德国Umlaute在Python3中的编解码
德国Umlaute在Python3中的编解码
提问于 2019-12-15 17:29:15
我有一个问题，我工作了几个小时，我不能把它修好。我相信这只是一件小事，但不知何故我不知道自己做错了什么。
我的目标是通过json从公共交通公司获取数据，并在显示屏上显示地铁/电车的下一个发车时间。基本上一切正常，但是一旦json返回一个umlaut (比如"ü")，我就会得到一个错误消息。有趣的是:锋利的s(S)有效！
以下是确切的错误信息(应该是"Hütteldorf")：
UnicodeEncodeError('ascii', u'H\xfctteldorf', 1, 2, 'ordinal not in range(128)')守则的部分：
...
apiurl = 'https://www.wienerlinien.at/ogd_realtime/monitor?rbl={rbl}&sender={apikey}'
...
for rbl in rbls:
r = requests.get(url, timeout=10)
##r.encoding = 'utf-8';
##print(r.json())
##print(r.encoding)
##r.encoding = 'latin1'
if requests.codes.ok:
try:
for monitor in r.json()['data']['monitors']:
rbl.station = monitor['locationStop']['properties']['title'].encode('utf-8')
for line in monitor['lines']:
#Decoding-Problem is here - ß works, ü doesn't
#UnicodeEncodeError('ascii', u'H\xfctteldorf', 1, 2, 'ordinal not in range(128)')
rbl.name = str(line['name'])
rbl.direction = str(line['towards'])
rbl.trafficjam = line['trafficjam'] #Boolean
...我个人认为我尝试了我发现的所有可能在Python3...encode，解码，.每一次，无论是夏普还是乌姆劳特都失败了。
有人能给我一个正确方向的提示吗？非常感谢!
编辑:这是完整的源代码，它有一个解决方案(ü=ue)：
#!/usr/bin/python
# -*- coding: utf-8 -*-
import sys, getopt, time
import requests
import smbus
# Define some device parameters
I2C_ADDR = 0x27 # I2C device address, if any error, change this address to 0x3f
LCD_WIDTH = 20 # Maximum characters per line
# Define some device constants
LCD_CHR = 1 # Mode - Sending data
LCD_CMD = 0 # Mode - Sending command
LCD_LINE_1 = 0x80 # LCD RAM address for the 1st line
LCD_LINE_2 = 0xC0 # LCD RAM address for the 2nd line
LCD_LINE_3 = 0x94 # LCD RAM address for the 3rd line
LCD_LINE_4 = 0xD4 # LCD RAM address for the 4th line
LCD_BACKLIGHT = 0x08 # On
#LCD_BACKLIGHT = 0x00 # Off
ENABLE = 0b00000100 # Enable bit
# Timing constants
E_PULSE = 0.0005
E_DELAY = 0.0005
#Open I2C interface
bus = smbus.SMBus(1) # Rev 2 Pi uses 1
class RBL:
id = 0
line = ''
station = ''
direction = ''
time = -1
def replaceUmlaut(s):
s = s.replace("Ä", "Ae") # A umlaut
s = s.replace("Ö", "Oe") # O umlaut
s = s.replace("Ü", "Ue") # U umlaut
s = s.replace("ä", "ae") # a umlaut
s = s.replace("ö", "oe") # o umlaut
s = s.replace("ü", "ue") # u umlaut
return s
def lcd_init():
# Initialise display
lcd_byte(0x33,LCD_CMD) # 110011 Initialise
lcd_byte(0x32,LCD_CMD) # 110010 Initialise
lcd_byte(0x06,LCD_CMD) # 000110 Cursor move direction
lcd_byte(0x0C,LCD_CMD) # 001100 Display On,Cursor Off, Blink Off
lcd_byte(0x28,LCD_CMD) # 101000 Data length, number of lines, font size
lcd_byte(0x01,LCD_CMD) # 000001 Clear display
time.sleep(E_DELAY)
def lcd_byte(bits, mode):
# Send byte to data pins
# bits = the data
# mode = 1 for data
# 0 for command
bits_high = mode | (bits & 0xF0) | LCD_BACKLIGHT
bits_low = mode | ((bits<<4) & 0xF0) | LCD_BACKLIGHT
# High bits
bus.write_byte(I2C_ADDR, bits_high)
lcd_toggle_enable(bits_high)
# Low bits
bus.write_byte(I2C_ADDR, bits_low)
lcd_toggle_enable(bits_low)
def lcd_toggle_enable(bits):
# Toggle enable
time.sleep(E_DELAY)
bus.write_byte(I2C_ADDR, (bits | ENABLE))
time.sleep(E_PULSE)
bus.write_byte(I2C_ADDR,(bits & ~ENABLE))
time.sleep(E_DELAY)
def lcd_string(message,line):
# Send string to display
message = message.ljust(LCD_WIDTH," ")
lcd_byte(line, LCD_CMD)
for i in range(LCD_WIDTH):
lcd_byte(ord(message[i]),LCD_CHR)
def main(argv):
apikey = False
apiurl = 'https://www.wienerlinien.at/ogd_realtime/monitor?rbl={rbl}&sender={apikey}'
#Time between updates
st = 10
# Initialise display
lcd_init()
lcd_string("Willkommen!",LCD_LINE_2)
try:
opts, args = getopt.getopt(argv, "hk:t:", ["help", "key=", "time="])
except getopt.GetoptError:
usage()
sys.exit(2)
for opt, arg in opts:
if opt in ("-h", "--help"):
usage()
sys.exit()
elif opt in ("-k", "--key"):
apikey = arg
elif opt in ("-t", "--time"):
try:
tmpst = int(arg)
if tmpst > 0:
st = tmpst
except ValueError:
usage()
sys.exit(2)
if apikey == False or len(args) < 1:
usage()
sys.exit()
rbls = []
for rbl in args:
tmprbl = RBL()
tmprbl.id = rbl
rbls.append(tmprbl)
x = 1
while True:
for rbl in rbls:
url = apiurl.replace('{apikey}', apikey).replace('{rbl}', rbl.id)
r = requests.get(url, timeout=10)
r.encoding = 'utf-8'
if requests.codes.ok:
try:
for monitor in r.json()['data']['monitors']:
rbl.station = monitor['locationStop']['properties']['title']
for line in monitor['lines']:
rbl.name = replaceUmlaut(str(line['name'].encode('ascii','xmlcharrefreplace').decode('ascii')))
rbl.direction = replaceUmlaut(str(line['towards'].encode('ascii','xmlcharrefreplace').decode('ascii')))
rbl.trafficjam = line['trafficjam']
rbl.type = line['type']
rbl.time1 = line['departures']['departure'][0]['departureTime']['countdown']
rbl.time2 = line['departures']['departure'][1]['departureTime']['countdown']
rbl.time3 = line['departures']['departure'][2]['departureTime']['countdown']
lcdShow(rbl)
time.sleep(st)
except Exception as e:
print("Fehler (Exc): " + repr(e))
print(r)
lcd_string("Fehler (Exc):",LCD_LINE_1)
lcd_string(repr(e),LCD_LINE_2)
lcd_string("",LCD_LINE_3)
lcd_string("",LCD_LINE_4)
else:
print('Fehler bei Kommunikation mit Server')
lcd_string("Fehler:",LCD_LINE_1)
lcd_string("Serverkomm.",LCD_LINE_2)
lcd_string("",LCD_LINE_3)
lcd_string("",LCD_LINE_4)
def lcdShow(rbl):
lcdLine1 = rbl.name + ' ' + rbl.station
lcdLine2 = rbl.direction
lcdLine3 = "".ljust(LCD_WIDTH-9) + ' ' + '{:0>2d}'.format(rbl.time1) + ' ' + '{:0>2d}'.format(rbl.time2) + ' ' + '{:0>2d}'.format(rbl.time3)
if not rbl.type == "ptMetro":
if rbl.trafficjam:
lcdLine4 = "Stau in Zufahrt"
else:
lcdLine4 = "kein Stau"
else:
lcdLine4 = ""
lcd_string(lcdLine1,LCD_LINE_1)
lcd_string(lcdLine2,LCD_LINE_2)
lcd_string(lcdLine3,LCD_LINE_3)
lcd_string(lcdLine4,LCD_LINE_4)
#print(lcdLine1 + '\n' + lcdLine2+ '\n' + lcdLine3+ '\n' + lcdLine4)
def usage():
print('usage: ' + __file__ + ' [-h] [-t time] -k apikey rbl [rbl ...]\n')
print('arguments:')
print(' -k, --key=\tAPI key')
print(' rbl\t\tRBL number\n')
print('optional arguments:')
print(' -h, --help\tshow this help')
print(' -t, --time=\ttime between station updates in seconds, default 10')
if __name__ == "__main__":
main(sys.argv[1:])回答 1
Stack Overflow用户
发布于 2019-12-15 20:35:29
我个人认为我尝试了我发现的所有可能在Python3...encode，解码，.每一次，无论是夏普还是乌姆劳特都失败了。
正如注释中所指出的那样，您似乎是根据所看到的错误消息运行Python 2的。
Python2有两种“string”类型，str包含原始字节，unicode包含unicode字符。当您调用.json()时，您将得到一个包含unicode字符串的数据结构。所以line['name']就是这样一个unicode字符串。
当您调用str(line['name'])时，您是在隐式地要求将unicode字符串编码成一个ASCII字节序列。这将失败，因为ASCII无法表示这些字符。不幸的是我不知道你为什么要在这里这么做。rbl.name需要成为str吗？它在哪用的？其他使用它的代码应该使用什么编码？
在评论中，Jorropo建议编写line['name'].decode("utf-8")，而您也指出它不起作用。这是因为去编码一个unicode字符串是没有意义的，但是Python2无论如何都会尝试，首先在ASCII中编码它(这会失败)，然后根据您的请求尝试在UTF-8中解码。
您的修复将取决于您对rbl.name所做的操作。你可以：
- 直接使用unicode字符串。这要求后续代码需要一个unicode string.
- Encode，将其转换为UTF-8字节。
rbl.name = line['name'].encode('utf-8')，这要求后续代码需要一个UTF-8字节序列。
。
无论是哪种方式，当您尝试这两种方法时，都有可能(甚至可能)发生其他事情的破坏，完全取决于代码的其余部分对rbl.name应该是什么以及它是如何编码的假设。
至于它为什么和U‘’Westbahnstra一起工作，我不能肯定。您能提供一个完整的示例，包括演示一个工作和另一个不工作的输入数据吗？
页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/59346377
复制相关文章
相似问题
腾讯云开发者
