add new basic pratice

Author: afunTW

00_GET_POST/00_GET_movie_board.ipynb

@@ -0,0 +1,95 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# 練習\n",
+    "\n",
+    "- 觀察 http://www.taipeibo.com/yearly/ 並撰寫爬蟲程式\n",
+    "- 抓取當年度週末冠軍排行榜\n",
+    "- 使用 requests + BeautifulSoup 實作\n",
+    "- 透過 pandas 輸出成 csv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "import pandas as pd\n",
+    "\n",
+    "from bs4 import BeautifulSoup\n",
+    "\n",
+    "url = 'http://www.taipeibo.com/yearly/'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "resp = requests.get(url)\n",
+    "resp.encoding = 'utf-8'\n",
+    "soup = BeautifulSoup(resp.text, 'lxml')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "5\n",
+      "4\n",
+      "<tr class=\"tb-top\">\n",
+      "<th>週次</th>\n",
+      "<th>日期</th>\n",
+      "<th>週末票房總和</th>\n",
+      "<th>漲跌幅</th>\n",
+      "<th>冠軍片名</th>\n",
+      "<th>英文片名</th>\n",
+      "<th class=\"import\">週末票房冠軍</th>\n",
+      "<th>冠軍比例*</th>\n",
+      "</tr>\n"
+     ]
+    }
+   ],
+   "source": [
+    "rows = soup.table.find_all('tr')\n",
+    "colname = rows.pop(0)"
+   ]
+  }
+ ],
+ "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": "3.5.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}