crawler example

main.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# import 建議放最上面\n",
    "import requests\n",
    "import re\n",
    "from bs4 import BeautifulSoup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "naibin@ms7.hinet.net\n",
      "jacob@mail.ypu.edu.tw\n",
      "reiheng@gmail.com\n",
      "suyu9966@yahoo.com.tw\n",
      "E-Mail：csie@mail.ypu.edu.tw\n",
      "cyberpaul747@mail.ypu.edu.tw\n",
      "djchou@mail.ypu.edu.tw\n",
      "E-MAIL： kuofeng@mail.ypu.edu.tw\n",
      "wyliu@mail.ypu.edu.tw\n",
      "ytchen@mail.ypu.edu.tw\n",
      "yitingchuang@yahoo.com\n",
      "neanben@mail.ypu.edu.tw\n",
      "wangts@seed.net.tw\n",
      "skchen@mail.ypu.edu.tw\n",
      "\n",
      "E-mail: howa@mail.ypu.edu.tw\n",
      "hcchan@mail.ypu.edu.tw\n",
      "cjchen@mail.ypu.edu.tw\n",
      "ikiyama@gmail.com\n",
      "lucyslin@gmail.com\n",
      "mhhuang@mail.ypu.edu.tw\n"
     ]
    }
   ],
   "source": [
    "def crawler():\n",
    "    for url01 in url_list:\n",
    "        pattern=re.compile(r'[a-zA-Z0-9_]+@[a-zA-Z0-9\\._]+')\n",
    "        res=requests.get(url01)\n",
    "        res.encoding = 'utf8'\n",
    "        soup=BeautifulSoup(res.text,'html.parser')\n",
    "        articles=soup.select(web_tag)\n",
    "        email_set=set()\n",
    "        for art in articles:\n",
    "            res2=requests.get(art['href'])\n",
    "            res2.encoding = 'utf8'\n",
    "            soup2=BeautifulSoup(res2.text,'html.parser')\n",
    "            email_set.add(soup2.find(text=pattern))\n",
    "        email_list=((\",\".join(list(email_set))).replace(\",\",\"\\n\")).replace(\";\",\"\\n\")\n",
    "        print(email_list)\n",
    "        email_set.clear() # 需要用email_set.clear()呼叫函式才會clear，你如果只有用email_set.clear什麼事情都不會發生\n",
    "    \n",
    "url_list=[\n",
    "    \"https://ndma.ypu.edu.tw/files/11-1077-82.php?Lang=zh-tw\",\n",
    "]\n",
    "\n",
    "url02 = \"http://civil.csu.edu.tw/wSite/\"\n",
    "web_tag = 'div.h5.title-noicon.title-center a' # 你要選到你說的那種元素，選擇器要這樣寫，建議去弄懂css selector的寫法\n",
    "\n",
    "crawler()"
   ]
  },
  {
   "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": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}