Parser for it-events

parse/DomainsResearch.ipynb

@@ -0,0 +1,135 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Исследование частоиспользуемых доменов"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import bs4, requests\n",
+    "import re\n",
+    "import pandas as pd\n",
+    "import meetup.api\n",
+    "import numpy as np\n",
+    "from matplotlib import pyplot as plt\n",
+    "import seaborn\n",
+    "from urllib.parse import urlparse"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0    https://www.meetup.com/ru-RU/CyberSecurityClub...\n",
+       "1                     https://noosphere.ru/hacknowlege\n",
+       "2    https://www.meetup.com/GolangKazan/events/2622...\n",
+       "3      https://www.facebook.com/events/649632242183168\n",
+       "4               https://index.timepad.ru/event/964050/\n",
+       "Name: link, dtype: object"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data = pd.read_csv(open('data.csv'))\n",
+    "data = data.dropna(subset=['link'])\n",
+    "data['link'].head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Топ-20 самых популярных доменов для организации мероприятий:\n",
+      "timepad            1144\n",
+      "vk                  400\n",
+      "yandex              349\n",
+      "redirect link       244\n",
+      "facebook            216\n",
+      "scout-gps           172\n",
+      "ingria-startup      128\n",
+      "meetup              117\n",
+      "dataart             116\n",
+      "mail                 92\n",
+      "dou                  91\n",
+      "ciseventsgroup       88\n",
+      "iidf                 85\n",
+      "luxoft-training      81\n",
+      "hse                  72\n",
+      "epam                 72\n",
+      "softline             61\n",
+      "polikom              59\n",
+      "cnews                58\n",
+      "codeib               52\n",
+      "Name: domains, dtype: int64\n"
+     ]
+    }
+   ],
+   "source": [
+    "def get_domain(ex):\n",
+    "    x = urlparse(ex).netloc\n",
+    "    l = x.replace('www.', '').replace('.ua', '').split('.')\n",
+    "    if len(l) > 1:\n",
+    "        y = l[-2]\n",
+    "        if y == 'google' and '/forms/' in ex:\n",
+    "            return 'google forms'\n",
+    "        if y == 'bit' or y == 'goo':\n",
+    "            return 'redirect link'\n",
+    "        return y\n",
+    "    return l[0]\n",
+    "# ex = 'https://www.facebook.com/events/649632242183168'\n",
+    "data['domains'] = data['link'].apply(get_domain)\n",
+    "domains = data['domains'].value_counts()\n",
+    "print('Топ-20 самых популярных доменов для организации мероприятий:')\n",
+    "print(domains.head(20))"
+   ]
+  },
+  {
+   "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": "3.7.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}