# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(.*)@(?!gmail)\w+\.com"
test_str = ("# 配對電子郵件\n\n"
"# 題目說明區塊\n"
"請幫我抓出@(小老鼠)前面的帳戶名稱,而且我不要 gmail 的。\n\n"
"#欲測試資料集\n\n"
"foobar@gmail.com\n"
"NoOneCareMe@gamil.com\n"
"SaveTheWorld@hotmail.com\n"
"zzzGroup@yahoo.com\n"
"eagle1963@gmail.com\n"
"maythefourthwithyiu@starwars.com\n\n"
"# 應配對結果(亮色區塊)\n"
"NoOneCareMe@gamil.com\n"
"SaveTheWorld@hotmail.com\n"
"zzzGroup@yahoo.com\n"
"maythefourthwithyiu@starwars.com\n\n"
"# (選項)寫上註解,好好說明你怎麼想的\n"
"首先將 @ 之前的文字都抓起來,所以放上(),因為不想顧及裡面的文字是什麼,所以很懶惰的使用 .*,步驟多了點但是我不在意XD,因為不想要 gmail 所以我再任意文字 \\w+ 前面判斷寫上不是 gmail,最後放上 \\.com來玩成此次配對,希望你可以幫我減少更多 step(步驟),來提高這個規則的效率。\n\n"
"# (選項)將你的 Regex 註解起來,使用 Extended Formating\n"
"/ # Start of Regex\n"
" ( # Group and Capturing follwoing\n"
" .* # Match any form zero-to-many\n"
" ) # End of group\n\n"
" @ # Match @\n\n"
" ( # Group and Capturing follwoing\n"
" ?! # Negative lookahead\n"
" gmail # Match Gmail\n"
" ) # End of group\n\n"
" \\w+ # Match any character from one-to-many\n"
" \\. # Match .(dot)\n"
" com # Match com\n"
"/ # End of Regex")
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