def get_tracking_by_courier(courier_link):
url = courier_link
r = requests.get(url)
data = r.text
soup = BeautifulSoup(data)
recent = soup.find_all('li',{'class':'checkpoint'})
if len(recent) <= 0:
status_text = soup.find('p',{'id':'status-text'})
print status_text
if status_text:
return 0
return None
recent = recent[0]
place = recent.find('div',{'class':'checkpoint__content'}).find('div',{'class':'hint'}).get_text()
datetime = recent.find('div',{'class':'checkpoint__time'})
date = datetime.find('strong').get_text()
tag = soup.find('p',{'class':'tag'}).get_text()
time = datetime.find('div',{'class':'hint'}).get_text()
if tag == "In Transit":
tag_th = u"กำลังจัดส่ง"
elif tag == "Delivered":
tag_th = u"ผู้รับได้รับเรียบร้อย"
elif tag == "Out For Delivery":
tag_th = u"เตรียมการนำจ่าย"
elif tag == "Info Received":
tag_th = u"รับเข้าระบบ"
else:
tag_th = u""
time = datetime.find('div',{'class':'hint'}).get_text()
return {"place": place, "date":date, "time":time, "tag":tag, "tag_th" :tag_th}
def cvt_dt(self, dt):
if type(dt) == str:
if dt.upper() == "FIRST":
return dt.datetime.fromtimestamp(0)
elif dt.find('/') >= 0:
return dt.datetime.strptime(dt, self.time_fmt)
else:
return dt.datetime.fromtimestamp(float(start))
elif type(dt) == float or type(dt) == int:
return dt.datetime.fromtimestamp(dt)
def get_tracking(tracking_id):
url = "https://track.aftership.com/" + tracking_id
r = requests.get(url)
data = r.text
soup = BeautifulSoup(data)
recent = soup.find_all('li', {'class': 'checkpoint'})
if len(recent) <= 0:
status_text = soup.find('p', {'id': 'status-text'})
if status_text:
return 0
return None
recent = recent[0]
courier = soup.find('div', {'class': 'courier-info'}).find('h2').get_text()
place = recent.find('div', {
'class': 'checkpoint__content'
}).find('div', {
'class': 'hint'
}).get_text()
datetime = recent.find('div', {'class': 'checkpoint__time'})
date = datetime.find('strong').get_text()
tag = soup.find('p', {'class': 'tag'}).get_text()
if tag == "In Transit":
tag_th = u"กำลังจัดส่ง"
elif tag == "Delivered":
tag_th = u"ผู้รับได้รับเรียบร้อย"
elif tag == "Out For Delivery":
tag_th = u"เตรียมการนำจ่าย"
elif tag == "Info Received":
tag_th = u"รับเข้าระบบ"
else:
print tag
tag_th = u""
time = datetime.find('div', {'class': 'hint'}).get_text()
return {
"courier": courier,
"place": place,
"date": date,
"time": time,
"tag": tag,
"tag_th": tag_th
}
def dateTimeParcer(dt):
if(dt.find(" ") == -1):
print("fail")
else:
datetime = dt
if not datetime.find("{") == -1:
datetime = datetime[datetime.index("{") + 1:len(datetime)]
if not datetime.find("}") == -1:
datetime = datetime[0:datetime.index("}")]
d = datetime.index(" ")
date = datetime[0:d]
date = date.strip(" ")
datetime2 = datetime[d + 1:len(datetime)]
d2 = datetime2.index(" ")
time = datetime2[0:d2]
time = time.strip(" ")
time = time + ":00"
timezone = datetime2[d2:len(datetime2)]
timezone = timezone.strip(" ")
timezone = timezone.strip("(")
timezone = timezone.strip(")")
return [date, time, timezone]
def get_tracking_all(tracking_id):
url = "https://track.aftership.com/"+tracking_id
r = requests.get(url)
data = r.text
soup = BeautifulSoup(data)
multi_courier = soup.find_all('a',{'class':'courier-detection__courier-link'});
multi_courier_return = []
if multi_courier:
for courier in multi_courier:
multi_courier_return.append({"name":courier.get_text(),"link": "https://track.aftership.com"+courier['href']})
return multi_courier_return
recent = soup.find_all('li',{'class':'checkpoint'})
if len(recent) <= 0:
status_text = soup.find('p',{'id':'status-text'})
print status_text
if status_text:
return 0
return None
courier = soup.find('div',{'class':'courier-info'}).find('h2').get_text()
recent = recent[0]
place = recent.find('div',{'class':'checkpoint__content'}).find('div',{'class':'hint'}).get_text()
datetime = recent.find('div',{'class':'checkpoint__time'})
date = datetime.find('strong').get_text()
tag = soup.find('p',{'class':'tag'}).get_text()
if tag == "In Transit":
tag_th = u"กำลังจัดส่ง"
elif tag == "Delivered":
tag_th = u"ผู้รับได้รับเรียบร้อย"
elif tag == "Out For Delivery":
tag_th = u"เตรียมการนำจ่าย"
elif tag == "Info Received":
tag_th = u"รับเข้าระบบ"
else:
tag_th = u""
time = datetime.find('div',{'class':'hint'}).get_text()
return {"courier": courier, "place": place, "date":date, "time":time, "tag":tag, "tag_th" :tag_th}
def download_quote_xls():
init()
_xls = _download_quote_xls()
if not _xls:
return
data = xlrd.open_workbook(_xls) #注意这里的workbook首字母是小写
sheet = data.sheet_names()[0]
table = data.sheet_by_name(sheet)
# ['数据更新时间', '12-25 15:15:12', '', '', '', '', '', '', '', '', '', '', '']
update_day = table.row_values(0)[1].split()[0]
dt = str(datetime.date.today())
if dt.find(update_day) < 0:
os.remove(_xls)
print('not today, xls removed')
return
return _xls
def mobile(settings):
BCOST = settings["BCOST"]
# коэффициент звонков до 0:30
ACOST = settings["ACOST"]
# коэффициент СМС
SMSCOST = settings["SMSCOST"]
# Время, отноительно которого изменяется коэффциент
TIMECONST = settings["TIMECONST"]
# номер из варианта 7
DEFAULT_PHONE = settings["DEFAULT_PHONE"]
input_filename = settings["input_filename"]
# Считываем данные из файла
mas = []
with open(input_filename) as cdr:
for line in cdr:
mas.append(line[:len(line) - 1].split(','))
phone = DEFAULT_PHONE
# если не введен другой номер, используется номер из варианта 7
if not phone.isdigit():
# print("Введенный номер не соответствует формату.\nБудет протарифицирован номер 933156729")
phone = DEFAULT_PHONE
sum = 0
calls_sum = 0
for line in mas:
# Тарифицируем исходящие звонки и СМС для номера
if line[1] == phone:
datetime = line[0]
time = datetime[datetime.find(":") - 2:]
try:
duration = float(line[3])
# print("Ошибка в call_duration")
except:
sys.exit()
sms = int(line[-1])
if time < TIMECONST:
time = float(
datetime[datetime.find(":") + 1:datetime.rfind(":")]
) + float(datetime[datetime.rfind(":") + 1:]) / 60
# Сколько осталось до 0:30
ost = 30.0 - time
# Если человек начал говорить раньше 0:30, а закончил позже,
# то находим соответствующие промежутки до(ost) и после(after)
if duration > ost:
after = duration - ost
# Считаем стоимость промежутков по соответствующим коэффициентам
calls_sum = ost * BCOST + after * ACOST
else:
# Иначе считаем по коэффициенту до 0:30
calls_sum = duration * BCOST
else:
# Если звонок начался после 0:30, то тарифицируем по коэффициенту после 0:30
calls_sum = duration * ACOST
sum += calls_sum
sms_sum = sms * SMSCOST
sum += sms_sum
elif line[2] == phone:
datetime = line[0]
time = datetime[datetime.find(":") - 2:]
try:
duration = float(line[3])
except:
# print("Ошибка в call_duration")
sys.exit()
if time < TIMECONST:
time = float(
datetime[datetime.find(":") + 1:datetime.rfind(":")]
) + float(datetime[datetime.rfind(":") + 1:]) / 60
# Сколько осталось до 0:30
ost = 30.0 - time
# Если человек начал говорить раньше 0:30, а закончил позже,
# то находим соответствующие промежутки до(ost) и после(after)
if duration > ost:
after = duration - ost
# Считаем стоимость промежутков по соответствующим коэффициентам
calls_sum = ost * BCOST + after * ACOST
else:
# Иначе считаем по коэффициенту до 0:30
calls_sum = duration * BCOST
else:
# Если звонок начался после 0:30, то тарифицируем по коэффициенту после 0:30
calls_sum = duration * ACOST
sum += calls_sum
return round(sum, 2)
def get_quote(xlsfile, dt=None):
#打开excel
data = xlrd.open_workbook(xlsfile) #注意这里的workbook首字母是小写
#查看文件中包含sheet的名称
sheets = data.sheet_names()
sheet = sheets[0]
#得到第一个工作表，或者通过索引顺序 或 工作表名称
table = data.sheets()[0]
table = data.sheet_by_index(0)
table = data.sheet_by_name(sheet)
if not check_format(table.row_values(1)):
raise Exception('xls format changed...')
#获取行数和列数
#nrows = table.nrows
#ncols = table.ncols
#获取整行和整列的值（数组）
#循环行,得到索引的列表
trade_date = None
# ['数据更新时间', '12-25 15:15:12', '', '', '', '', '', '', '', '', '', '', '']
update_day = table.row_values(0)[1].split()[0]
if dt == None:
dt = str(datetime.date.today())
if dt.find(update_day) < 0:
print(dt, update_day, 'not today\'s quote')
#os.remove(xlsfile)
return
trade_date = dt
val_many = []
for rownum in range(table.nrows):
row = table.row_values(rownum)
if not row[0].startswith('s'):
continue
print(row[0])
key_xls = [
'代码', '名称', '最新价', '涨跌幅', '涨跌额', '买入', '卖出', '成交量', '成交额', '今开',
'昨收', '最高', '最低', '日期'
]
key_dict = {
'代码': 'code',
'名称': '',
'最新价': 'close',
'涨跌幅': '',
'涨跌额': '',
'买入': '',
'卖出': '',
'成交量': 'volume',
'成交额': 'turnover',
'今开': 'open',
'昨收': '',
'最高': 'high',
'最低': 'low',
'日期': 'trade_date'
}
row.append(trade_date)
row[0] = row[0][2:]
#AttributeError: 'dict' object has no attribute 'iteritems'
key_list = [
'code', 'trade_date', 'open', 'high', 'low', 'close', 'volume',
'turnover'
]
indice = [0, 13, 9, 11, 12, 2, 7, 8] #subscript
fmt_list = ['%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s']
val_list = []
volume = row[7]
if int(volume) <= 0:
#print(row[0], '停牌')
continue
row[7] *= 100
for i, idx in enumerate(indice):
val_list.append(row[idx])
if key_list[i] != key_dict[key_xls[idx]]:
exit(0)
#print('{0}\t{1}\t{2}'.format(key_list[i], key_xls[idx], row[idx]))
val = tuple(val_list)
val_many.append(val)
# print(sql_str % tuple(val_list))
return val_many
def get_content(html):
soup = BeautifulSoup(html, 'html.parser')
matches = []
table = soup.find('table', class_='table')
desks = table.find_all('tbody', class_='table__body')
#print("Кря_desks:",len(desks))
i = 1
for desk in desks:
flag = 0
#print(" Кря_desk_"+str(i))
i = i + 1
comp = ""
games = []
rows = desk.find_all('tr', class_='table__row')
#print(" Кря_rows:",len(rows))
for row in rows:
if row == rows[0]:
headline = row.find("th")
if headline != None:
comp = headline.find(
"h2", class_='table__title-text').get_text(strip=True)
#print(' Кря_comp: ' + comp)
else:
notmatch = row.find('td', class_='table-complex__wrap')
notlive = row.find('div', class_='table__live')
if (notmatch == None) and (notlive == None):
flag = 1
bothteams = row.find(
'h3',
class_='table__match-title-text').get_text(strip=True)
#print(' Кря: '+bothteams)
team1 = bothteams[:bothteams.find(' — ')]
team2 = bothteams[bothteams.find(' — ') + 3:]
#print(' Кря_teams: '+team1+' : '+team2)
datetime = row.find('div', class_='table__timescore')
str_datetime = datetime.find(has_no_class).get_text(
strip=True)
str_date = str_datetime[:str_datetime.find(' в ')]
date = format_date(str_date)
str_time = str_datetime[str_datetime.find(' в ') + 3:]
time = format_time(str_time)
coefs = row.find_all('td', class_='_type_btn', limit=3)
try:
c1 = float(coefs[0].get_text(strip=True))
cX = float(coefs[1].get_text(strip=True))
c2 = float(coefs[2].get_text(strip=True))
except ValueError:
pass
#print(' Кря_game:',team1,'vs',team2,'|',str_date,str_time,'|','нет коэффициентов')
else:
#print(' Кря_game:',team1,'vs',team2,'|',str_date,str_time,'|',c1,'|',cX,'|',c2)
games.append({
'type': 'game',
'date': date,
'time': time,
'team1': team1,
'team2': team2,
'k1': c1,
'kx': cX,
'k2': c2
})
if flag == 1:
matches.append({'type': 'comp', 'name': comp})
matches.extend(games)
return matches
def get_score_data(url):
"""Return gameId (str), date (date), time (time), location (str),
homeTeam (int), awayTeam (int), homeFinal (int), awayFinal (int),
and playerRows (list) for a given espn game URL.
"""
#initialize variables
rows = []
playerRows = []
html = urllib.urlopen(url).read()
schoolDict = get_schooldict()
homeTeam = -1
awayTeam = -1
gameId = url[url.find('=')+1:]
#main data extraction block
if html:
print "Getting the score data for game " + gameId
soup = BeautifulSoup(html)
#game date
dateElement = soup.find(class_="game-time-location").find("p")
datetime = dateElement.get_text()
time = (datetime[:datetime.find(',')]).encode('utf-8')
time = convert_time(time)
date = (datetime[datetime.find(',')+2:]).encode('utf-8')
#game location
locationElement = dateElement.find_next('p')
location = locationElement.get_text()
#score data
awayFinalElement = soup.find(class_="ts")
awayFinal = awayFinalElement.get_text()
homeFinalElement = awayFinalElement.find_next(class_="ts")
homeFinal = homeFinalElement.get_text()
#find school1
school1 = soup.find(id="my-players-table").find("th")
school1Name = (school1.get_text()).encode('utf-8')
#replace school name with schoolid
if schoolDict.has_key(school1Name):
awayTeam = int(schoolDict[school1Name])
else:
print school1Name + " doesn't exist... adding it..."
add_school(school1Name)
schoolDict = get_schooldict()
awayTeam = int(schoolDict[school1Name])
#Find school1 starter stats
starters = soup.find(id="my-players-table").find("tbody")
for row in starters.find_all('tr'):
rows.append([awayTeam] + [val.text.encode('utf-8') for val in row.find_all('td')] + [1])
#find school1 bench stats
bench = starters.next_sibling.next_sibling
for row in bench.find_all('tr'):
rows.append([awayTeam] + [val.text.encode('utf-8') for val in row.find_all('td')] + [0])
#find school2
school2 = soup.find(id="my-players-table").find("thead")
school2 = school2.find_next_sibling("thead").find_next_sibling("thead").find_next_sibling("thead")
school2Name = (school2.find("th").get_text()).encode('utf-8')
#replace school name with schoolid... if the school doesn't exist, create it
if schoolDict.has_key(school2Name):
homeTeam = int(schoolDict[school2Name])
else:
print school2Name + "doesn't exist... adding it..."
add_school(school2Name)
schoolDict = get_schooldict()
homeTeam = int(schoolDict[school2Name])
#Find school2 starter stats
starters = school2.find_next_sibling("tbody")
for row in starters.find_all('tr'):
rows.append([homeTeam] + [val.text.encode('utf-8') for val in row.find_all('td')] + [1])
#find school2 bench stats
bench = starters.next_sibling.next_sibling
for row in bench.find_all('tr'):
rows.append([homeTeam] + [val.text.encode('utf-8') for val in row.find_all('td')] + [0])
#remove the bad rows
for row in rows:
if (row and row[0] > -1 and len(row) > 10):
playerRows.append([gameId] + row)
#make player position its own field and replace dashes in stats
for row in playerRows:
#split player and position
playerpos = row[2]
commaIndex = playerpos.rfind(',')
if commaIndex == -1:
position = 'N'
player = playerpos
else:
position = playerpos[commaIndex+2:]
player = playerpos[:commaIndex]
row[2] = player
row.insert(3, position)
#handle cases where minutes doesn't exist for the line score... make the minutes -1 for that player
if '-' in row[4]:
row.insert(4, -1)
#make 'of' stats two fields
i = 5
while i < 11:
s1 = row[i][:row[i].index('-')]
s2 = row[i][row[i].index('-')+1:]
if s1 == '':
s1 = 0
if s2 == '':
s2 = 0
row.pop(i)
row.insert(i, s1)
row.insert(i+1, s2)
i = i+2
return gameId, date, time, location, homeTeam, awayTeam, homeFinal, awayFinal, playerRows