Question

我使用此脚本生成必须采用特定格式的自定义XML文件。它查询数据库并将结果转换为一个大的xml文件。我这样做是为了从库存零件清单到员工记录的多个数据库。

import csv
import StringIO
import time
import MySQLdb
import lxml.etree
import lxml.builder
from datetime import datetime
import string
from lxml import etree
from lxml.builder import E as buildE
from datetime import datetime
from time import sleep
import shutil
import glob
import os
import logging

def logWrite(message):
    logging.basicConfig(
        filename="C:\\logs\\XMLSyncOut.log",
        level=logging.DEBUG,
        format='%(asctime)s %(message)s',
        datefmt='%m/%d/%Y %I:%M:%S: %p'
    )
    logging.debug(message)


def buildTag(tag,parent=None,content=None):
        element = buildE(tag)
        if content is not None:
                element.text = unicode(content)
        if parent is not None:
                parent.append(element)
        return element

def fetchXML(cursor):
        logWrite("constructing XML from cursor")
        fields = [x[0] for x in cursor.description]
        doc = buildTag('DATA')
        for record in cursor.fetchall():
                r = buildTag('ROW',parent=doc)
                for (k,v) in zip(fields,record):
                        buildTag(k,content=v,parent=r)
        return doc

def updateDatabase 1():
        try:
                conn = MySQLdb.connect(host = 'host',user = 'user',passwd = 'passwd',db = 'database')
                cursor = conn.cursor()

        except:
                sys.exit(1)
                logWrite("Cannot connect to database - quitting!")

        cursor.execute("SELECT * FROM database.table")
        logWrite("Dumping fields from database.table into cursor")                
        xmlFile = open("results.xml","w")
        doc = fetchXML(cursor)
        xmlFile.write(etree.tostring(doc,pretty_print=True))
        logWrite("Writing XML results.xml")
        xmlFile.close()

由于某种原因，我从excel电子表格导入的一个新数据库出现了某些类型的编码错误，而其他数据库没有。这是错误

element.text = unicode(content)
UnicodeDecodeError: 'ascii' codec can't decode byte 0x96 in position 21: ordinal not in range(128)

我尝试通过将buildTag函数更改为显式编码为ascii：

def buildTag(tag,parent=None,content=None):
        element = buildE(tag)
        if content is not None:
            content = str(content).encode('ascii','ignore')
            element.text = content
        if parent is not None:
                parent.append(element)
        return element

这仍然无效。

关于我能做些什么来阻止这种想法？我无法逃避它们，因为我不能将“\ x92”作为输出显示在记录中。

Answer 1

我认为你在windows编码中遇到的问题可以在shell中尝试：

In: print '\x92'.decode('cp1251')
Out: '

Answer 2

我专注于

element.text = unicode(content)
UnicodeDecodeError: 'ascii' codec can't decode byte 0x96 in position 21: ordinal not in range(128)

我假设content的类型为str，即它包含字节代码（仅适用于Python 2）。您必须知道已使用哪种编码来生成此字节代码。然后，为了从这个字节代码创建一个unicode对象，你必须明确告诉Python如何解码它，例如：

element.text = content.decode("utf-8")

将MySQL查询转换为XML时的Python编码错误

2 个答案: