# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"class=\"\"pinyin\"\">(.*?)<script>(?:(?!<script>).)*"
test_str = ("<br>\n"
"<span class=\"\"b\"\">拼音:</span><span class=\"\"pinyin\"\">xī<script>Setduyin('Duyin/xi1')</script></span> <span class=\"\"b\"\">注音:</span><span class=\"\"pinyin\"\">ㄒㄧ<script>Setduyin('Duyin/xi1')</script></span><br>\n"
"<span class=\"\"b\"\">简体部首:</span>丨 <span class=\"\"b\"\">部首笔画:</span>1 <span class=\"\"b\"\">总笔画:</span>8<br><span class=\"\"b\"\">ç¹ä½“部首:</span>åœã€€<span class=\"\"b\"\">部首笔画:</span>2 <span class=\"\"b\"\">总笔画:</span>8<br><span class=\"\"b\"\">康熙å—典笔画</span>( å¥:8ï¼› )")
subst = "-"
# 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