html entities to unicode text,python中HTML Entities处理及print特殊字符

python3中处理HTML Entities：

from html.parser import HTMLParser

str = HTMLParser.unescape('utf8’,’Orange Blossom Body Crème/5.9 oz.’)

str = HTMLParser.unescape('© 2010')

python2中：

import HTMLParser

html_cont = " asdfg>123<  >"

html_parser = HTMLParser.HTMLParser()

new_cont = html_parser.unescape(html_cont)

print new_cont #new_cont = " asdfg>123

Java中可用：

org.apache.commons.lang3.StringEscapeUtils.unescapeHtml4(String);

print特殊字符：

#方式1

import sys

sys.stdout = open(1, 'w', encoding='utf-8', closefd=False)

print("vadsэавфыаЭХÜÜÄ")

#方式2

print(bytes("аЭХÜ", "utf-8"))

#方式3

TestText = "Test - āĀēĒčČ..šŠūŪžŽ" # this NOT utf-8...it is a Unicode string in Python 3.X.

TestText2 = TestText.encode('utf8') # THIS is "just bytes" in UTF-8.

print(TestText2)

import sys

sys.stdout.buffer.write(TestText2)

#方式4

utf8stdout = open(1, 'w', encoding='utf-8', closefd=False) # fd 1 is stdout

print('Test - āĀēĒčČ..šŠūŪžŽ33', file=utf8stdout)

#方式5

print('Test - āĀēĒčČ..šŠūŪžŽ33'.encode('utf8'))

text='中文524μg/m³'.encode('gbk', 'ignore').decode('gbk')

print(text)