# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"[a-zA-Z0-9\x{4e00}-\x{9fa5}]+"
test_str = ("What Does the Fox Say? 12 狐狸怎叫 34\n\n"
" \n"
"What Does the shiba inu say? 柴犬怎叫\n"
"蘋果公司,原稱蘋果電腦公司,是總部位於美國加州庫比蒂諾的跨國科技公司,與亞馬遜,Google、微軟和Meta一起被認為是五大技術公司之一,合稱為MAMAA。\n"
"現時的業務包括設計、開發、手機通信和銷售消費電子、電腦軟體、線上服務和個人電腦。")
matches = re.finditer(regex, test_str, re.MULTILINE)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# 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