Питон изучаю всего второй день. И перед мной была поставлена задача распарсить
Catalog.xml
Сам написал парсер для него, но при работе он выдает ошибку. Знающие люди помогите, в чем причина ошибки.
Код parser.py
import xml.dom.minidom
dom1 = xml.dom.minidom.parse('catalogue.xml')
product_id = dom1.getElementsByTagName('product_id')
code = dom1.getElementsByTagName('code')
name = dom1.getElementsByTagName('name')
product_size = dom1.getElementsByTagName('product_size')
matherial = dom1.getElementsByTagName('matherial')
small_image = dom1.getElementsByTagName('small_image')
big_image = dom1.getElementsByTagName('big_image')
content = dom1.getElementsByTagName('content')
state = dom1.getElementsByTagName('state')
currency = dom1.getElementsByTagName('currency')
status = dom1.getElementsByTagName('status')
brand = dom1.getElementsByTagName('brand')
weight = dom1.getElementsByTagName('weight')
product_id_t = open('product_id.txt', 'w')
for e in product_id:
for t in e.childNodes:
product_id_t.write(t.data + '\n')
product_id_t.close()
code_t = open('code.txt', 'w')
for e in code:
for t in e.childNodes:
code_t.write(t.data + '\n')
code_t.close()
name_t = open('name.txt', 'w')
for e in name:
for t in e.childNodes:
name_t.write(str(t.data + '\n'))
name_t.close()
product_size_t = open('product_size.txt', 'w')
for e in product_size:
for t in e.childNodes:
product_size_t.write(t.data + '\n')
product_size_t.close()
matherial_t = open('matherial.txt', 'w')
for e in matherial:
for t in e.childNodes:
matherial_t.write(t.data + '\n')
matherial_t.close()
small_image_t = open('small_image.txt', 'w')
for e in small_image:
for t in e.childNodes:
small_image_t.write(t.data + '\n')
small_image_t.close()
big_image_t = open('big_image.txt', 'w')
for e in big_image:
for t in e.childNodes:
big_image_t.write(t.data + '\n')
big_image_t.close()
content_t = open('content.txt', 'w')
for e in content:
for t in e.childNodes:
content_t.write(t.data + '\n')
content_t.close()
state_t = open('state.txt', 'w')
for e in state:
for t in e.childNodes:
state_t.write(t.data + '\n')
state_t.close()
currency_t = open('currency.txt', 'w')
for e in currency:
for t in e.childNodes:
currency_t.write(t.data + '\n')
currency_t.close()
status_t = open('status.txt', 'w')
for e in status:
for t in e.childNodes:
status_t.write(t.data + '\n')
status_t.close()
brand_t = open('brand.txt', 'w')
for e in brand:
for t in e.childNodes:
brand_t.write(t.data + '\n')
brand_t.close()
weight_t = open('weight.txt', 'w')
for e in weight:
for t in e.childNodes:
weight_t.write(t.data + '\n')
weight_t.close()
Ошибка:
Traceback (most recent call last):
File "D:\incoming\WorkSpace\Eclipse\Parser\sten-parser.py", line 37, in
name_t.write(str(t.data + '\n'))
File "D:\Instal\Program\Python3\lib\encodings\cp1251.py", line 19, in encode
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
UnicodeEncodeError: 'charmap' codec can't encode character '\u044e' in position 6: character maps to
