scrape_marathon_photo.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-02-26T12:53:52.960343Z",
     "start_time": "2019-02-26T12:53:52.701602Z"
    }
   },
   "outputs": [],
   "source": [
    "import requests \n",
    "import parsel\n",
    "import logging\n",
    "\n",
    "\n",
    "def get_photo_urls(event='2014 Сестрорецкий полумарафон', number=10):\n",
    "    URL = 'https://www.marathon-photo.ru/index.php'\n",
    "\n",
    "    params = {\n",
    "        'sphoto': 'on', # WHAT IS IT\n",
    "        'competition': event,\n",
    "        'search': number\n",
    "    }\n",
    "    \n",
    "    res = requests.get(URL.format(10), params=params)\n",
    "    logging.debug(res.url)\n",
    "    \n",
    "    sel = parsel.Selector(res.content.decode())\n",
    "    \n",
    "    \n",
    "    for part in sel.css('.tr2 img::attr(src)').getall():\n",
    "        yield 'https://www.marathon-photo.ru' + part \n",
    "        "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-02-26T12:53:52.960343Z",
     "start_time": "2019-02-26T12:53:52.701602Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['https://www.marathon-photo.ru/static2/preview1/stock-photo-10-101-223082.jpg']"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(get_photo_urls(number=101))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "jupytext": {
   "main_language": "python",
   "text_representation": {
    "extension": ".md",
    "format_name": "markdown",
    "format_version": "1.0",
    "jupytext_version": "0.8.5"
   }
  },
  "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"
  },
  "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": false
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}