# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"它常被昵称为胶水语言([^。]+)。"
test_str = "Python具有丰富和强大的库。它常被昵称为胶水语言,能够把用其他语言制作的各种模块(尤其是C/C++)很轻松地联结在一起。常见的一种应用情形是,使用Python快速生成程序的原型(有时甚至是程序的最终界面),然后对其中有特别要求的部分,用更合适的语言改写,比如3D游戏中的图形渲染模块,性能要求特别高,就可以用C/C++重写,而后封装为Python可以调用的扩展类库。需要注意的是在您使用扩展类库时可能需要考虑平台问题,某些可能不提供跨平台的实现。"
matches = re.finditer(regex, test_str)
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