Spaces:
Sleeping
Sleeping
File size: 8,937 Bytes
d737845 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### import"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: xmltodict in c:\\users\\user\\appdata\\local\\programs\\python\\python311\\lib\\site-packages (0.13.0)\n",
"Note: you may need to restart the kernel to use updated packages.\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"[notice] A new release of pip is available: 23.2.1 -> 24.0\n",
"[notice] To update, run: python.exe -m pip install --upgrade pip\n"
]
}
],
"source": [
"%pip install xmltodict"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"# Use request to download a xml file\n",
"import requests\n",
"import json\n",
"import xmltodict"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"# url = 'http://tisvcloud.freeway.gov.tw/history/motc20/ETag.xml'\n",
"# response = requests.get(url)\n",
"# with open('ETag.xml', 'wb') as f:\n",
"# f.write(response.content)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"# # Turn xml to json\n",
"# filename = 'ETag'\n",
"# with open(f'{filename}.xml', 'r', encoding='utf-8-sig') as f:\n",
"# data_dict = xmltodict.parse(f.read())\n",
"# data_json = json.dumps(data_dict, ensure_ascii=False)\n",
"# # dump to Etag.json with json\n",
"# json.dump(data_dict, open(f'{filename}.json', 'w'), ensure_ascii=False, indent=2)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"'pwd' ���O�����Υ~���R�O�B�i���檺�{���Χ妸�ɡC\n"
]
}
],
"source": [
"!pwd"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Read ETagPairLive_1615.xml.gz and decompress it\n",
"import gzip\n",
"import shutil\n",
"import threading\n",
"\n",
"\n",
"\n",
"def crawl(url, filename):\n",
" try:\n",
" try:\n",
" response = requests.get(url)\n",
" except Exception as e:\n",
" print(\"Error\",e)\n",
" with open(f'{filename}.xml.gz', 'wb') as f:\n",
" f.write(response.content)\n",
" \n",
" # 解壓縮\n",
" with gzip.open(f'{filename}.xml.gz', 'rb') as f_in:\n",
" with open(f'{filename}.xml', 'wb') as f_out:\n",
" shutil.copyfileobj(f_in, f_out)\n",
"\n",
" # xml to json\n",
" with open(f'{filename}.xml', 'r') as f:\n",
" data_dict = xmltodict.parse(f.read())\n",
" data_json = json.dumps(data_dict, ensure_ascii=False)\n",
" # dump to Etag.json with json\n",
" json.dump(data_dict, open(f'{filename}.json', 'w'), ensure_ascii=False, indent=2)\n",
" except Exception as e:\n",
" print(e)\n",
" print(f'{url} failed')\n",
" print(f'{url} done')\n",
"\n",
"threads = []\n",
"day_list = ['202405%02d'%(x) for x in range(6, 13)]\n",
"hour_list = ['%02d'%(i) for i in range(24)]\n",
"five_minute_list = ['%02d'%(i) for i in range(0,60,5)]\n",
"print(\"Lens = \", len(day_list) * len(hour_list) * len(five_minute_list))\n",
"for day in day_list:\n",
" for hour in hour_list:\n",
" for minute in five_minute_list:\n",
" i = hour + minute\n",
" # filename = f'ETagPairLive_{str(i)}'\n",
" # url = f'https://tisvcloud.freeway.gov.tw/history/motc20/ETag/20240522/{filename}.xml.gz'\n",
" filename = f'./data/ETagPairLive_{day}_{str(i)}'\n",
" url = f'https://tisvcloud.freeway.gov.tw/history/motc20/ETag/{day}/ETagPairLive_{str(i)}.xml.gz'\n",
" t = threading.Thread(target=crawl, args=(url, filename))\n",
" threads.append(t)\n",
" t.start()\n",
"\n",
"# Wait for all threads to finish\n",
"for t in threads:\n",
" t.join()\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import matplotlib.pyplot as plt\n",
"import matplotlib.font_manager as fm\n",
"\n",
"EtagPairId = '01F0339S-01F0376S'\n",
"EtagStart = '01F0339S'\n",
"EtagEnd = '01F0376S'\n",
"EtagStartRoad = ['五股','高公局','林口(文化一路)']\n",
"VehicleTypeDict = {\n",
" 31: \"Car\",\n",
" 32: \"Small Truck\",\n",
" 41: \"Bus\", # (含計程車)\n",
" 42: \"Heavy Truck\",\n",
" 5: \"Trailer\"\n",
"}\n",
"\n",
"time_series_31data = {}\n",
"time_series_32data = {}\n",
"time_series_41data = {}\n",
"time_series_42data = {}\n",
"time_series_5data = {}\n",
"\n",
"\n",
"day_list = ['202405%02d'%(x) for x in range(6, 13)]\n",
"hour_list = ['%02d'%(i) for i in range(24)]\n",
"five_minute_list = ['%02d'%(i) for i in range(0,60,5)]\n",
"for day in day_list:\n",
" for hour in hour_list:\n",
" for minute in five_minute_list:\n",
" i = hour + minute\n",
" filename = f'./data/ETagPairLive_{day}_{str(i)}'\n",
" try:\n",
" with open(f'{filename}.json', 'r') as f:\n",
" data = json.load(f)\n",
" EtagPairLive = data['ETagPairLiveList']['ETagPairLives']['ETagPairLive']\n",
" for ETagPair in EtagPairLive:\n",
" if ETagPair['ETagPairID'] == EtagPairId:\n",
" # print(ETagPair['ETagPairID'])\n",
" Flow = ETagPair['Flows']['Flow']\n",
" for vehicle in Flow:\n",
" # print(f\"VehicleType: {VehicleTypeDict[int(vehicle['VehicleType'])]}, VehicleNum: {vehicle['VehicleCount']}, Speed: {vehicle['SpaceMeanSpeed']}, Time: {vehicle['TravelTime']}\")\n",
" if int(vehicle['VehicleType']) == 31:\n",
" time_series_31data[f'{day}_{i}'] = int(vehicle['VehicleCount'])\n",
" elif int(vehicle['VehicleType']) == 32:\n",
" time_series_32data[f'{day}_{i}'] = int(vehicle['VehicleCount'])\n",
" elif int(vehicle['VehicleType']) == 41:\n",
" time_series_41data[f'{day}_{i}'] = int(vehicle['VehicleCount'])\n",
" elif int(vehicle['VehicleType']) == 42:\n",
" time_series_42data[f'{day}_{i}'] = int(vehicle['VehicleCount'])\n",
" elif int(vehicle['VehicleType']) == 5:\n",
" time_series_5data[f'{day}_{i}'] = int(vehicle['VehicleCount'])\n",
" except:\n",
" pass\n",
"\n",
"step = 6\n",
"plt.figure(figsize=(30,10))\n",
"plt.plot(list(time_series_31data.keys())[::step], list(time_series_31data.values())[::step], label=VehicleTypeDict[31])\n",
"plt.plot(list(time_series_32data.keys())[::step], list(time_series_32data.values())[::step], label=VehicleTypeDict[32])\n",
"plt.plot(list(time_series_41data.keys())[::step], list(time_series_41data.values())[::step], label=VehicleTypeDict[41])\n",
"plt.plot(list(time_series_42data.keys())[::step], list(time_series_42data.values())[::step], label=VehicleTypeDict[42])\n",
"plt.plot(list(time_series_5data.keys())[::step], list(time_series_5data.values())[::step], label=VehicleTypeDict[5])\n",
"plt.xlabel('Time')\n",
"plt.xticks(fontsize=14)\n",
"plt.xticks(rotation=60)\n",
"plt.ylabel('VehicleCount')\n",
"plt.title(f'{EtagStart} to {EtagEnd}')\n",
"plt.legend()\n",
"plt.show()"
]
}
],
"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": "3.11.7"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|