148 lines
4.4 KiB
Plaintext
148 lines
4.4 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Regular Expressions"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"## Basic Matching"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"<re.Match object; span=(2, 5), match='aza'>\n",
|
|
"<re.Match object; span=(1, 4), match='aza'>\n",
|
|
"None\n",
|
|
"<re.Match object; span=(0, 1), match='x'>\n",
|
|
"<re.Match object; span=(4, 8), match='ping'>\n",
|
|
"<re.Match object; span=(1, 5), match='pong'>\n",
|
|
"<re.Match object; span=(0, 4), match='Pang'>\n",
|
|
"<re.Match object; span=(0, 6), match='Python'>\n",
|
|
"<re.Match object; span=(18, 22), match='hway'>\n",
|
|
"None\n",
|
|
"<re.Match object; span=(0, 6), match='cloudy'>\n",
|
|
"<re.Match object; span=(0, 6), match='cloud9'>\n",
|
|
"<re.Match object; span=(4, 5), match=' '>\n",
|
|
"<re.Match object; span=(30, 31), match='.'>\n",
|
|
"<re.Match object; span=(7, 10), match='cat'>\n",
|
|
"<re.Match object; span=(7, 10), match='dog'>\n",
|
|
"<re.Match object; span=(12, 15), match='dog'>\n",
|
|
"<re.Match object; span=(7, 10), match='cat'>\n",
|
|
"<re.Match object; span=(7, 10), match='dog'>\n",
|
|
"<re.Match object; span=(12, 15), match='dog'>\n",
|
|
"['dog', 'cat']\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"import re\n",
|
|
"result1 = re.search(r\"aza\", \"plaza\")\n",
|
|
"result2 = re.search(r\"aza\", \"bazaar\")\n",
|
|
"print(result1)\n",
|
|
"print(result2)\n",
|
|
"print(re.search(r\"aza\", \"maze\"))\n",
|
|
"print(re.search(r\"^x\", \"xenon\"))\n",
|
|
"print(re.search(r\"p.ng\", \"clapping\"))\n",
|
|
"print(re.search(r\"p.ng\", \"sponge\"))\n",
|
|
"print(re.search(r\"p.ng\", \"Pangaea\", re.IGNORECASE))\n",
|
|
"print(re.search(r\"[Pp]ython\", \"Python\"))\n",
|
|
"print(re.search(r\"[a-z]way\", \"The end of the highway\"))\n",
|
|
"print(re.search(r\"[a-z]way\", \"What a way to go\"))\n",
|
|
"print(re.search(\"cloud[a-zA-Z0-9]\", \"cloudy\"))\n",
|
|
"print(re.search(\"cloud[a-zA-Z0-9]\", \"cloud9\"))\n",
|
|
"print(re.search(r\"[^a-zA-Z]\", \"This is a sentence with spaces.\"))\n",
|
|
"print(re.search(r\"[^a-zA-Z ]\", \"This is a sentence with spaces.\"))\n",
|
|
"print(re.search(r\"cat|dog\", \"I like cats.\"))\n",
|
|
"print(re.search(r\"cat|dog\", \"I love dogs!\"))\n",
|
|
"print(re.search(r\"cat|dog\", \"I like both dogs and cats.\"))\n",
|
|
"print(re.search(r\"cat|dog\", \"I like cats.\"))\n",
|
|
"print(re.search(r\"cat|dog\", \"I love dogs!\"))\n",
|
|
"print(re.search(r\"cat|dog\", \"I like both dogs and cats.\"))\n",
|
|
"print(re.findall(r\"cat|dog\", \"I like both dogs and cats.\"))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"True\n",
|
|
"False\n",
|
|
"True\n",
|
|
"True\n",
|
|
"False\n",
|
|
"True\n",
|
|
"True\n",
|
|
"False\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"import re\n",
|
|
"def check_aei (text):\n",
|
|
" result = re.search(r\"a.e.i\", text)\n",
|
|
" return result != None\n",
|
|
"\n",
|
|
"print(check_aei(\"academia\")) # True\n",
|
|
"print(check_aei(\"aerial\")) # False\n",
|
|
"print(check_aei(\"paramedic\")) # True\n",
|
|
"\n",
|
|
"def check_punctuation (text):\n",
|
|
" result = re.search(r\"[,.:;?!]\", text)\n",
|
|
" return result != None\n",
|
|
"\n",
|
|
"print(check_punctuation(\"This is a sentence that ends with a period.\")) # True\n",
|
|
"print(check_punctuation(\"This is a sentence fragment without a period\")) # False\n",
|
|
"print(check_punctuation(\"Aren't regular expressions awesome?\")) # True\n",
|
|
"print(check_punctuation(\"Wow! We're really picking up some steam now!\")) # True\n",
|
|
"print(check_punctuation(\"End of the line\")) # False"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.12.3"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|