#!/usr/bin/env python3
import glob
import xml.etree.ElementTree as ET
filenames = glob.glob("C:\\Users\\####\\Desktop\\BNC2\\[A00-ZZZ]*.xml")
out_lines = []
for filename in filenames:
with open(filename, 'r', encoding="utf-8") as content:
tree = ET.parse(content)
root = tree.getroot()
for w in root.iter('w'):
lemma = w.get('hw')
pos = w.get('pos')
tag = w.get('c5')
out_lines.append(w.text + "," + lemma + "," + pos + "," + tag)
with open("C:\\Users\\####\\Desktop\\bnc.txt", "w") as out_file:
for line in out_lines:
line = bytes(line, 'utf-8').decode('utf-8', 'ignore')
out_file.write("{}\n".format(line))
给出错误:
UnicodeEncodeError:'charmap'编解码器无法对位置0中的字符'\ u2192'进行编码:字符映射到未定义
我认为这条线会解决这个问题......
line = bytes(line,'utf-8')。decode('utf-8','ignore')
答案 0 :(得分:2)
打开输出文件时需要指定编码,与输入文件相同:
with open("C:\\Users\\####\\Desktop\\bnc.txt", "w", encoding="utf-8") as out_file:
for line in out_lines:
out_file.write("{}\n".format(line))
答案 1 :(得分:-2)
如果您的脚本有多个读写操作,并且您希望对所有这些编码使用特定的编码(例如utf-8),我们也可以更改默认编码
import sys
reload(sys)
sys.setdefaultencoding('UTF8')
我们应该只在我们有多个读/写时使用它,并且应该在脚本的开头完成