XML处理不起作用

Question

我试图从传感器中提取数据（它与“xml类型”字符串通信）并将其转换为csv。 在实际代码中，我已经编写了xml文件，但是数据是单行的（从根到根）。在

不知道是不是这个原因，但我得到了一个元素树.parse文档元素后出现错误“垃圾邮件”。到目前为止，我所读到的所有内容，问题都在xml构造中（不止一个根，没有根等等），所以我对我的案例有点不知所措。在

登录的xml文件：

<li820><data><celltemp>5.1120729e1</celltemp><cellpres>9.7705745e1</cellpres><co2>7.7808494e2</co2><co2abs>5.0983281e-2</co2abs><ivolt>1.1380004e1</ivolt><raw>2726238,1977386</raw></data></li820>
<li820><data><celltemp>5.1120729e1</celltemp><cellpres>9.7684698e1</cellpres><co2>7.7823929e2</co2><co2abs>5.0991268e-2</co2abs><ivolt>1.1380004e1</ivolt><raw>2725850,1976922</raw></data></li820>
<li820><data><celltemp>5.1120729e1</celltemp><cellpres>9.7705745e1</cellpres><co2>7.7797288e2</co2><co2abs>5.0977463e-2</co2abs><ivolt>1.1373291e1</ivolt><raw>2726166,1977001</raw></data></li820>

前一行的内容（在树状图中）：

^{pr2}$

错误：

Traceback (most recent call last):
 File "licor_read.py", line 96, in <module>
  tree = et.parse(file_xml)              # Set XML Parser
 File "/usr/lib/python2.7/xml/etree/ElementTree.py", line 1182, in parse
  tree.parse(source, parser)
 File "/usr/lib/python2.7/xml/etree/ElementTree.py", line 656, in parse
  parser.feed(data)
 File "/usr/lib/python2.7/xml/etree/ElementTree.py", line 1642, in feed
  self._raiseerror(v)
 File "/usr/lib/python2.7/xml/etree/ElementTree.py", line 1506, in _raiseerror
  raise err
xml.etree.ElementTree.ParseError: junk after document element: line 2, column 0

我的代码：

import os, sys, subprocess
import time, datetime
import serial
import string
import glob
import csv
import xml.etree.ElementTree  as et

from xml.etree.ElementTree import XMLParser, XML, fromstring, tostring
from os  import path
from bs4 import BeautifulSoup as bs


#-------------------------------------------------------------
#------------------ Open configurations ----------------------
#-------------------------------------------------------------

  ############
  # Settings #
  ############

DEBUG   = True
LOG     = True
FREQ    = 1
PORT    = '/dev/ttyUSB0'
BAUD    = 9600
PARITY  = 'N'
STOPBIT = 1
BYTE_SZ = 8
TIMEOUT = 5.0

log_dir   = 'logs/'
out_dir   = 'export/'
fname_xml = 'licor820-data-{}.xml'.format(datetime.datetime.now())            # DO NOT touch the {} brackets
fname_csv = 'licor820-data-{}.csv'.format(datetime.datetime.now())            #
isLooping = 20                                                                # Nr of data extractions
isHeader  = True                                                              # Do not touch if data headers are required
isBegin   = False


#-------------------------------------------------------------
#----- Better know what you are doing from this point --------
#-------------------------------------------------------------

  ##################
  # Initialisation #
  ##################

file_xml = os.path.join(log_dir, fname_xml)                                   # Define path and file name
file_csv = os.path.join(out_dir, fname_csv)                                   #
fp_xml   = open(file_xml, 'w')                                                # Open writing streams
fp_csv   = open(file_csv, 'w')                                                #

try:
  buff = serial.Serial(PORT, BAUD, BYTE_SZ, PARITY, STOPBIT, TIMEOUT)         # Open Serial connection
except Exception as e:
  if DEBUG:
    print ("ERROR: {}".format(e))

  sys.exit("Could not connect to the Licor")

csv_writer    = csv.writer(fp_csv)                                            # Define CSV writer
instruct_head = []                                                            # '' 


  ################
  # Main program #
  ################

while isLooping :                                                             # Define nr of refreshed data extracted
  #os.system('clear')
  print('RAW/XML in progress... ' + str(isLooping))                           # Debug this loop

  if(isBegin is False) :                                                      # Verify presence of the <licor> tag
    while(buff.readline()[0] is not '<' and buff.readline()[1] is not 'l') :    
      raw_output = buff.readline()                                            # Jump the lines readed until <licor>
  isBegin = True

  raw_output = buff.readline()
  xml_output = raw_output

  print(xml_output)
  fp_xml.write(xml_output)                                                    # Write from serial port to xml 

  isLooping -= 1

fp_xml.close()

tree = et.parse(file_xml)                                                     # Set XML Parser
root = tree.getroot()                                                         # ''

for instruct_row in root.findall('li820'):                                    # XML to CSV buffer
  instruct = []

  if isHeader is True:                                                        # Buffering header
    celltemp = instruct_row.find('celltemp').tag
    instruct_head.append(celltemp)
    cellpres = instruct_row.find('cellpres').tag
    instruct_head.append(cellpres)      
    co2 = instruct_row.find('co2').tag
    instruct_head.append(co2)      
    co2abs = instruct_row.find('co2abs').tag
    instruct_head.append(co2abs)      
    ivolt = instruct_row.find('ivolt').tag
    instruct_head.append(ivolt)      
    raw = instruct_row.find('raw').tag
    instruct_head.append(raw)

    csv_writer.writerow(instruct_head)                                        # Write header      
    isHeader = False

  celltemp = instruct_row.find('celltemp').text                               # Buffering data
  instruct.append(celltemp)    
  cellpres = instruct_row.find('cellpres').text
  instruct.append(cellpres)    
  co2 = instruct_row.find('co2').text
  instruct.append(co2)    
  co2abs = instruct_row.find('co2abs').text
  instruct.append(co2abs)      
  ivolt = instruct_row.find('ivolt').text
  instruct.append(ivolt)      
  raw = instruct_row.find('raw').text
  instruct.append(raw)

  csv_writer.writerow(instruct)                                             # Write data'''

csv_writer.close()
fp_csv.close()
os.system('clear')

print('Job done. \nSaved at : ./' + file_xml + '\nAnd at ./' + file_csv + '\n')

Answer 1

应该用“read”而不是“write”打开输入文件。或者在运行代码时清空文件。在

fp_xml   = open(file_xml, 'r');

另外，我还有更好的方法元素。你不需要提前知道所有标签的名称。在

^{pr2}$

我的输入xml如下：

<li820>
<data><celltemp>5.1120729e1</celltemp><cellpres>9.7705745e1</cellpres><co2>7.7808494e2</co2><co2abs>5.0983281e-2</co2abs><ivolt>1.1380004e1</ivolt><raw>2726238,1977386</raw></data>
<data><celltemp>5.1120729e1</celltemp><cellpres>9.7705745e1</cellpres><co2>7.7808494e2</co2><co2abs>5.0983281e-2</co2abs><ivolt>1.1380004e1</ivolt><raw>2726238,1977386</raw></data>
</li820>

最后，您可以在csv文件中看到数据。在