%d %b %y %I:%M%p")
return (time.mktime(strptime(fin, "%Y-%m-%dT%H:%M:%S"))-time.mktime(strptime(ini, "%Y-%m-%dT%H:%M:%S")))/3600
def get_runtime(instrument='HRPD', runno=0):
inst = instrument[0:3]
cycle = rawpath(str(runno), inst=inst)
fname = cycle + '/' + inst + str(runno) + '.raw'
load(Filename=fname, OutputWorkspace='Dummy')
wksp = mtd['Dummy']
# [date_ini,time_ini]=
ini = wksp.getRun().get('run_start').value
# [date_fin,time_fin]=
fin = wksp.getRun().get('run_end').value
try:
strptime = time.strptime
except AttributeError:
from strptime import strptime
# print strptime("31 Nov 00", "%d %b %y")
# print strptime("1 Jan 70 1:30am", "%d %b %y %I:%M%p")
return (time.mktime(strptime(fin, "%Y-%m-%dT%H:%M:%S")) -
time.mktime(strptime(ini, "%Y-%m-%dT%H:%M:%S"))) / 3600
def loopLogs():
totalBytes = 0
totalSeconds = 0
totalFiles = 0
apppath = os.path.dirname(os.path.abspath(sys.argv[0]))
indexMatch = re.compile("^threadlog_[0-9]+\.log$")
fileMatch = re.compile("uploaded totally ([0-9]+) files")
byteMatch = re.compile("uploaded totally ([0-9]+) bytes")
timeFormat = "%Y-%m-%d %H:%M:%S"
theStartTime = datetime.datetime.max
theEndTime = datetime.datetime.min
for f in os.listdir(apppath):
if indexMatch.match(f):
fobj = open(os.path.join(apppath, f))
lines = fobj.readlines()
fobj.close()
m = fileMatch.match(lines[-1])
if m:
totalFiles = totalFiles + int(m.group(1))
m = byteMatch.match(lines[-2])
if m:
totalBytes = totalBytes + int(m.group(1))
startTimeTup = strptime.strptime(lines[-4].strip(), timeFormat)
endTimeTup = strptime.strptime(lines[-3].strip(), timeFormat)
startTime = datetime.datetime(startTimeTup[0], startTimeTup[1], startTimeTup[2], startTimeTup[3], startTimeTup[4], startTimeTup[5])
if startTime < theStartTime:
theStartTime = startTime
endTime = datetime.datetime(endTimeTup[0], endTimeTup[1], endTimeTup[2], endTimeTup[3], endTimeTup[4], endTimeTup[5])
if endTime > theEndTime:
theEndTime = endTime
deltaTime = theEndTime - theStartTime
totalSeconds = totalSeconds + deltaTime.days * 24 * 3600 + deltaTime.seconds
print "Upload started from: \t%s" % theStartTime.strftime(timeFormat)
print "Upload stopped at: \t%s" % theEndTime.strftime(timeFormat)
print "Upload last for:\t", deltaTime
print "Total files: \t%s" % number_format(totalFiles)
print "Total bytes: \t%s" % number_format(totalBytes)
print "Total seconds: \t%s" % number_format(totalSeconds)
print "Speed: %d bytes/sec" % (totalBytes / totalSeconds)
print "Speed: %d files/sec" % (totalFiles / totalSeconds)
'''
将字符串转换为时间对象
'''
# 使用 time.strptime 函数解析时间
# time 模块包含了 strptime 函数, 它的作用与 strftime 相反.
# 给定一个字符串和模式, 它返回相应的时间对象
import time
try:
strptime = time.strptime
except AttributeError:
from strptime import strptime
print(strptime('30 Nov 00','%d %b %y'))
print(strptime('1 Jan 70 1:30pm','%d %b %y %I:%M%p'))
'''
time.struct_time(tm_year=2000, tm_mon=11, tm_mday=30, tm_hour=0, tm_min=0, tm_sec=0, tm_wday=3, tm_yday=335, tm_isdst=-1)
time.struct_time(tm_year=1970, tm_mon=1, tm_mday=1, tm_hour=13, tm_min=30, tm_sec=0, tm_wday=3, tm_yday=1, tm_isdst=-1)
'''
print('-----------------')
# strptime 实现
# 对于没有提供标准实现的平台, 下面提供了一个不完全的实现.
import re
MONTHS = ["Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"]
SPEC = {
# map formatting code to a regular expression fragment
"%a": "(?P<weekday>[a-z]+)",
"%A": "(?P<weekday>[a-z]+)",
import time
# make sure we have a strptime function!
try:
strptime = time.strptime
except AttributeError:
from strptime import strptime
print(strptime("30 Nov 00", "%d %b %y"))
print(strptime("1 Jan 70 1:30pm", "%d %b %y %I:%M%p"))
#"d:\\data\\fileter_processedChekins.txt"
#J:\\checkin\\filter_allCheckinNewYork.txt
fileName = "d:\\data\\fileter_processedChekins.txt"
f=open(fileName,'r')
#trainf=open("d:\\trainfilter2.txt",'w+')
#testf=open("d:\\testfilter2.txt",'w+')
#逐行处理数据
#第一行初始化,为位置关系等比较
lastline=f.readline()
arr=lastline.split('\t')
lasttime=time.mktime(strptime(arr[1],"20%y-%m-%dT%H:%M:%SZ"))
lastuserid=arr[0]
lastlocid=arr[4]
timeDic={0:0}
i=0
while True:
newline=f.readline()
if newline=='':
break;
arr=newline.split('\t')
tm=strptime(arr[1],"20%y-%m-%dT%H:%M:%SZ")
newtime=time.mktime(tm)
#统计每个签到的时间分布
yearmon = int(str(tm.tm_year)+str(tm.tm_mon))
def initFromDirectoryListing(self, dirname, line):
mode = 0
isSymlink = False
self.dirname = dirname
link_target = None
if not line:
log.debug("initFromDirectoryListing: No line to process!")
return False
# Check the first character of the listing is a unix style
if line[0] in self._possible_first_chars_for_unix_listing:
# UNIX-style listing, without inum and without blocks */
# "-rw-r--r-- 1 root other 531 Jan 29 03:26 README" */
# "dr-xr-xr-x 2 root other 512 Apr 8 1994 etc" */
# "dr-xr-xr-x 2 root 512 Apr 8 1994 etc" */
# "lrwxrwxrwx 1 root other 7 Jan 25 00:17 bin -> usr/bin" */
# Note that UNIX-style listings can use names that contain a space:
# "-rw------- 1 incognito.guy Domain Users 11420 2011-12-29 18:51 .bash_history"
# Also produced by Microsoft's FTP servers for Windows: */
# "---------- 1 owner group 1803128 Jul 10 10:18 ls-lR.Z" */
# "d--------- 1 owner group 0 May 9 19:45 Softlib" */
# Also WFTPD for MSDOS: */
# "-rwxrwxrwx 1 noone nogroup 322 Aug 19 1996 message.ftp" */
# Also NetWare: */
# "d [R----F--] supervisor 512 Jan 16 18:53 login" */
# "- [R----F--] rhesus 214059 Oct 20 15:27 cx.exe" */
# Also NetPresenz and Rumpus on the Mac: */
# "-------r-- 326 1391972 1392298 Nov 22 1995 MegaPhone.sit" */
# "drwxrwxr-x folder 2 May 10 1996 network" */
# We used to regex on the line, but that is too slow, now we just
# use split() and do our best with that.
fi = line.split(None, 7)
if len(fi) == 7 and fi[1] == "folder":
# NetPresenz and Rumpus folder format
fi = fi[:1] + ["", ""] + fi[2:]
# First char dictates the type of file
if line[0] == "d":
mode |= stat.S_IFDIR # directory
elif line[0] == "-":
mode |= stat.S_IFREG # regular file
elif line[0] == "l":
mode |= stat.S_IFLNK # symlink
isSymlink = True
elif line[0] == "s":
mode |= stat.S_IFSOCK # socket
elif line[0] == "b":
mode |= stat.S_IFBLK # block type (special file)
elif line[0] == "c":
mode |= stat.S_IFCHR # character type (special file)
else:
mode |= stat.S_IFREG # unknown
#self.log.debug("THIS IS A SYMLINK!!!")
# we unfortunately dont know if we are owner or group member, so guess again
mode_str = fi[0]
# Determine the file permissions, i.e. from the line "drwxr-xr-x"
if mode_str[1:2] == "r": mode |= stat.S_IRUSR
if mode_str[2:3] == "w": mode |= stat.S_IWUSR
if mode_str[3:4] == "x": mode |= stat.S_IXUSR
elif mode_str[3:4] == "s": mode |= (stat.S_IXUSR | stat.S_ISUID)
elif mode_str[3:4] == "S": mode |= stat.S_ISUID
if mode_str[4:5] == "r": mode |= stat.S_IRGRP
if mode_str[5:6] == "w": mode |= stat.S_IWGRP
if mode_str[6:7] == "x": mode |= stat.S_IXGRP
elif mode_str[6:7] == "s": mode |= (stat.S_IXGRP | stat.S_ISGID)
elif mode_str[6:7] == "S": mode |= stat.S_ISGID
if mode_str[7:8] == "r": mode |= stat.S_IROTH
if mode_str[8:9] == "w": mode |= stat.S_IWOTH
if mode_str[9:10] == "x": mode |= stat.S_IXOTH
elif mode_str[9:10] == "t": mode |= (stat.S_IXOTH | stat.S_ISVTX)
elif mode_str[9:10] == "T": mode |= stat.S_ISVTX
# Deal with spaces in the user or group names - bug .
if fi[4] and fi[4][0].lower() in ascii_lowercase and \
fi[5] and fi[5][0] in string_digits and \
fi[7] and fi[7][0] in string_digits and \
" " in fi[7] and \
fi[3] and fi[3][0].lower() in ascii_lowercase and \
fi[2] and fi[2][0].lower() in ascii_lowercase:
while len(fi) >= 8:
fi[3] += fi.pop(5)
fi = fi[:6] + fi[6].split(None, 1)
if fi[5] and fi[5][0] in string_digits:
break
if fi[4].lower() in self._3char_month_names:
# Not enough fields, pad it out.
fi.insert(1, "")
if fi[4]: self.st_size = fi[4] # File size
# Work out the date
try:
# Date is in fi[5], check it's format. I.e
# "Nov 30"
# "2005-11-30"
# "26 fev"
# to see if we have a time, or a year?
guessedYear = False
if fi[5] and (fi[5][0] not in string_digits or
(len(fi[6]) == 3 and fi[6][0] not in string_digits)):
if " " in fi[7] and fi[7][0] in string_digits:
# Requires the filename field to be split up:
fi = fi[:1] + fi[2:7] + fi[7].split(None, 1)
if len(fi) == 9:
fi.pop(1)
month,day,year = fi[4:7]
# Some locales swap the day and the month, i.e. french:
# "26 fev 22:00", bug 88866.
if month and month[0] in string_digits and \
day and day not in string_digits:
day, month = month, day
if year.find(":") > -1:
hour = year
# fix time to be 5 digit always
year = "%d"%(time.gmtime(time.time())[0])
guessedYear = True
else:
hour = "00:00"
if len(day) < 2: day = "0"+day
if len(hour) < 5: hour = "0"+hour
date = "%s %s %s %s" % (month, day, year, hour)
try:
# Note: This can fail due to locale differences between
# the client and server, as time.strptime uses the
# locale for converting the fields. If this does
# fail, we give it one other chance using default
# English as the locale setting. See bug:
# http://bugs.activestate.com/show_bug.cgi?id=62638
t = time.strptime(date, '%b %d %Y %H:%M')
except Exception, e: # Error parsing the date field
# Try using internal strptime, with ENGLISH setting
t = strptime.strptime(date, '%b %d %Y %H:%M')
else:
sp = fi[5].split('-', 2)
if len(sp) == 3:
# 2005-11-30 format
year, month, day = sp
hour = fi[6]
date = "%s %s %s %s" % (year, month, day, hour)
t = time.strptime(date, '%Y %m %d %H:%M')
else:
raise Exception("Uknown date")
self.st_mtime = time.mktime(t)
if guessedYear:
# Bug 81475.
# If the time is more than a day ahead, set it back one
# year. For example, we recieved: "Dec 31 23:29", but
# if today's date is "March 18 2009", then the year should
# actually be 2008, otherwise the date is in the future...
# A date too far ahead is defined as two days greater than
# the current local machine time (> 99% correct).
if self.st_mtime >= time.time() + (2 * 60 * 60 * 24):
t = list(t)
t[0] -= 1
self.st_mtime = time.mktime(t)
locr={0:{0:0}}
user_loc={0:{0:0}}
checkintime=[0]*21
x=0
locr_max=0#位置边的最大权值
trainc=0
testc=0
locckins={0:0}
userckins={0:0}
#逐行处理数据
#第一行初始化,为位置关系等比较
lastline=f.readline()
arr=lastline.split('\t')
lasttime=time.mktime(strptime(arr[1],"20%y-%m-%dT%H:%M:%SZ"))
lastuserid=arr[0]
lastlocid=arr[4]
i=0
while True:
#i=i+1
newline=f.readline()
if newline=='':
break;
arr=newline.split('\t')
tm=strptime(arr[1],"20%y-%m-%dT%H:%M:%SZ")
newtime=time.mktime(tm)
userid=int(arr[0])
locidstr=arr[4]
locid=int(locidstr[:-2])
#第一行初始化,为位置关系等比较
lastline=f.readline()
arr=lastline.split(',')
#lasttime=time.mktime(strptime(arr[2],"%d/%m/20%y %H:%M:%S"))
lastuserid=arr[1]
lastlocid=arr[3]
i=0
time={0:0}
while True:
newline=f.readline()
if newline=='':
break;
arr=newline.split(',')
tm=strptime(arr[2],"%d/%m/20%y %H:%M:%S")
newtime=time.mktime(tm)
userid=int(arr[1])
locidstr=arr[3]
'''#统计每个签到的时间分布
if tm.tm_year==2010 and tm.tm_mon>=10:
testf.write(newline)
testc=testc+1
else:
trainf.write(newline)
trainc=trainc+1
'''
#统计每个用户的签到次数
#!/usr/bin/python
import time
try:
strptime = time.strptime
except AttributeError:
print("load from strptime")
from strptime import strptime
print strptime("2013-09-14 00:00:00","%Y-%m-%d %H:%M:%S")
print strptime("30 Nov 00","%d %b %y")
print strptime("1 Jan 70 1:30pm","%d %b %y %I:%M%p")
'''
#import strptime
try:
strptime = time.strptime
except AttributeError:
from strptime import strptime
f=open("d:\\1totalCheckins.txt",'r')
out=file("d:\\1out.txt","w")
#第一行，把时间值存储在lastt中,初始化
lastline=f.readline()
arr=lastline.split('\t')
print arr
lastt=time.mktime(strptime(arr[1],"20%y-%m-%dT%H:%M:%SZ"))
lastflag=True
i=0
#后面的每行与前一行判断，如果user相同且时间在五分钟之内，则放弃，否则写入到out。txt中
#（默认为不同用户之间最早的和最晚的签到时间不可能在五分钟之内）
while True:
line=f.readline()
arr=line.split('\t')
i=i+1
if i%1000==0:
print i,":",arr
#获得时间值
intt=time.mktime(strptime(arr[1],"20%y-%m-%dT%H:%M:%SZ"))
if lastt-intt>300:
if lastflag:
littleTime=201311
largeTime=0
#逐行处理数据
timeCountStatc=[0,0,0,0,0,0,0,0,0,0,0]
#将string类型的locId改为int型的
locStrIdDic={}
locIdNum=0
while True:
newline=f.readline()
if newline=='':
break;
arr=newline.split(',')#arr=newline.split('\t')
tm=strptime(arr[2],"%d/%m/20%y %H:%M:%S")#tm=strptime(arr[1],"20%y-%m-%dT%H:%M:%SZ")
newtime=time.mktime(tm)
userid=int(arr[1])
locidstr=arr[3]
locid=locIdNum
if locidstr in locStrIdDic.keys():
locid=locStrIdDic[locidstr]
else:
locStrIdDic[locidstr]=locIdNum
locIdNum+=1
timenum=timeNum(tm.tm_year,tm.tm_mon)
'''
if timenum>largeTime: largeTime=timenum
if timenum<littleTime :littleTime=timenum
if timenum<=201301:timeCountStatc[0]+=1
import time
# make sure we have a strptime function!
try:
strptime = time.strptime
except AttributeError:
from strptime import strptime
print strptime("31 Nov 00", "%d %b %y")
print strptime("1 Jan 70 1:30pm", "%d %b %y %I:%M%p")
fout=open("E:\\checkin\\foursquare_allCheckin.txt",'w')
#将string类型的locId改为int型的
locStrIdDic={}
locIdNum=0
i=0
while True:
i=i+1
if i%10000 ==0:
print i
newline=f.readline()
if newline=='':
break;
arr=newline.split(',')#arr=newline.split('\t')
tm=strptime(arr[2],"%d/%m/20%y %H:%M:%S")#tm=strptime(arr[1],"20%y-%m-%dT%H:%M:%SZ")
newtime=time.mktime(tm)
userid=int(arr[1])
locidstr=arr[3]
locid=locIdNum
if locidstr in locStrIdDic:
locid=locStrIdDic[locidstr]
else:
locStrIdDic[locidstr]=locIdNum
locIdNum+=1
timenum=timeNum(tm.tm_year,tm.tm_mon)
nline=str(userid)+'\t'+str(tm.tm_year)+'-'+str(tm.tm_mon)+'-'+str(tm.tm_mday)+'T'+str(tm.tm_hour)+':'\
+str(tm.tm_min)+":"+str(tm.tm_sec)+'Z\t'+arr[5]+'\t'+arr[6]+'\t'+ str(locid)+'\n'
else:
self.st_size = fi[1]
try:
#t = time.strptime(fi[0],'%m-%d-%y %I:%M%p')
try:
# Note: This can fail due to locale differences between
# the client and server, as time.strptime uses the
# locale for converting the fields. If this does
# fail, we give it one other chance using default
# English as the locale setting. See bug:
# http://bugs.activestate.com/show_bug.cgi?id=62638
t = time.strptime(fi[0],'%m-%d-%y %I:%M%p')
except Exception, e: # Error parsing the date field
# Try using internal strptime, with ENGLISH setting
t = strptime.strptime(fi[0],'%m-%d-%y %I:%M%p')
#print "date trans: ",repr(t)
self.st_time = time.mktime(t)
except Exception, e: # Error parsing the date field
#print "\n%s" % e
self.log.warn("Unknown date in line: '%s'" % (line))
self.st_mtime = 0 # Unknown date, 1970 it is!
filename = fi[2]
#print "filename:", filename
self.st_mode = mode
# Set the full path
# XXX - Windows/DOS filenames break ??
self._setpathinfo(dirname, filename, link_target)
#self.log.debug("initFromDirectoryListing: %s", self)
return True
f.write(str(cur))
dbcon.commit()
cur.execute("SELECT * FROM trends")
f.write("".join(["\n----Rows after deletion---\n",str(cur.rowcount),"\n"]))
twohoursbefore = (datetime.now() - timedelta(0,2*60*60))
onehourbefore = (datetime.now() - timedelta(0,1*60*60))
for row in cursor: # Iteration is equivalent to lots of fetchone() calls
entrytime = strptime(row[0], "2013-%m-%d %H:%M")
entrydatetime = datetime.fromtimestamp(mktime(entrytime))
#print entrydatetime.hour;
#if entrydatetime.hour == twohoursbefore.hour and entrydatetime.hour < onehourbefore.hour:
f.write ("".join([row[1],str(row[2])]))
cur.execute("SELECT * FROM trends WHERE word = %s", (row[1],))
print(cur)
if cur.rowcount == 0:
#means the row has to be inserted
f.write('\nWord does not exist. Will now be inserted.\n')
cur.execute("INSERT INTO trends (word, count) VALUES (%s, %s)", (row[1], row[2],))
f.write(str(cur))
dbcon.commit()
else:
else:
self.st_size = fi[1]
try:
#t = time.strptime(fi[0],'%m-%d-%y %I:%M%p')
try:
# Note: This can fail due to locale differences between
# the client and server, as time.strptime uses the
# locale for converting the fields. If this does
# fail, we give it one other chance using default
# English as the locale setting. See bug:
# http://bugs.activestate.com/show_bug.cgi?id=62638
t = time.strptime(fi[0], '%m-%d-%y %I:%M%p')
except Exception, e: # Error parsing the date field
# Try using internal strptime, with ENGLISH setting
t = strptime.strptime(fi[0], '%m-%d-%y %I:%M%p')
#print "date trans: ",repr(t)
self.st_time = time.mktime(t)
except Exception, e: # Error parsing the date field
#print "\n%s" % e
self.log.warn("Unknown date in line: '%s'" % (line))
self.st_mtime = 0 # Unknown date, 1970 it is!
filename = fi[2]
#print "filename:", filename
self.st_mode = mode
# Set the full path
# XXX - Windows/DOS filenames break ??
self._setpathinfo(dirname, filename, link_target)
#self.log.debug("initFromDirectoryListing: %s", self)
return True
def initFromDirectoryListing(self, dirname, line):
mode = 0
isSymlink = False
self.dirname = dirname
link_target = None
if not line:
log.debug("initFromDirectoryListing: No line to process!")
return False
# Check the first character of the listing is a unix style
if line[0] in self._possible_first_chars_for_unix_listing:
# UNIX-style listing, without inum and without blocks */
# "-rw-r--r-- 1 root other 531 Jan 29 03:26 README" */
# "dr-xr-xr-x 2 root other 512 Apr 8 1994 etc" */
# "dr-xr-xr-x 2 root 512 Apr 8 1994 etc" */
# "lrwxrwxrwx 1 root other 7 Jan 25 00:17 bin -> usr/bin" */
# Note that UNIX-style listings can use names that contain a space:
# "-rw------- 1 incognito.guy Domain Users 11420 2011-12-29 18:51 .bash_history"
# Also produced by Microsoft's FTP servers for Windows: */
# "---------- 1 owner group 1803128 Jul 10 10:18 ls-lR.Z" */
# "d--------- 1 owner group 0 May 9 19:45 Softlib" */
# Also WFTPD for MSDOS: */
# "-rwxrwxrwx 1 noone nogroup 322 Aug 19 1996 message.ftp" */
# Also NetWare: */
# "d [R----F--] supervisor 512 Jan 16 18:53 login" */
# "- [R----F--] rhesus 214059 Oct 20 15:27 cx.exe" */
# Also NetPresenz and Rumpus on the Mac: */
# "-------r-- 326 1391972 1392298 Nov 22 1995 MegaPhone.sit" */
# "drwxrwxr-x folder 2 May 10 1996 network" */
# We used to regex on the line, but that is too slow, now we just
# use split() and do our best with that.
fi = line.split(None, 7)
if len(fi) == 7 and fi[1] == "folder":
# NetPresenz and Rumpus folder format
fi = fi[:1] + ["", ""] + fi[2:]
# First char dictates the type of file
if line[0] == "d":
mode |= stat.S_IFDIR # directory
elif line[0] == "-":
mode |= stat.S_IFREG # regular file
elif line[0] == "l":
mode |= stat.S_IFLNK # symlink
isSymlink = True
elif line[0] == "s":
mode |= stat.S_IFSOCK # socket
elif line[0] == "b":
mode |= stat.S_IFBLK # block type (special file)
elif line[0] == "c":
mode |= stat.S_IFCHR # character type (special file)
else:
mode |= stat.S_IFREG # unknown
#self.log.debug("THIS IS A SYMLINK!!!")
# we unfortunately dont know if we are owner or group member, so guess again
mode_str = fi[0]
# Determine the file permissions, i.e. from the line "drwxr-xr-x"
if mode_str[1:2] == "r": mode |= stat.S_IRUSR
if mode_str[2:3] == "w": mode |= stat.S_IWUSR
if mode_str[3:4] == "x": mode |= stat.S_IXUSR
elif mode_str[3:4] == "s": mode |= (stat.S_IXUSR | stat.S_ISUID)
elif mode_str[3:4] == "S": mode |= stat.S_ISUID
if mode_str[4:5] == "r": mode |= stat.S_IRGRP
if mode_str[5:6] == "w": mode |= stat.S_IWGRP
if mode_str[6:7] == "x": mode |= stat.S_IXGRP
elif mode_str[6:7] == "s": mode |= (stat.S_IXGRP | stat.S_ISGID)
elif mode_str[6:7] == "S": mode |= stat.S_ISGID
if mode_str[7:8] == "r": mode |= stat.S_IROTH
if mode_str[8:9] == "w": mode |= stat.S_IWOTH
if mode_str[9:10] == "x": mode |= stat.S_IXOTH
elif mode_str[9:10] == "t": mode |= (stat.S_IXOTH | stat.S_ISVTX)
elif mode_str[9:10] == "T": mode |= stat.S_ISVTX
# Deal with spaces in the user or group names - bug .
if fi[4] and fi[4][0].lower() in ascii_lowercase and \
fi[5] and fi[5][0] in string_digits and \
fi[7] and fi[7][0] in string_digits and \
" " in fi[7] and \
fi[3] and fi[3][0].lower() in ascii_lowercase and \
fi[2] and fi[2][0].lower() in ascii_lowercase:
while len(fi) >= 8:
fi[3] += fi.pop(5)
fi = fi[:6] + fi[6].split(None, 1)
if fi[5] and fi[5][0] in string_digits:
break
if fi[4].lower() in self._3char_month_names:
# Not enough fields, pad it out.
fi.insert(1, "")
if fi[4]: self.st_size = fi[4] # File size
# Work out the date
try:
# Date is in fi[5], check it's format. I.e
# "Nov 30"
# "2005-11-30"
# "26 fev"
# to see if we have a time, or a year?
guessedYear = False
if fi[5] and (fi[5][0] not in string_digits or
(len(fi[6]) == 3
and fi[6][0] not in string_digits)):
if " " in fi[7] and fi[7][0] in string_digits:
# Requires the filename field to be split up:
fi = fi[:1] + fi[2:7] + fi[7].split(None, 1)
if len(fi) == 9:
fi.pop(1)
month, day, year = fi[4:7]
# Some locales swap the day and the month, i.e. french:
# "26 fev 22:00", bug 88866.
if month and month[0] in string_digits and \
day and day not in string_digits:
day, month = month, day
if year.find(":") > -1:
hour = year
# fix time to be 5 digit always
year = "%d" % (time.gmtime(time.time())[0])
guessedYear = True
else:
hour = "00:00"
if len(day) < 2: day = "0" + day
if len(hour) < 5: hour = "0" + hour
date = "%s %s %s %s" % (month, day, year, hour)
try:
# Note: This can fail due to locale differences between
# the client and server, as time.strptime uses the
# locale for converting the fields. If this does
# fail, we give it one other chance using default
# English as the locale setting. See bug:
# http://bugs.activestate.com/show_bug.cgi?id=62638
t = time.strptime(date, '%b %d %Y %H:%M')
except Exception, e: # Error parsing the date field
# Try using internal strptime, with ENGLISH setting
t = strptime.strptime(date, '%b %d %Y %H:%M')
else:
sp = fi[5].split('-', 2)
if len(sp) == 3:
# 2005-11-30 format
year, month, day = sp
hour = fi[6]
date = "%s %s %s %s" % (year, month, day, hour)
t = time.strptime(date, '%Y %m %d %H:%M')
else:
raise Exception("Uknown date")
self.st_mtime = time.mktime(t)
if guessedYear:
# Bug 81475.
# If the time is more than a day ahead, set it back one
# year. For example, we recieved: "Dec 31 23:29", but
# if today's date is "March 18 2009", then the year should
# actually be 2008, otherwise the date is in the future...
# A date too far ahead is defined as two days greater than
# the current local machine time (> 99% correct).
if self.st_mtime >= time.time() + (2 * 60 * 60 * 24):
t = list(t)
t[0] -= 1
self.st_mtime = time.mktime(t)
if tm.tm_sec<10:
dayStr = "0"+ str(tm.tm_sec)
return str(tm.tm_year)+'-'+monStr+'-'+dayStr+'T'+hourStr+':'+minStr+":"+secStr
'''
path="E:\\checkin\\"
outpath="E:\\checkin\\"
f=open(path+"filter_foursquare_CheckinNewYork.txt",'r')
outf=open(outpath+"foursquare_NewYork_allcheckin.txt",'w')
i=0
while True:
i=i+1
if i%10000 ==0:
print i
newline=f.readline()
if newline=='':
break;
arr=newline.split('\t')
tm=strptime(arr[1],"20%y-%m-%dT%H:%M:%SZ")
newtime=time.mktime(tm)
timenum=timeNum(tm.tm_year,tm.tm_mon)
newline=arr[0]+'\t'+timeStr(tm)+'Z\t'+arr[2]+'\t'+arr[3]+'\t'+ arr[4]
outf.write(newline)
f.close()
outf.close()
# -*- coding:utf-8 -*-
# Example 1-81. 使用 time.strptime 函数解析时间
# File: time-example-6.py
import time
# make sure we have a strptime function!
# 确认有函数 strptime
try:
strptime = time.strptime
except AttributeError:
from strptime import strptime
print strptime("31 Nov 00", "%d %b %y")
print strptime("1 Jan 70 1:30pm", "%d %b %y %I:%M%p")
