我是python和SO的新手。该脚本打开文件夹中的xml文件。使用os.walk迭代集合并打开文件,然后调用函数迭代xml文件并更新xml文件,使用.writexml重写更新的文件。问题是,当我从命令行运行该程序时,它表示存在错误
Traceback (most recent call last):
File "./XMLParser.py", line 67, in <module>
xmldoc = minidom.parse(xml)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/xml/dom/minidom.py", line 1918, in parse
return expatbuilder.parse(file)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/xml/dom/expatbuilder.py", line 928, in parse
result = builder.parseFile(file)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/xml/dom/expatbuilder.py", line 207, in parseFile
parser.Parse(buffer, 0)
UnicodeEncodeError: 'ascii' codec can't encode character u'\xa0' in position 5614: ordinal not in range(128)
CODE:
from xml.dom import minidom
import os
import codecs
'''
Function to iterate over the directory that contains the work items
params:
CoreID of new author,
x is the path to the workItem.xml file,
p is the path to the workItem.xml that will be overwritten with new data
'''
def changeauthor(coreid, x, p):
# Gets the content of the xml based within the work item tag.
testcase = x.getElementsByTagName("work-item")[0]
# All fields are stored as a <field> tag with the id attribute being the
# differentiators between them. Fields is a list of all the field tags in the
# document.
fields = testcase.getElementsByTagName("field")
# Loop iterates over the field tags and looks for the one tag where the id
# attribute has a value of author. when this tag is found the tags value is
# updated to the core id passed to the function.
for field in fields:
attribute = field.attributes['id'].value
if attribute == "author":
# print the current author.
print("Previous Author: ", field.firstChild.data)
# Set the author to the core id entered into the script
field.firstChild.data = coreid
# Print the updated author field
print("New Author: ", field.firstChild.data)
# Create a temp file with the same path as the source
tmp_config = p
# Open the new temp file with the write mode set.
with codecs.open(tmp_config, 'w', "utf-8") as f:
# f = open(tmp_config, 'w')
# Write the xml into the file at the same location as the orginal
x.writexml(f)
# Close the file
# f.close()
return
while True:
core = str(input("Enter Core ID of the new author: "))
core = core.upper()
spath = str(input("Please enter the full path to the directory of test cases: "))
count = 0
confirm = str(input("Confirm path and core id (Y/N or Exit to leave script): "))
confirm = confirm.upper()
if confirm == "Y":
'''Hard code path here and comment out line above asking for input either will work.'''
# spath = "/Users/Evan/Desktop/workitems-r583233"
# Loop iterates over the directory. Whenever a workitem.xml file is found the path is stored and the file is
# parsed. the core ID entered and the path as well as the parsed xml doc are passed to the change author
# function.
for roots, dirs, files in os.walk(spath):
for file in files:
title = file.title()
if title == "Workitem.Xml":
path = os.path.join(roots, file)
with codecs.open(path, 'r+', "utf-8") as xml:
xmldoc = minidom.parse(xml)
lst = path.split('/')
wi = lst[5]
print("Updating: ", wi)
changeauthor(core, xmldoc, path)
count += 1
print(wi, "updated succesfully.")
print("-------------------------------")
if count > 0:
# Print how many test cases were updated.
print("All Done", count, "workItems updated!")
else:
print("Please double check path and try again no workItems found to update!")
elif confirm == "N":
continue
elif confirm == "EXIT":
break