질본 크롤링

LiveCoronaDetector · Mar 18, 2020 · 2154e89 · 2154e89
1 parent 224508a
commit 2154e89
Showing 1 changed file with 114 additions and 0 deletions.
diff --git a/002. korea_cumulative_data_crwler/002_질본_현황크롤링.ipynb b/002. korea_cumulative_data_crwler/002_질본_현황크롤링.ipynb
@@ -0,0 +1,114 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>확진환자</th>\n",
+       "      <th>격리해제</th>\n",
+       "      <th>격리중</th>\n",
+       "      <th>사망</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>8,413</td>\n",
+       "      <td>1,540</td>\n",
+       "      <td>6,789</td>\n",
+       "      <td>84</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    확진환자   격리해제    격리중  사망\n",
+       "0  8,413  1,540  6,789  84"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from bs4 import BeautifulSoup\n",
+    "from urllib.request import urlopen\n",
+    "import urllib.request\n",
+    "import pandas as pd\n",
+    "\n",
+    "html = urlopen(\"http://ncov.mohw.go.kr/bdBoardList_Real.do?brdId=1&brdGubun=11&ncvContSeq=&contSeq=&board_id=&gubun=\")\n",
+    "source = html.read()\n",
+    "html.close()\n",
+    "\n",
+    "soup = BeautifulSoup(source, 'lxml')\n",
+    "table = soup.find(\"div\", class_ = \"data_table mgt16\")\n",
+    "tables1 = table.find_all(\"th\")\n",
+    "tables2 = table.find_all(\"td\")\n",
+    "\n",
+    "status = []\n",
+    "for i in range(0,len(tables1)) :\n",
+    "    a = tables1[i].get_text()\n",
+    "    status.append(a)\n",
+    "\n",
+    "num=[]\n",
+    "for i in range(0, len(tables2)) :\n",
+    "    a = tables2[i].get_text()\n",
+    "    num.append(a)\n",
+    "\n",
+    "tot = []\n",
+    "tot.append(num)\n",
+    "tot = pd.DataFrame(tot)\n",
+    "\n",
+    "tot.rename(columns={tot.columns[0] : status[0],\n",
+    "                            tot.columns[1] : status[1],\n",
+    "                            tot.columns[2] : status[2],\n",
+    "                            tot.columns[3] : status[3]})"
+   ]
+  }
+ ],
+ "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": "3.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}