parse data from mkrf.ru

Untitled5.ipynb

{
  "cells": [
    {
      "metadata": {
        "trusted": true,
        "collapsed": true
      },
      "cell_type": "code",
      "source": "import requests",
      "execution_count": 1,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false
      },
      "cell_type": "code",
      "source": "from bs4 import BeautifulSoup",
      "execution_count": 15,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": true
      },
      "cell_type": "code",
      "source": "r = requests.get(\"http://mkrf.ru/registr/\", {'q': 'Утомленные солнцем'.encode('cp1251')})",
      "execution_count": 51,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false
      },
      "cell_type": "code",
      "source": "bs = BeautifulSoup(r.text)",
      "execution_count": 54,
      "outputs": [
        {
          "output_type": "stream",
          "text": "/usr/local/lib/python3.5/site-packages/bs4/__init__.py:166: UserWarning: No parser was explicitly specified, so I'm using the best available HTML parser for this system (\"lxml\"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently.\n\nTo get rid of this warning, change this:\n\n BeautifulSoup([your markup])\n\nto this:\n\n BeautifulSoup([your markup], \"lxml\")\n\n  markup_type=markup_type))\n",
          "name": "stderr"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false
      },
      "cell_type": "code",
      "source": "[a['href'] for a in bs.find_all(\"table\")[1].find_all(\"a\")]",
      "execution_count": 59,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": "['/registr/detail.php?ID=156113132&q=%D3%F2%EE%EC%EB%E5%ED%ED%FB%E5+%F1%EE%EB%ED%F6%E5%EC',\n '/registr/detail.php?ID=123780497&q=%D3%F2%EE%EC%EB%E5%ED%ED%FB%E5+%F1%EE%EB%ED%F6%E5%EC',\n '/registr/detail.php?ID=148779834&q=%D3%F2%EE%EC%EB%E5%ED%ED%FB%E5+%F1%EE%EB%ED%F6%E5%EC',\n '/registr/detail.php?ID=146484465&q=%D3%F2%EE%EC%EB%E5%ED%ED%FB%E5+%F1%EE%EB%ED%F6%E5%EC']"
          },
          "metadata": {},
          "execution_count": 59
        }
      ]
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": true
      },
      "cell_type": "code",
      "source": "baseurl = \"http://mkrf.ru\"",
      "execution_count": 60,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false
      },
      "cell_type": "code",
      "source": "datas = []\nfor link in bs.find_all(\"table\")[1].find_all(\"a\")[:1]:\n    url = baseurl + link['href']\n    r = requests.get(url)\n    datas.append(BeautifulSoup(r.text))",
      "execution_count": 61,
      "outputs": [
        {
          "output_type": "stream",
          "text": "/usr/local/lib/python3.5/site-packages/bs4/__init__.py:166: UserWarning: No parser was explicitly specified, so I'm using the best available HTML parser for this system (\"lxml\"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently.\n\nTo get rid of this warning, change this:\n\n BeautifulSoup([your markup])\n\nto this:\n\n BeautifulSoup([your markup], \"lxml\")\n\n  markup_type=markup_type))\n",
          "name": "stderr"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": false
      },
      "cell_type": "code",
      "source": "datas[0].find_all(\"table\")[1]",
      "execution_count": 71,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": "<table align=\"center\" border=\"0\" cellpadding=\"3\" cellspacing=\"0\" class=\"table\" style=\"border-collapse: collapse;\" width=\"100%\">\n<tr>\n<td><b>Номер прокатного удостоверения</b></td>\n<td>1103394</td>\n</tr>\n<tr>\n<td><b>Дата прокатного удостоверения</b></td>\n<td>04.04.1994</td>\n</tr>\n<tr>\n<td><b>Категория прав проката</b></td>\n<td>Все права</td>\n</tr>\n<tr>\n<td><b>Окончание прав проката</b></td>\n<td></td>\n</tr>\n<tr>\n<td><b>Дополнительное описание прав проката</b></td>\n<td>на срок действия авторского права на фильм</td>\n</tr>\n<tr>\n<td><b>Фирма-заявитель</b></td>\n<td>Студия \"ТриТэ\", Роскомкино, фирма \"Русский Клуб\". Права проката у Студия \"ТриТэ\" на срок действия авторского права на фильм</td>\n</tr>\n<tr>\n<td><b>Телефон фирмы-заявителя</b></td>\n<td></td>\n</tr>\n<tr>\n<td><b>Номер договора</b></td>\n<td></td>\n</tr>\n<tr>\n<td><b>Дата заключения договора</b></td>\n<td></td>\n</tr>\n<tr>\n<td><b>Дата заполнения</b></td>\n<td>04.04.1994</td>\n</tr>\n</table>"
          },
          "metadata": {},
          "execution_count": 71
        }
      ]
    },
    {
      "metadata": {
        "trusted": true,
        "collapsed": true
      },
      "cell_type": "code",
      "source": "",
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3",
      "language": "python"
    },
    "language_info": {
      "version": "3.5.2",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "name": "python",
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "gist": {
      "id": "",
      "data": {
        "description": "parse data from mkrf.ru",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}