# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"US\s*(?:[2-9]\d{3}\/?\d{7}\s*A[129]|\d{7}\s*B[12])"
test_str = ("发明专利申请号 1-6 位顺序号或 2 位序列号\n"
"(01-28)+/6 位顺序号 1234 13/001234\n"
"发明专利临时申请号 60+/6 位顺序号或 61/+/6 位\n"
"顺序号 60/001234 61/000456\n"
"发明专利申请公布号 US+4 位年代+/7 位顺序号\n"
"+A1\n"
"无 US 2001/0001111 A1\n"
"发明专利申请再公布号 US+4 位年代+/7 位顺序号\n"
"+A2\n"
"无 US 2002/0042300 A2\n"
"发明专利申请公布的更\n"
"正号\n"
"US+4 位年代+/7 位顺序号\n"
"+A9\n"
"无 US 2002/0090260 A9\n"
"发明专利号(无专利申\n"
"请公布)\n"
"1-7 位顺序号或 US+1-7 位顺\n"
"序号+B1\n"
"123456 US 6198606 B1\n"
"发明专利号(有专利申\n"
"请公布)\n"
"US+1-7 位顺序号+B2 无 US 6654321 B2 \n")
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