{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# **FBA.gov 조달서비스 크롤링**\n",
    "- https://www.fbo.gov/index.php?s=opportunity&amp=&pageID=3\n",
    "- https://www.fbo.gov/index.php?s=opportunity&mode=list&tab=list&tabmode=list&pp=100\n",
    "- https://www.fbo.gov/index.php?s=opportunity&mode=list&tab=list&tabmode=list&pp=100&pageID=2\n",
    "- https://www.fbo.gov/index.php?s=opportunity&mode=list&tab=list&tabmode=list"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## **1 전체 페이지에서 개별 목록 수집하기**\n",
    "https://github.com/SmugZombie/FBO_Parser/blob/master/fbo_parse.py\n",
    "\n",
    "```html\n",
    "<div class=\"solt\">Janitorial Service </div>,\n",
    "<div class=\"soln\">70FBR919Q00000072 </div>,\n",
    "<div class=\"solcc\">S -- Utilities and housekeeping services </div>\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# import requests\n",
    "# def html_download(url, method=\"get\", params=None, data=None):\n",
    "#     userAgent = {\"user-agent\":\"Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:61.0) Gecko/20100101 Firefox/61.0\"}\n",
    "#     return requests.request(method, url, params=params, data=data, headers= userAgent)\n",
    "\n",
    "# from bs4 import BeautifulSoup\n",
    "# url  = \"https://www.fbo.gov/index.php?s=opportunity&mode=list&tab=list&tabmode=list&pp=100\"\n",
    "# html = html_download(url)\n",
    "# dom  = BeautifulSoup(html.text, \"html.parser\") # 오류시 \n",
    "# type(html.text), type(dom)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(str, bs4.BeautifulSoup)"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# with open('fbo.html', \"w\") as f:\n",
    "#     f.write(html.text)\n",
    "with open('fbo.html', \"r\") as f:\n",
    "    html = f.read()\n",
    "\n",
    "from bs4 import BeautifulSoup\n",
    "dom  = BeautifulSoup(html, \"html.parser\") # 오류시 \n",
    "type(html), type(dom)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Janitorial Service ',\n",
       " '40--SWEEP WIRE,FAIRED STBD ',\n",
       " '40--WIRE ROPE ASSEMBLY, ',\n",
       " '51--JACK,SCREW,MECHANIC ',\n",
       " 'Notice of intent to sole source: Azure Biosystems Inc. ']"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 링크가 포함된 페이지만 추출하기\n",
    "link_pages = [_ for _ in dom.find(\"\", {\"class\":\"list\"}).find_all(\"a\")  \n",
    "              if str(_['href']).find(\"s=opportunity&mode=form&id\") != -1]\n",
    "\n",
    "# 추출 내용 중 제목만 추출\n",
    "[_.find(\"\", {\"class\":'solt'}).text    for _ in link_pages][:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['70FBR919Q00000072',\n",
       " 'SPE4A619T38X9',\n",
       " 'SPE4A619T828X',\n",
       " 'SPE4A619T13F9',\n",
       " '12905B19R8027']"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 추출 내용 중 ID만 추출\n",
    "[_.find(\"\", {\"class\":'soln'}).text.strip()   for _ in link_pages][:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['S -- Utilities and housekeeping services',\n",
       " '40 -- Rope, cable, chain & fittings',\n",
       " '40 -- Rope, cable, chain & fittings',\n",
       " '51 -- Hand tools',\n",
       " '99 -- Miscellaneous']"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 추출 내용 중 품목명 추출\n",
    "[_.find(\"\", {\"class\":'solcc'}).text.strip()   for _ in link_pages][:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'?s=opportunity&mode=form&id=8901b7da304242cf60579b4a94870a6d&tab=core&_cview=0'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 개별 페이지 링크 주소만 추출\n",
    "href_links = [_['href']    for _ in link_pages][:5]\n",
    "href_links[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>id</th>\n",
       "      <th>soln</th>\n",
       "      <th>solcc</th>\n",
       "      <th>href</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>70FBR919Q00000072</td>\n",
       "      <td>Janitorial Service</td>\n",
       "      <td>S -- Utilities and housekeeping services</td>\n",
       "      <td>https://www.fbo.gov/index.php?s=opportunity&amp;mo...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>SPE4A619T38X9</td>\n",
       "      <td>40--SWEEP WIRE,FAIRED STBD</td>\n",
       "      <td>40 -- Rope, cable, chain &amp; fittings</td>\n",
       "      <td>https://www.fbo.gov/index.php?s=opportunity&amp;mo...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>SPE4A619T828X</td>\n",
       "      <td>40--WIRE ROPE ASSEMBLY,</td>\n",
       "      <td>40 -- Rope, cable, chain &amp; fittings</td>\n",
       "      <td>https://www.fbo.gov/index.php?s=opportunity&amp;mo...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>SPE4A619T13F9</td>\n",
       "      <td>51--JACK,SCREW,MECHANIC</td>\n",
       "      <td>51 -- Hand tools</td>\n",
       "      <td>https://www.fbo.gov/index.php?s=opportunity&amp;mo...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>12905B19R8027</td>\n",
       "      <td>Notice of intent to sole source: Azure Biosyst...</td>\n",
       "      <td>99 -- Miscellaneous</td>\n",
       "      <td>https://www.fbo.gov/index.php?s=opportunity&amp;mo...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  id                                               soln  \\\n",
       "0  70FBR919Q00000072                                 Janitorial Service   \n",
       "1      SPE4A619T38X9                         40--SWEEP WIRE,FAIRED STBD   \n",
       "2      SPE4A619T828X                            40--WIRE ROPE ASSEMBLY,   \n",
       "3      SPE4A619T13F9                            51--JACK,SCREW,MECHANIC   \n",
       "4      12905B19R8027  Notice of intent to sole source: Azure Biosyst...   \n",
       "\n",
       "                                      solcc  \\\n",
       "0  S -- Utilities and housekeeping services   \n",
       "1       40 -- Rope, cable, chain & fittings   \n",
       "2       40 -- Rope, cable, chain & fittings   \n",
       "3                          51 -- Hand tools   \n",
       "4                       99 -- Miscellaneous   \n",
       "\n",
       "                                                href  \n",
       "0  https://www.fbo.gov/index.php?s=opportunity&mo...  \n",
       "1  https://www.fbo.gov/index.php?s=opportunity&mo...  \n",
       "2  https://www.fbo.gov/index.php?s=opportunity&mo...  \n",
       "3  https://www.fbo.gov/index.php?s=opportunity&mo...  \n",
       "4  https://www.fbo.gov/index.php?s=opportunity&mo...  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "url  = \"https://www.fbo.gov/index.php?s=opportunity&mode=list&tab=list&tabmode=list&pp=100\"\n",
    "\n",
    "import pandas as pd\n",
    "import requests\n",
    "fbo_links          = pd.DataFrame()\n",
    "fbo_links['id']    = [_.find(\"\", {\"class\":'soln'}).text.strip()   for _ in link_pages]\n",
    "fbo_links['soln']  = [_.find(\"\", {\"class\":'solt'}).text.strip()   for _ in link_pages]\n",
    "fbo_links['solcc'] = [_.find(\"\", {\"class\":'solcc'}).text.strip()  for _ in link_pages]\n",
    "# fbo_links['href']  = [_['href']   for _ in link_pages]\n",
    "fbo_links['href']  = [requests.compat.urljoin(url, _['href'])     for _ in link_pages]\n",
    "fbo_links.head()"
   ]
  }
 ],
 "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}