# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(\\\w\\\w)|(\\[u][A-Za-z0-9A@#\\(]{4})|([\\][n])"
test_str = ("@DethDeelinDale DALE BUB⁉️\\n\\nU ALRIT⁉️\\n\\nU NEED BAKUP⁉️\n"
"RT @DethDeelinDale: WHO N THE FUK R U #DIKS⁉️\\n\\nHOLEE FUK‼️ PUT DEM \\uD83D\\uDD2B AWAY!!!\\n\\nU kan hav the \\uD83D\\uDCB0 I dun giv a fuk bout dat!!!\\n\\nHear u go…jus ta…\n"
"@DethDeelinDale Waz rong dale⁉️\\n\\nWaz it a menshall er 1 a em lite \\uD83D\\uDEAC⁉️\\n\\nI dun HAYT thoz‼️\\n\\nNuthin but #MarbReds\\uD83D\\uDEAC 4 me‼️\n"
"WAT N THE FLYIN FUK⁉️\\n\\nHEY, U DUM B!TCH, PULL UP UR FN \\uD83D\\uDC56‼️\\n\\nU KANT NOT FRIGGEN \\uD83D\\uDCA9 HER‼️\\n\\nI swar 2 fn God, thez #ratards\\uD83E\\uDD24 @ friggen @Walmart r gonna dun mayk me looz mi fn mind!!! \\uD83E\\uDD2C\\uD83E\\uDD2C https://t.co/xsQg26SWIk\n"
"WOOD U HUREE THE FUK UP U STUPID LITLE KIDS N GET ON UR GOD DAM SKOOL \\uD83D\\uDE8C!!! \\uD83E\\uDD2C\\n\\nU MOTHAFUKERS R GONNA DUN MAYK ME LAYT AGAN 2 MI JOB #HAWLINKARTS\\uD83D\\uDED2 @Walmart‼️\\n\\nThas it! I aint not got Tim 4 this, Im passin thez fn ratards!!! \\uD83D\\uDCA8\\n\\nOhhhh fukkkkk... \\uD83D\\uDEA8\\uD83D\\uDE94\\uD83E\\uDD26\\uD83C\\uDFFB♂️\\uD83E\\uDD26\\uD83C\\uDFFB♂️\n"
"WAR N TYE FLYIN FUK M I N WAT HAPND 2 MI FN \\uD83D\\uDC56!!!???\n"
"@DethDeelinDale Wat 4 bub⁉️ U dun need mi #glock \\uD83D\\uDD2B???\n"
"RT @DethDeelinDale: I NEEDA #GAT \\uD83D\\uDD2B‼️\n"
"RT @DethDeelinDale: BOOOOOMMMMM‼️ \\n\\nDAS WAT I THOT #BALDYBILL \\uD83D\\uDC68\\uD83C\\uDFFB\\uD83E\\uDDB2‼️\\n\\nU cum talkin all dat SHIT 2 me n think u waznt gonna get put 2 fukin…\n"
"Hapins 2 the best a us! \\uD83D\\uDC56\\uD83D\\uDCA9 https://t.co/TVzch1v0du\n"
"RT @HistoryMuppet: This is a brilliant example of the Muppet team going that extra step with a gag \\uD83D\\uDE02\\n(look closely at those “Written By” cr…\n"
"RT @BroadwayWorld: .@MusicManBway will close on Broadway on January 1, 2023. https://t.co/8sMQ3LUsnA\n"
"RT @TWJSciNat: Are you feeling lucky? \\n\\nThe latest episode of Mysteries of Science, starring @DerrenBrown is now live. \\n\\n\\uD83D\\uDD17Listen at https:/…\n"
"RT @JustinRYoung: Very excited to finally release @DontExplainPod, the latest from @DogPonyAudio.\\n\\nEvery cliche and trope began as a brilli…\n"
"RT @Justin_Willman: People love me on holidays https://t.co/Ft1udKGydl\n"
"RT @BroadwaySym: Shana Tova! Wishing eveyone a sweet new year filled w/ many blessings in #stagemanagement & #smlife! May the year bring yo…\n"
"RT @memgrizz: #BeyondGrit: Making Magic w/ @jacob_laravia3 + @droddy22 \\uD83E\\uDE84 \\n\\nIn this episode, LaRavia & Roddy link up with Piff The Magic Dra…\n"
"RT @BroadwayWorld: Obituary: Rita Gardner, Original Luisa in THE FANTASTICKS, Passes Away at 87\\nhttps://t.co/GClzbN6Mii\n"
"Oh no! Broadway legend \\uD83D\\uDE22\\uD83D\\uDE22 RIP https://t.co/J7JXoEmEYZ\n"
"RT @levarburton: Happy Rosh Hashanah, y’all! #ShanaTova \\uD83D\\uDC9C\\uD83D\\uDE4F\\uD83C\\uDFFE\n\n"
"\\u@83D \n"
"\\u#123 \n"
"\\u(223")
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