def format_date(self, date):
# Get rid of eg. 2008-06-26T08:30:00
self.date = date
if "T" in self.date:
self.date=date.split("T")[0]
elif self.date == "Varies by indicator":
return ''
elif "00:00:00" in self.date:
self.date=date.split('00:00:00')[0]
elif self.date == "Every 5-10 minutes":
return ''
try:
if ", " in self.date:
self.valid_date = datetime.strptime(self.date, "%B %d, %Y")
elif "/" in self.date:
self.valid_date = datetime.strptime(self.date, "%Y/%m/%d")
elif len(date)==4:
self.valid_date = datetime.strptime(self.date, "%Y")
else:
self.valid_date = datetime.strptime(self.date, '%Y-%m-%d')
return str(self.valid_date.date())
except ValueError:
return ''
def format_date(date):
new_date = {}
new_date['year'] = int(date.split('-')[0])
new_date['month'] = int(date.split('-')[1])
new_date['day'] = int(date.split('-')[2])
return new_date
def waterdata_func(site_num,begin_year,begin_mon,begin_date,end_year,end_mon,end_date):
import urllib
url = []
#site_num = '08078000'
begin_date = str(datetime(begin_year,begin_mon,begin_date).date())
end_d = str(datetime(end_year,end_mon,end_date).date())
url = 'http://waterdata.usgs.gov/nwis/dv?cb_00060=on&cb_00065=on&format=rdb&period=&begin_date='+begin_date+'&end_date='+end_d+'&site_no='+site_num
data = urllib.urlopen(url)
discharge = []
dates = []
for lines in data.readlines()[30:]:
da = lines.split()
discharge.append(float(da[3]))
date = da[2]
year = int(date.split('-')[0])
month = int(date.split('-')[1])
day = int(date.split('-')[2])
dates.append(datetime(year,month,day))
discharges = 0.028316*np.array(discharge) # converting to cubic meter
data_date = np.array(dates)
return discharges, data_date
print discharges
print data_date
def main(self):
# 作成日
date = str(datetime.today()).split('.')[0]
day = date.split(' ')[0]
time = 'T' + date.split(' ')[1] + 'Z'
# print day + time
# ルート
zabbix = Element('zabbix_export')
# バージョン
version = SubElement(zabbix, 'version')
version.text = '2.0'
# 日付
date = SubElement(zabbix, 'date')
date.text = day + time
# グループ
groups = SubElement(zabbix, 'groups')
group = SubElement(groups, 'group')
groupname = SubElement(group, 'name')
groupname.text = 'AAA'
# テンプレート
templates = SubElement(zabbix, 'templates')
template = SubElement(templates, 'template')
templatechild = SubElement(template, 'template')
templatechild.text = 'BBB'
#templatechild.set = ('discription', 'BBB')
templatename = SubElement(template, 'name')
templatename.text = 'CCC'
templategroups = SubElement(template, 'groups')
templategroup = SubElement(templategroups, 'group')
templategroupname = SubElement(templategroup, 'name')
templategroupname.text = 'AAA'
# while True:
# templategroups = SubElement(template, 'groups')
# templategroup = SubElement(templategroups, 'group')
# templategroupname = SubElement(templategroup, 'name')
# templategroupname.text = 'AAA'
# xmlファイル書き込み
#tree = ElementTree(zabbix)
#tree.write(xmlfile, 'UTF-8', 'True') #改行なし
f = open('test.xml', 'w')
tree = minidom.parseString(tostring(zabbix)).toprettyxml()
print tree
f.write(tree)
f.flush()
f.close()
def github_date(date):
if date is not None:
date = date.split("T")[0]
year, month, day = [int(p) for p in date.split("-")]
else:
gm = time.gmtime()
year = gm.tm_year
month = gm.tm_mon
day = gm.tm_mday
return year, month, day
def valid_date(date):
if len(date.split('/')) == 3:
try:
year, month, day = [int(x) for x in date.split('/')]
return 1987 <= year <= int(
datetime.today().year) and 0 < month <= 12 and 0 < day <= 31
except ValueError:
return False
return False
def format_date(self,date):
"""
Formats the date from STELA mode to MASTER2009
YYYYMMDDT.HHH->yyyy mm dd hh
"""
d = datetime.now()
d = d.strftime("%Y %m %d %H")
if(re.search("T",date)):
d = " ".join([date.split("T")[0].replace("-"," "),date.split("T")[1].split(":")[0]])
return d
def getUnixTime(dateTime):
dateTime = str(dateTime)
date = dateTime.split(' ')[0]
time = dateTime.split(' ')[1]
dt = datetime(int(date.split('-')[0]), int(date.split('-')[1]),
int(date.split('-')[2]), int(time.split(':')[0]),
int(time.split(':')[1]))
timestamp = dt.replace(tzinfo=timezone.utc).timestamp()
return int(timestamp)
def day(article_text):
article = article_text
if len(list(datefinder.find_dates(article))) > 0:
date = str(list(datefinder.find_dates(article))[0])
date = date.split()
date = date[0]
year, month, day = date.split('-')
day_name = datetime.date(int(year), int(month), int(day))
return day_name.strftime("%A")
return "Monday"
def get_unix_time(dt):
dt = str(dt)
date = dt.split(' ')[0]
time = dt.split(' ')[1]
timestamp = datetime(
int(date.split('-')[0]), int(date.split('-')[1]),
int(date.split('-')[2]), int(time.split(':')[0]),
int(time.split(':')[1])).replace(tzinfo=timezone.utc).timestamp()
return int(timestamp)
def reverse_datetime(date):
tmp = date.split(" ")
date = tmp[0]
time = tmp[1]
d = int(date.split("-")[0])
m = int(date.split("-")[1])
y = int(date.split("-")[2])
h = int(time.split(":")[0])
mi = int(time.split(":")[1])
date = datetime(int(y), int(m), int(d), int(h), int(mi), 00, 000)
return date
def __init__(self, date=None):
if date != None:
self.day = int(date.split()[1].replace(',', ''))
self.month = date.split()[0]
self.year = int(date.split()[2])
else:
now = datetime.now(EST()).date()
self.today = now.strftime("%B %d, %Y")
self.day = int(self.today.split()[1].replace(',', ''))
self.month = self.today.split()[0]
self.year = int(self.today.split()[2])
def update_graph_scatter(df, column, per):
years = list(set(df["YEAR"]))
n = len(years)
data = []
if per == 'DAY':
for i in range(n):
trace = go.Scatter(
x=df[df["YEAR"] == years[i]][per].apply(
lambda date: date.split('-')[1]),
y=df[df["YEAR"] == years[i]][column],
name=str(years[i]),
mode='lines+markers+text',
#text = df[df["YEAR"]==years[i]][column],
#textposition='middle center',
textfont=dict(size=10, ),
marker=dict(size=3, color=colors[i], line=dict(width=1, )))
data.append(trace)
layout = go.Layout(
dict(
title=df[df["YEAR"] == years[0]][per].apply(
lambda date: date.split('-')[0]).tolist()[0],
legend_bgcolor="rgb(255,255,255)",
plot_bgcolor="rgb(255,255,255)",
paper_bgcolor="rgb(255,255,255)",
showlegend=True,
margin=dict(t=50),
))
else:
for i in range(n):
trace = go.Scatter(
x=df[df["YEAR"] == years[i]][per],
y=df[df["YEAR"] == years[i]][column],
name=str(years[i]),
mode='lines+markers+text',
text=df[df["YEAR"] == years[i]][column],
#textposition='middle center',
textfont=dict(size=10, ),
marker=dict(size=3, color=colors[i], line=dict(width=1, )))
data.append(trace)
layout = go.Layout(
dict(
title="",
legend_bgcolor="rgb(255,255,255)",
plot_bgcolor="rgb(255,255,255)",
paper_bgcolor="rgb(255,255,255)",
showlegend=True,
margin=dict(t=50),
))
return {"data": data, "layout": layout}
def getPrices():
session = HTMLSession()
r = session.get(
'https://elen.nu/timpriser-pa-el-for-elomrade-se3-stockholm')
datetable = r.html.find('tr')
for tr in datetable:
date = tr.find('td', first=True)
if (date != None):
date = date.text
year = date.split('-')[0]
month = date.split('-')[1]
splitday = date.split('-')[2]
day = splitday.split(' ')[0]
time = date.split(" ")[1]
hour = time.split(":")[0]
priceList = tr.find('td')
counter = 0
for price in priceList:
counter = counter + 1
if (counter % 2 == 0):
amount = price.text
priceString = amount.split(" ")[0]
priceFloat = float(priceString)
alreadyExists = HourPrice.query.filter_by(year=year,
month=month,
day=day,
hour=hour).all()
if (len(alreadyExists) == 0):
hourPrice = HourPrice(year=year,
month=month,
day=day,
hour=hour,
price=priceFloat)
db.session.add(hourPrice)
db.session.commit()
print("Getting hourly prices")
averagetable = r.html.find(".elspot-area-price")[2].text
priceAverageString = (averagetable.split(" ")[0])
priceAverageFloat1 = float(priceAverageString.split(",")[0])
priceAverageFloat2 = float(priceAverageString.split(",")[1]) / 100
priceAverage = priceAverageFloat1 + priceAverageFloat2
alreadyExists2 = AveragePrice.query.filter_by(year=year,
month=month,
day=day).all()
if (len(alreadyExists2) == 0):
averagePrice = AveragePrice(year=year,
month=month,
day=day,
priceAverage=priceAverage)
db.session.add(averagePrice)
db.session.commit()
print("Getting daily averages")
def search_by_month_and_day(phone_book, date):
flag = False
for key, value in phone_book.items():
if len(value) == 1:
pass
else:
if value[1].split('/')[0] == date.split('/')[0] and value[1].split(
'/')[1] == date.split('/')[1]:
flag = True
print(key, *value)
if not flag:
print('Sorry, nothing was found')
def extract(ground_truth, horizon, sou, version, model, mc, dates):
df = pd.DataFrame()
for date in dates[1:]:
if date == dates[-1] and not os.path.exists("result/prediction/"+model+"/"+ '_'.join([ground_truth,date,horizon,version+".csv"])):
date = '-'.join([date.split('-')[0],"06-30" if date.split('-')[1] <= "06" else "12-31"])
print(date)
if not os.path.exists("result/prediction/"+model+"/"+ '_'.join([ground_truth,date,horizon,version+".csv"])):
print("Missing prediction in "+ '_'.join([ground_truth,date,horizon,version+".csv"]))
continue
df = pd.concat([df,pd.read_csv("result/prediction/"+model+"/"+ '_'.join([ground_truth,date,horizon,version+".csv"]), index_col = 0)],axis = 0)
return df.loc[dates[0]:dates[-1],:]
def getDailyURLS(date):
month=date.split('-')[0]
day=date.split('-')[1]
year=date.split('-')[2]
url = 'https://www.basketball-reference.com/boxscores/?month=%s&day=%s&year=%s' %(month,day,year)
r = requests.get(url)
soup = BeautifulSoup(r.text, 'lxml')
# Find which teams are playing #
teamtables = soup.findAll('table', {'class': 'teams'})
teamlist=[]
for tbl in teamtables:
tbody = tbl.find('tbody')
trlist=[]
for tr in tbody.findAll('tr'):
trlist.append(tr)
for row in trlist:
for a in row.findAll('a'):
teamlist.append(a.text)
teamlist[:] = (value for value in teamlist if value != 'Final')
with open('/home/Jon2Anderson/nba/boxScoreScrape/teamnames/nbateamnames.json') as json_file:
teamnamedict = json.load(json_file)
teamsthatplayed = [teamnamedict.get(item,item) for item in teamlist]
listofteams=teamsthatplayed
gamelist=[]
while len(teamsthatplayed)>1:
gamelist.append(teamsthatplayed[0:2])
teamsthatplayed.pop(0)
teamsthatplayed.pop(0)
data = soup.findAll('p', {'class': 'links'})
i=0
urls=[]
for game in data:
first=str(data[i])
start="href=\""
end="\">Box"
url=(first[first.find(start)+len(start):first.rfind(end)])
base="https://www.basketball-reference.com"
url = base + url
urls.append(url)
i=i+1
tuplelist=[]
for i in range(len(urls)):
tuplelist.append((urls[i],gamelist[i]))
return(tuplelist)
def scrapeVipMarket5():
# UTF-8 support
reload(sys)
sys.setdefaultencoding('utf-8')
now = datetime.now()
down = Downloader('http://www.vipmarket5.mk/search/')
content = down.get_content()
html = unicode(content)
linkovi = xpath.search(html, '//tr[@class="frame_content"]')
ads = []
for l in linkovi:
link = "http://www.vipmarket5.mk" + xpath.get(l, '//div[@style="width:365px; height:90%; margin-top:10px;"]/b/a/@href')
title = xpath.get(l, '//div[@style="width:365px; height:90%; margin-top:10px;"]/b/a')
imageUrl = xpath.get(l, '//div[@style="overflow:hidden; width:150px; height: 146px; margin: 5px;"]/a/img/@src')
download = Downloader(link)
cont = download.get_content()
cont = unicode(cont)
description = xpath.get(cont, '//div[@class="feature"]/p').strip()
if description == "":
description = "/"
#VNIMANIE! NEMA KATEGORII
category="/"
subcategory="/"
price = xpath.get(l, '//div[@style="margin-top:5px; margin-left:10px;height:155px; overflow:hidden;"]/h4/a')
if price == u"Цена:По договор":
value = "/"
currency = "/"
else:
price = price.split(":")
price = price[1]
price = price.split(" ")
value = price[0]
if price[1]=="€":
currency = "EUR"
elif price[1]=="ден.":
currency = "MKD"
date = xpath.get(l, '//b[@style="font-weight:bold;"]')
date = date.split(": ")
date = date[1]
date = date.split(".")
date = date[2]+"-"+date[1]+"-"+date[0]
country = u"Македонија"
region = xpath.get(cont, '//div[@style="float:left; width: 140px; overflow:hidden; font-family: Tahoma,Geneva,sans-serif; font-weight:bold"]')
if region == "":
region = "/"
ad = Ad(link, title, imageUrl, description, category, subcategory, value, currency, region, date, country)
ads.append(ad)
return adsToJson(ads)
#print scrapeVipMarket5()
def get_date_from_afvaltype(self, data, afvalnaam):
try:
date = data["datum"]
day = date.split()[1]
month = MONTH_TO_NUMBER[date.split()[2]]
year = str(datetime.today().year if datetime.today().
month <= int(month) else datetime.today().year + 1)
return year + "-" + month + "-" + day
except Exception as exc:
_LOGGER.warning(
"Something went wrong while splitting data: %r. This probably means that trash type %r is not supported on your location",
exc, afvalnaam)
return ""
def getAllFromEsumXML(tree, uid):
list_tags=['Authors','ArticleIds']
doc_summary = tree.find('DocumentSummarySet').find('DocumentSummary')
rec={}
columns=["uid"]
values=[uid]
for child in doc_summary:
if child.tag == 'Authors':
authorIDs=extractAuthors(child, uid)
elif child.tag == 'ArticleIds':
artcolumns, artvalues=extractArticleIds(child)
for i in range(len(artcolumns)):
if child.text!=None and not ("\n") in child.text and child.text!="null":
rec[artcolumns[i]]=artvalues[i]
columns.append(artcolumns[i])
values.append(artvalues[i].replace("'",""))
elif child.text!=None and not ("\n") in child.text and child.text!="null":
rec[child.tag] = child.text
columns.append(child.tag)
values.append(child.text.replace("'","").replace('"',""))
if child.tag=="FullJournalName":
journalid=check_insert_select("id", "journals", ("name",), (child.text.replace("'","").replace('"',""),))[0][0]
columns.append("journalid")
values.append(journalid)
values.append( values[columns.index("PubDate")])
columns.append( "PubDateString")
#logging.debug(columns, "columns")
#logging.debug(values, "values")
try:
check_insert("uid","papers", tuple(columns),tuple(values))
except psycopg2.DataError:
if (values[columns.index("PubDate")].find("-")!=-1):
date=values[columns.index("PubDate")][0:values[columns.index("PubDate")].index("-")]
else:
date=values[columns.index("PubDate")]
if len(date.split())==1:
date=date+" Jan"
if len(date.split())==2:
date=date+" 01"
try:
date=datetime.strptime(date,'%Y %b %d').strftime('%Y %m %d')
except ValueError:
date=datetime.strptime(date.split()[0]+" Jan 01", '%Y %b %d').strftime('%Y %m %d')
values[columns.index("PubDate")]=date
check_insert("uid","papers", tuple(columns),tuple(values))
return rec
def parse_date(date):
hora = date.split('_')[1]
date = date.split('_')[0].split('-')
year = date[0]
month = date[1]
day = date[2]
if month[0] == '0':
month = month[1]
if day[0] == '0':
day = day[1]
final_date = year + '-' + month + '-' + day + '_' + hora
return final_date
def fix_date(date):
# Get rid of eg. 2008-06-26T08:30:00
if "T" in date:
date=date.split("T")[0]
elif date == "Varies by indicator":
return ''
elif "00:00:00" in date:
date=date.split('00:00:00')[0]
try:
valid_date = time.strptime(date, '%Y-%m-%d')
return date
except ValueError:
#print 'Invalid date!', date
return ''
def validateDate(date):
vd = dateType(date)
if vd > 0:
if vd == 1:
return date
elif vd == 2:
ds = date.split('-')
return ds[2]+'-'+ds[1]+'-'+ds[0]
else:
ds = date.split('-')
months = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']
return ds[2]+'-'+str(months.index(ds[0])+1)+'-'+ds[1]
else:
print('Wrong date. Input date in one of possible formats: YYYY-MM-DD, or DD-MM-YYYY or MMM-DD-YYYY (eg 2014-12-22, 22-12-2014 or Dec-22-2014)')
return ''
def reschedule_termly_polls(date):
#enable script in case its disabled
Script.objects.filter(slug='emis_school_administrative').update(enabled=True)
#first destroy all existing script progress for head teachers in annual script
ScriptProgress.objects.filter(connection__contact__groups__name__iexact='head teachers',\
script__slug='emis_school_administrative').delete()
reporters = EmisReporter.objects.filter(groups__name__iexact='head teachers')
# Schedule annual messages
d = datetime.datetime.now()
dl = date.split('-')
new_time = datetime.datetime(int(dl[0]), int(dl[1]), int(dl[2]), d.hour, d.minute, d.second, d.microsecond)
for reporter in reporters:
connection = reporter.default_connection
sp = ScriptProgress.objects.create(connection=connection, script=Script.objects.get(slug='emis_school_administrative'))
sp.set_time(new_time)
#now the smcs termly scripts
Script.objects.filter(slug='emis_smc_termly').update(enabled=True)
#first destroy all existing script progress for smcs in their termly script
ScriptProgress.objects.filter(connection__contact__groups__name__iexact='smc',\
script__slug='emis_smc_termly').delete()
reporters = EmisReporter.objects.filter(groups__name__iexact='smc')
for reporter in reporters:
connection = reporter.default_connection
sp = ScriptProgress.objects.create(connection=connection, script=Script.objects.get(slug='emis_smc_termly'))
sp.set_time(new_time)
def diurnalCompute(emails, PLOT=False):
'''Diurnal plot of all emails, with years on x axis and time of day on y axis.
Input must be a list of emails of class HeaderParser, with the key 'Date' containing
the date.
Outputs the (year,month,day), (Hour, minute second) '''
xday = []
ytime = []
#for i in range(len(headers)):
for email in emails:
try:
date = email['Date']
_temp = date.split(',')
_temp[0] = _temp[0].strip()
email = ', '.join(_temp)
timestamp = mktime(parsedate(date))
mailstamp = datetime.fromtimestamp(timestamp)
xday.append(mailstamp)
# Time the email is arrived
# Note that years, month and day are not important here.
y = datetime(2010,10,14,
mailstamp.hour, mailstamp.minute, mailstamp.second)
ytime.append(y)
except Exception as e:
print email
print e
#return headers[i]
#figure(figsize=(20,8))
#plot_date(xday,ytime,'.',alpha=.7)
#xticks(rotation=30)
if PLOT:
diurnalPlot(xday, ytime)
return xday, ytime
def get_flights_mobile(request):
date = request.GET.get("date")
if not date:
py_date = datetime.now()
else:
YYMMDD = date.split("-")
py_date = datetime.now().replace(year=int(YYMMDD[0]), month=int(YYMMDD[1]), day=int(YYMMDD[2]))
dest = request.GET.get("dest")
if not dest:
dest = ".*"
limit = request.GET.get("limit")
if not limit:
limit = 5
flights = Flight.objects.filter(destination__iregex=dest, flight_date__gte=py_date).order_by('flight_date')[:limit]
print "HERE"
flights_dict = {}
flights_arr = []
for f in flights:
flights_arr.append({
"flight_number": f.flight_number,
"flight_date": f.flight_date,
"destination": f.destination,
"status": f.status
})
flights_dict['flights'] = flights_arr
flights_dict['date'] = py_date
return JsonResponse(flights_dict)
def get_id_period (self, date):
from_iso_dt, to_iso_dt = util.inc_dt(date.strftime(util.ISO8601_DATE), util.ISO8601_DATE, self.PERIOD_TYPE)
from_dt = util.get_dt(from_iso_dt, util.ISO8601_DATE)
to_dt = util.get_dt(to_iso_dt, util.ISO8601_DATE)
response = self.br.open(self.search_url)
fields = {}
date = date.strftime(self.request_date_format)
date_parts = date.split('/')
#fields [self.date_from_field['day']] = date_parts[0]
fields [self.date_field_from['month']] = date_parts[1]
fields [self.date_field_from['year']] = date_parts[2]
util.setup_form(self.br, self.search_form, fields )
if self.DEBUG: print self.br.form
response = util.submit_form(self.br)
final_result = []
if response:
html = response.read()
url = response.geturl()
result = scrapemark.scrape(self.scrape_ids, html, url)
if result and result.get('records'):
self.clean_ids(result['records'])
final_result.extend(result['records'])
if final_result:
return final_result, from_dt, to_dt
else:
return [], None, None # monthly scraper - so empty result is always invalid
def delete_tweets_from_archive_until_year( filename_archive, tweets_year, tweets_month ):
global APP_API
FILE_PATH = APP_PATH+'/'+filename_archive
if not os.path.exists( FILE_PATH ):
print 'TWEETS: Das twitter-Archiv in '+FILE_PATH+' ist nicht vorhanden.'
return
if not is_api_configured():
return
# get list of ids to destroy from zip file
result_array = tweets_extract_ids_from_zipfile( filename_archive, tweets_year, tweets_month )
tweet_ids = result_array[0]
num_to_delete = result_array[1]
# sort in reversed order
tweet_ids_sorted = sorted( tweet_ids.keys(), reverse=True )
print "TWEETS: There are %d tweets to delete." % num_to_delete
estimated_time_needed = estimated_time_of_arrival( num_to_delete )
print "TWEETS: Deletion will take an estimated %s to finish." % estimated_time_needed
continue_deleting = query_yes_no( "TWEETS: REALLY DELETE ALL TWEETS NOW?", default="no" )
if not continue_deleting:
print "TWEETS: Aborted deleting."
return
begin = False
num_deleted = 0
for date in tweet_ids_sorted:
year, month = date.split("/") # not really used
num_to_delete_month = len( tweet_ids[date] )
num_deleted_month = 0
print "TWEETS: Deleting %s tweets of: %s" % ( str( num_to_delete_month ), date )
for tid in tweet_ids[date]:
if begin or last == 0 or tid == last:
begin = True
error_counter = 0
while True:
try:
APP_API.DestroyStatus(tid)
num_deleted += 1
num_deleted_month += 1
print "TWEETS: %d DELETED %d/%d of %d/%d (MONTH/TOTAL)" % ( tid, num_deleted_month,num_deleted, num_to_delete_month, num_to_delete )
break
except twitter.error.TwitterError, e:
try:
message = e.message[0]['message']
retry = False
except:
message = repr( e.message )
retry = True
print "TWEETS: %d ERROR %s %d/%d of %d/%d (MONTH/TOTAL)" % (tid, message, num_deleted_month,num_deleted, num_to_delete_month, num_to_delete)
error_counter += 1
if error_counter > 5:
print "TWEETS: Too many errors, aborting!"
exit(1)
if not retry:
break # exit endless while loop
def calendar_change_date():
date = request.form['new_date']
date_chunks = date.split(' ')
date = date_chunks[1] + ' ' + date_chunks[2] + ' ' + date_chunks[3]
new_date = datetime.datetime.strptime(date, "%b %d %Y")
# Send them to the new day
return redirect(url_for('.home', date=new_date, teacherset=request.form['teacherset']))
def reshape_date(date):
# ~시간전, ~분전, ~초전 시간 고치기
if re.search('전', date):
if re.search('시간', date):
date = datetime.now() - timedelta(hours=int(date.split("시간")[0]))
date = date.strftime("%Y-%m-%d")
elif re.search('분', date):
date = datetime.now() - timedelta(minutes=int(date.split("분")[0]))
date = date.strftime("%Y-%m-%d")
elif re.search('초', date):
date = datetime.now() - timedelta(seconds=int(date.split("초")[0]))
date = date.strftime("%Y-%m-%d")
else:
date = datetime.strptime(date, "%Y.%m.%d")
date = date.strftime("%Y-%m-%d")
return date
def parse_details(self, response):
# print 'parse_details'
url = response.url
title = response.xpath(
'//div[@id="art_header"]/h1[@class="title"]/text()').extract_first(
)
texts = response.xpath(
'//div[@id="art_start"]/p/text() | //div[@id="art_start"]/div/text() | //div[@id="art_start"]/a/b/text() | //div[@id="art_start"]/text()'
).extract()
article = u''.join(texts)
date = response.xpath(
'//div[@class="art_author"]/text()').extract_first()
(day, month, year) = date.split()[0:3]
#print day, type(month), year
articleDate = makeStdDate(day, month, year)
# print '>1>',articleDate, strToday,(articleDate == strToday)
# if (articleDate == strToday):
yield {
'url': url,
'title': title,
'text': article,
'date': strToday #articleDate
}
def check_humandate(date):
"""
'humandate' must be a human-readable date with a 3-letter month
and 4-digit year. Examples include 'Feb 18-20, 2025' and 'Feb 18
and 20, 2025'. It may be in languages other than English, but the
month name should be kept short to aid formatting of the main
Software Carpentry web site.
"""
if ',' not in date:
return False
month_dates, year = date.split(',')
# The first three characters of month_dates are not empty
month = month_dates[:3]
if any(char == ' ' for char in month):
return False
# But the fourth character is empty ("February" is illegal)
if month_dates[3] != ' ':
return False
# year contains *only* numbers
try:
int(year)
except:
return False
return True
def convert_str_datetime(date: str, pattern: str):
if pd.isnull(date):
return DateTimeUtils.datetime_default
if "T" in date:
return datetime.strptime(date.split("T")[0], pattern)
else:
return datetime.strptime(date, pattern)
def get_date(self , date):
""" Returns a date in Bhav Website compatible format """
date_list = date.split('-')
date_list[1] = str(int(date_list[1]))
date_list[2] = str(int(date_list[2]))
return date_list[0] + '-' + date_list[1] + '-' + date_list[2]
def dateToDatetime(date):
if date:
date = date.split('/')
date = datetime.datetime(int(date[2]), int(date[0]), int(date[1]))
current_tz = timezone.get_current_timezone()
date = date.astimezone(current_tz)
return date
def is_date(date):
'''
# Функция принимает на вход строку с датой
# Возвращает True, еслли дата корректна, False если не корректна
# Для примера возьмём дату "1995-04-30"
'''
# Разбиваем дату разделителем "-", фукнция split возвращает список
# Если дата корректна, список будет вида ["YYYY","MM","DD"]
date_splitted = date.split("-")
# Для начала, длина списка должна быть равной 3
if len(date_splitted) == 3:
# Теперь запишем в переменные year, month, day элементы списка date_splitted
year, month, day = date_splitted
# Теперь просто проверим, что строка с годом имеет длину 4, строки с месяцем и днём длину 2
if len(year) == 4 and len(month) == 2 and len(
day) == 2 and int(month) < 13 and int(month) > 0 and int(
day) > 0 and int(day) < 32:
# Дата нам подходит
return True
else:
# Иначе дата нам не подходит
return False
else:
# Иначе дата не подходит
return False
def store_holiday():
d = datetime.strptime('0001-1-1','%Y-%m-%d')
r = requests.get("https://isthemarketopen.com/")
soup = BeautifulSoup(r._content)
find = soup.find_all("font")
date = ""
for link in find:
if "clos" in link.text.lower():
date = (link.text.split("-")[1][1:].lower())
year = date.split(",")[1][1:]
day = date[date.index(",")-2: date.index(",")]
# if "jan" in date:
#
# elif "feb" in date:
#
# elif "april" in date:
#
# elif "may" in date:
#
# elif "june" in date:
#
if "july" in date.lower():
d = datetime.strptime(str(year+"-"+str(7)+"-"+day), '%Y-%m-%d')
# elif "aug" in date:
#
# elif "sep" in date:
#
# elif "oct" in date:
#
# elif "nov" in date:
#
# elif "dec" in date:
print(d.strftime("%Y-%m-%d"))
def checkquery(self, location=None, date=None, islog=False):
datesplit = date.split(',')
if len(datesplit) <= 1:
period = timedelta(days=1)
datef0 = datetime.strptime(datesplit[0], "%Y-%m-%d")
datef1 = datef0 + period
datef0str, datef1str = datef0.strftime(
'%Y-%m-%d %X'), datef1.strftime('%Y-%m-%d %X')
else:
period = timedelta(days=1)
datef0 = datetime.strptime(datesplit[0], "%Y-%m-%d")
datef1 = datetime.strptime(datesplit[1], "%Y-%m-%d") + period
datef0str, datef1str = datef0.strftime(
'%Y-%m-%d %X'), datef1.strftime('%Y-%m-%d %X')
timeperiod = (datef0str, datef1str)
query = {
'siteName': location,
'log_time': {
'$gte': timeperiod[0],
'$lte': timeperiod[1]
}
}
try:
if islog is False:
self.airdata.find(query)[0]
find_result = self.airdata.find(query)
else:
self.datalog.find(query)[0]
find_result = self.datalog.find(query)
except IndexError:
find_result = None
finally:
self.client.close()
# the return of this method is a mongodb cursor object or None object
return find_result
def gedcomDateToUnixTimestamp(date):
dateArray = date.split(' ')
month = MONTHS[dateArray[1]]
day = dateArray[0]
year = dateArray[2]
timeString = '{0}/{1}/{2}'.format(day, month, year)
return time.mktime(datetime.strptime(timeString, '%d/%m/%Y').timetuple())
def join_files(data_path, out_path='./'):
"""
Joins all the Detector Health Detail files in the directory into one big csv and dataframe.
Args:
dir (str) = path to data directory
out_path (str) = path to the directory where you want to save the csv
"""
fnames = os.listdir(data_path)
# Count the rows
r = 0
start_path = os.getcwd()
os.chdir(data_path) # change cwd to data dir
for name in fnames:
with open(name, 'r') as f:
f.next() # skip header
for line in f: r+=1
# Iitialize the output df
temp = pd.read_csv(fnames[0], sep='\t')
h = list(temp.columns) # header labels
df = pd.DataFrame(index=np.arange(0,r), columns=['Date']+h)
# Read all the files and combine into one dataframe
i=0
#TODO Find a faster way to do this loop.
for name in fnames:
date = name.split('_health')[0] # YYYY_MM_DD
with open(name,'r') as f:
f.next() # skip header
for line in f:
df.iloc[i,:] = [date] + line.split('\t')
i += 1
os.chdir(start_path) # change back to original dir
df.to_csv(out_path+date.split('_')[0]+'_joined_health_detail.csv')
return df
def isWeekday(self, date):
dates = date.split('-')
if len(dates) == 3:
# if calendar.weekday(int(dates[0]),int(dates[1]),int(dates[2])) < 5:
if self.isDayOfWeek(date,5) == 0 and self.isDayOfWeek(date,6) == 0:
return 1
return 0
def statistical_temperature_query_by_initial_date(date):
date_parts = date.split('-')
start_date = dt.date(int(date_parts[0]), int(date_parts[1]),
int(date_parts[2]))
session = Session(engine)
station_temperature = session.query(
func.max(Measurement.tobs).label("highest_temperature"),
func.avg(Measurement.tobs).label("average_temperature"),
func.min(Measurement.tobs).label("lowest_temperature")).filter(
Measurement.date >= start_date)
session.close()
results = station_temperature.one()
highest_temperature = results.highest_temperature
lowest_temperature = results.lowest_temperature
average_temperature = results.average_temperature
list = []
list.append({"Highest temperature": highest_temperature})
list.append({"Lowest temperature": lowest_temperature})
list.append({"Average temperature": average_temperature})
return jsonify(list)
def check_valid_date(date):
""" Verifica que la fecha tenga el formato correcto
:param date:
:return: año, mes, dia
:rtype: tuple
"""
if not isinstance(date, str):
# raise ValueError("La date no es del tipo string")
return False
split = date.split("-")
m = int(split[0])
d = int(split[1])
if m < 1 or m > 12:
raise ValueError(
"Error en {}: El mes debe ser mayor a 1 y menor a 12".format(
date))
# return False
maxday = Season.month_day[m]
if d < 1 or d > maxday:
raise ValueError(
"Error en {}: En el mes {} el dia debe ser menor a {}".format(
date, m, maxday))
# return False
return m, d
def export_users_csv_date(request):
response = HttpResponse(content_type='text/csv')
response['Content-Disposition'] = 'attachment; filename=" Custom Report.csv"'
date = request.POST.get('date')
tobepassed=""
global datel
if(date!=None):
date = date.split('/')
tobepassed+= date[2] + "-" + date[0] + "-" + date[1]
datel.append(tobepassed)
print(datel)
writer = csv.writer(response)
writer.writerow(['Entry No.','Name','Entry Time','Entry Date', 'Exit Time', 'Phone', 'Email', 'Address', 'Purpose', 'Identity', 'If Other then Specify', 'Reference ID','Aadhar','Section to be Visited ','Image Name As Taken on Device','Reference Person Name','Reference Person Contact'])
print("here")
passv=""
if len(datel)!=0:
passv+=datel[len(datel)-1]
users = visitor.objects.filter(dateofentry=passv).values_list()
for user in users:
writer.writerow(user)
if request.method=="GET":
while(len(datel)!=0):
datel.pop(0)
return response
def Single_Day_Inquriy_Obs(self, date):
"""
Takes argument date format Jan 01 2021
"""
date = date.split()
new_date = date[0] + date[1] + date[2]
results = self.collectiondayhist.find({"Date": new_date})
High = self.Preferences.HighTemp()
Low = self.Preferences.LowTemp()
Rainfall = self.Preferences.Rainunit()
Snowfall = self.Preferences.Snowunit()
TempUnit = self.Preferences.UnitT()
PreUnit = self.Preferences.UnitP()
for x in results:
High = str(x[High]) + TempUnit
Low = str(x[Low]) + TempUnit
if str(x[Rainfall]) == "Trace amount":
Rain = "Trace amount"
if str(x[Rainfall]) != "Trace amount":
Rain = str(x[Rainfall]) + " " + PreUnit
if str(x[Snowfall]) == "Trace amount":
Snow = "Trace amount"
if str(x[Snowfall]) != "Trace amount":
Snow = str(x[Snowfall]) + " " + PreUnit
WDate = date[0] + " " + date[1] + " " + date[2]
Webreturn = {
"Date": WDate,
"High": High,
"Low": Low,
"Rainfall": Rain,
"Snowfall": Snow
}
return Webreturn
def day_menu():
options = {'1': ('Today', Menu.aut_menu)}
# add 4 prior days to options
for i in range(1, 5):
formdate = Menu.DATE + timedelta(days=-i)
options[str(i + 1)] = (formdate.strftime('%m/%d/%Y'),
Menu.ini_menu)
options['6'] = ('Archive', Menu.ini_menu)
options['9'] = ('Back', Menu.back)
print('###############')
print('# {haz} -{sec}- #'.format(
haz='Winter' if Menu.obs['haz'][0] == '2' else 'Severe',
sec=Menu.obs['sec'][0]))
print('# ' + Menu.DATE.strftime('%m/%d/%Y') + ' #')
print('###############')
print()
print('Select Day')
sel = Menu.show_menu(options)
# if archive day selected, get date
if sel == '6':
Menu.archive = True
print('\nEnter the Archive date (mm/dd/yyyy):')
date = input('\n>> ')
date = date.split('/')
Menu.obs['day'] = datetime.datetime(int(date[2]), int(date[0]),
int(date[1]))
else:
Menu.obs['day'] = Menu.DATE + timedelta(days=-(int(sel) - 1))
return options[sel][1]()
def get_day_number(date):
days = [31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31]
date = date.split("-")
month = int(date[1])
res = sum(days[:month - 1])
res = res + int(date[2])
return res
def Single_Day_Inquiry_Hourly_Obs(self, date):
"""
Take argument date format Jan 02 2021 1 PM
"""
date = date.split()
Date = date[0] + date[1] + date[2]
time = self.time_convert(date[3], date[4])
Precipitation = self.Preferences.Precipunit()
Temp = self.Preferences.Temp()
results = self.collectionhourhist.find({"Date": Date, "Time": time})
TempUnit = self.Preferences.UnitT()
PreUnit = self.Preferences.UnitP()
for x in results:
Temp = str(x[Temp]) + TempUnit
Precip = str(x[Precipitation])
if str(x[Precipitation]) == "No precipitation":
Precip = "No precipitation"
if str(x[Precipitation]) == "Trace amount":
Precip = "Trace amount"
if str(x[Precipitation]) != "No precipitation" and str(
x[Precipitation]) != "Trace amount":
Precip = str(x[Precipitation]) + " " + PreUnit
time_per = date[0] + " " + date[1] + " " + date[2] + " " + time
Webreturn = {"Date": time_per, "Temp": Temp, "Precipitation": Precip}
return Webreturn
def check_humandate(date):
"""
'humandate' must be a human-readable date with a 3-letter month
and 4-digit year. Examples include 'Feb 18-20, 2025' and 'Feb 18
and 20, 2025'. It may be in languages other than English, but the
month name should be kept short to aid formatting of the main
Software Carpentry web site.
"""
if ',' not in date:
return False
month_dates, year = date.split(',')
# The first three characters of month_dates are not empty
month = month_dates[:3]
if any(char == ' ' for char in month):
return False
# But the fourth character is empty ("February" is illegal)
if month_dates[3] != ' ':
return False
# year contains *only* numbers
try:
int(year)
except:
return False
return True
def date_to_timestamp(date):
date = date.split('/')
if len(date) == 3:
if len(date[2].strip()) == 2:
date[2] = '19'+date[2].strip()
return time.mktime((int(date[2]), int(date[1]), int(date[0]), 0,0,0,0,0,-1))
else:
return False
def calendar_change_date_teacher():
date = request.form['new_date']
current_teacher = request.form['current_teacher']
date_chunks = date.split(' ')
date = date_chunks[1] + ' ' + date_chunks[2] + ' ' + date_chunks[3]
new_date = datetime.datetime.strptime(date, "%b %d %Y").date()
# Send them to the new day
return redirect(url_for('.filter_teachers', date=new_date, current_teacher=current_teacher))
def split_datetime_range(date):
if isinstance(date,(tuple,list)):
d0,d1 = date
elif isinstance(date, (str,unicode)) and date.find('~')>=0:
d0,d1 = date.split('~')
else:
d0,d1 = date, date
return d0, d1
def date_time(date):
db_date = date.split(" ")
hours = db_date[1].split(".")
hours = hours[0]
if hours > "00:00:01" and hours < "05:59:59":
current_date=datetime.strptime(date, "%Y-%m-%d %H:%M:%S.%f") + timedelta(days=-1)
current_date.strftime("%Y-%m-%d %H:%M:%S.%f")
return current_date
return date
def parse_date(date=None, default=None):
if date is None:
if default is None:
default = datetime.today()
return default
year, month, day = [int(x) for x in date.split('-')]
return datetime(year=year, month=month, day=day)
def get_date(date):
#this function returns the date in "date" format
split_date = date.split("-")
return_date = []
if len(split_date) > 0:
year = int(split_date[0])
month = int(split_date[1])
day = int(split_date[2].split(" ")[0])
return_date = [year, month, day]
return return_date
def getDateStats(dt):
if "T" in dt:
date, time = dt.split("T")
else:
date, time = dt.split(" ")
time = time.split(".")[0]
yr, m, d = map(int, date.split("-"))
h, minute, s = map(int, map(float, time.split(":")))
return (yr, m , d, h, minute)
def get_archive_date():
''' Get date of latest archive files on USAspending.gov
'''
url = 'https://apps.usaspending.gov/DownloadCenter/AgencyArchive'
d = pq(url)
date = d('#ResultsTable').find('tr').eq(1).find('td').eq(3).text()
date = date.split('/')
date = date[2]+date[0]+date[1]
return date
def get_archive_date():
""" Get date of latest archive files on USAspending.gov
"""
url = "https://apps.usaspending.gov/DownloadCenter/AgencyArchive"
d = pq(url)
date = d("#ResultsTable").find("tr").eq(1).find("td").eq(3).text()
date = date.split("/")
date = date[2] + date[0] + date[1]
return date
def is_valid_date(date):
#mm-dd-yyyy
try:
date = date.split('/')
if (int(date[0]) > 0 and int(date[0]) <= 12) and (int(date[1]) > 0 and int(date[1]) <= 31) and (int(date[2])>= 1900 and int(date[2]) <= 2300):
return '/'.join(date)
else:
return ''
except:
wrong_date.append(date)
return ''
def get_current_date(self):
curDate=str(datetime.datetime.utcnow() + datetime.timedelta(hours=-8))
date=curDate.split(' ')
date=date[0]
date=date.split('-')
to_return={}
to_return['year']=date[0]
to_return['month']=date[1]
to_return['day']=date[2]
return to_return
