{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Web scraping"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-25T10:30:12.743707Z",
     "start_time": "2020-06-25T10:30:12.457375Z"
    }
   },
   "outputs": [],
   "source": [
    "import requests\n",
    "from bs4 import BeautifulSoup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-25T10:30:13.221448Z",
     "start_time": "2020-06-25T10:30:13.205396Z"
    }
   },
   "outputs": [],
   "source": [
    "def get_soup(session, url):\n",
    "    \"\"\"Convenience function to use a session to get the soup of a webpage.\"\"\"\n",
    "    response = session.get(url)\n",
    "    response.raise_for_status()\n",
    "    return BeautifulSoup(response.text, \"lxml\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Get all the links on our homepage"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-25T10:30:14.582116Z",
     "start_time": "2020-06-25T10:30:14.513037Z"
    }
   },
   "outputs": [],
   "source": [
    "session = requests.Session()\n",
    "base_url = \"https://www.physik.uzh.ch/~python/python\"\n",
    "soup = get_soup(session, f\"{base_url}/programme.php\")\n",
    "links = [a['href'] for a in soup.select(\"a.internal\")]\n",
    "print(links)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-25T10:30:16.058054Z",
     "start_time": "2020-06-25T10:30:16.054613Z"
    }
   },
   "outputs": [],
   "source": [
    "def download(url, file_name):\n",
    "    response = requests.get(url) \n",
    "    response.raise_for_status()\n",
    "    with open(file_name, \"wb\") as f:\n",
    "        f.write(response.content)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-25T10:30:16.765122Z",
     "start_time": "2020-06-25T10:30:16.577318Z"
    }
   },
   "outputs": [],
   "source": [
    "for link in links:\n",
    "    soup = get_soup(session, f\"{base_url}/{link}\")\n",
    "    print(soup.title.text.split(\" - \")[-1])\n",
    "    for file_name in [a['href'] for a in soup.select(\"a.download\")]:\n",
    "        url = f\"{base_url}/{link}/{file_name}\"\n",
    "        print(url)\n",
    "        # uncomment this to actually download the files:\n",
    "        # download(url, file_name)\n",
    "    print()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Subprocess"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-25T10:30:24.872326Z",
     "start_time": "2020-06-25T10:30:24.869649Z"
    }
   },
   "outputs": [],
   "source": [
    "import subprocess"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Python 3.7+"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-25T10:30:25.463931Z",
     "start_time": "2020-06-25T10:30:25.378149Z"
    },
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "r = subprocess.run([\"du\", \"-h\", \".\"], capture_output=True)\n",
    "print(r.stdout)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-06-25T10:30:28.663280Z",
     "start_time": "2020-06-25T10:30:28.653155Z"
    }
   },
   "outputs": [],
   "source": [
    "subprocess.run([\"cat\"], capture_output=True, input=b\"test\")\n",
    "print(r.stdout)"
   ]
  },
  {
   "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": "3.8.10"
  },
  "latex_envs": {
   "LaTeX_envs_menu_present": true,
   "autoclose": false,
   "autocomplete": true,
   "bibliofile": "biblio.bib",
   "cite_by": "apalike",
   "current_citInitial": 1,
   "eqLabelWithNumbers": true,
   "eqNumInitial": 1,
   "hotkeys": {
    "equation": "Ctrl-E",
    "itemize": "Ctrl-I"
   },
   "labels_anchors": false,
   "latex_user_defs": false,
   "report_style_numbering": false,
   "user_envs_cfg": false
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": true
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}