# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"<div class=\"con news_content\">(.*?)<\/div>"
test_str = ("body = \"\"\"234234<div class=\"con news_content\">解决什么问题?解决人的æ€è€ƒï¼Ÿè¿˜æ˜¯è§£å†³äººçš„预测\n"
"还是解决现象?人工智能它的机ç†æ˜¯ä»€ä¹ˆï¼Œç®€å•æ¥è®²è‡³å°‘大数æ®å¯ä»¥åœ¨äººå·¥æ™ºèƒ½åšé¢„测决ç–的范畴起到促进作用。</p> \n"
" <p class=\"copyright\"</p>\n"
" </div></div>34234\"\"\"")
matches = re.search(regex, test_str, re.DOTALL)
if matches:
print ("Match was found at {start}-{end}: {match}".format(start = matches.start(), end = matches.end(), match = matches.group()))
for groupNum in range(0, len(matches.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = matches.start(groupNum), end = matches.end(groupNum), group = matches.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