# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^(\D+[路|街|大道|村|队][--\d]+号)?(\D*)?(.+[幢|栋|号楼])?(.+单元)?([-\d]+室?)?$"
test_str = ("万达茂e座B栋1513\n"
"马群街道馨康苑12号楼1单元1003室\n"
"南京栖霞区银城KINMA-Q+社区3栋902\n"
"和燕路438号城市绿洲花园11幢四单元208室\n"
"合班村省电宿舍14幢102室\n"
"学仕风华苑33栋503\n"
"华电三宿舍27幢215室\n"
"尧顺佳园2765栋2单元306\n"
"金马路16号6幢三单元401室\n"
"江苏南京市栖霞区尧林仙居青山苑17幢601室\n"
"仙境路29号50幢一单元302室\n"
"尧化门街道新城家园5幢2-603室\n"
"江苏南京市栖霞区宁杭公路2号百水芊城秀水坊6幢三单元106室\n"
"四季金辉8-3401\n"
"临江街64-1号\n"
"文澜路6号亚朵酒店")
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