# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(?=.{1,20}$)(?=.*。)(?!.*,)([^。]*)。"
test_str = ("<h1>这是一个测试。<h1>\n"
"这是一个测试,这是一个测试而已,希望去掉不需要的。\n\n"
"测试。\n"
"这是一个测试,这是一个测试而已,希望去掉不需要的第二行。\n"
"这是一行非常长的文字但是句号不需要被移除。")
subst = "$1"
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0, re.MULTILINE)
if result:
print (result)
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html