add author to draft

.gitignore

@@ -5,3 +5,4 @@ _site
 vendor
 .DS_Store
 _posts/.DS_Store
+assets/notebooks/.ipynb_checkpoints/

_posts/2020-05-01-start.md

@@ -2,6 +2,7 @@
 title: Где начать?
 date: 2020-05-01
 minutes: 7
+author: Rustem G
 ---
 
 Краткий пересказ [схемы Эндрю Ына](https://landing.ai/ai-transformation-playbook/)

assets/notebooks/0.2-rg-count-post-chars.ipynb

@@ -0,0 +1,132 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Count post chars"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 75,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "import json\n",
+    "import random\n",
+    "from bs4 import BeautifulSoup\n",
+    "import time"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 78,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "posts = {\n",
+    "    \"distinct-count\": \"https://rusteam.github.io/blog/2019/07/25/distinct-count\",\n",
+    "    \"data-clustering\": \"https://rusteam.github.io/blog/2020/05/25/data-clustering\",\n",
+    "    \"person-reid\": \"https://rusteam.github.io/blog/2019/06/11/person-reid\",\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 79,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class Article:\n",
+    "    def __init__(self, url):\n",
+    "        self.url = url\n",
+    "        \n",
+    "    def get_html(self):\n",
+    "        contents = requests.get(url).content.decode('utf-8')\n",
+    "        self.soup = BeautifulSoup(contents)\n",
+    "        self.texts = self.soup.find_all(['h2','h2','h3','h4','h5','h6','p', 'th', 'td'])\n",
+    "\n",
+    "    def count_chars(self):\n",
+    "        n_chars = 0\n",
+    "        for txt in self.texts:\n",
+    "            n_chars += len(txt.text)\n",
+    "        return n_chars\n",
+    "    \n",
+    "    def run(self):\n",
+    "        self.get_html()\n",
+    "        return self.count_chars()\n",
+    "    \n",
+    "    def show_random(self):\n",
+    "        tag = random.choice(self.texts)\n",
+    "        print('tag:', tag, end='\\n\\n')\n",
+    "        print('text:', tag.text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 81,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "distinct-count 4474 characters\n",
+      "data-clustering 5286 characters\n",
+      "person-reid 4212 characters\n"
+     ]
+    }
+   ],
+   "source": [
+    "for title,url in posts.items():\n",
+    "    a = Article(url)\n",
+    "    n_c = a.run()\n",
+    "    print(title, n_c, 'characters')\n",
+    "    time.sleep(0.5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "myblog",
+   "language": "python",
+   "name": "myblog"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.7"
+  },
+  "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
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}