# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"^[a-zA-Z][a-zA-Z=0-9;]*"
test_str = ("3. 宿舍开水一壶价格已达到1元以上,%给学生用水造成很大负担。\n"
"4. 空调租赁机制不合理问题,%租赁只能以年为单位,但学生一般只在夏季使用,多出费用很多\n"
"5. 厕所洗手液没有%及时更换\n"
"matlab=123;%this is a matlab test function\n"
"Matlab=123;%this is a matlab test function")
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