scraping_post.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from bs4 import BeautifulSoup\n",
    "import requests"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = requests.get('https://bolajiolajide.github.io')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "source = BeautifulSoup(url.text, 'html.parser')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "post_feed = source.find('div', class_=\"post-feed\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "posts = post_feed.find_all('article', class_=\"post-card\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "single_post = posts[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "title = single_post.find('h2', class_='post-card-title')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "u'Recursion For Beginners'"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "title.text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "excerpt = single_post.find('section', class_=\"post-card-excerpt\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "u'What is recursion? Recursion is a method where the solution to a problem depends on solutions to smaller instances of the same problem (as opposed to iteration). The approach can be applied to'"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "excerpt.p.text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "author = single_post.find('span', class_=\"post-card-author\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "u'Bolaji Olajide'"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "author.a.text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_post_details(article):\n",
    "    title = article.find('h2', class_='post-card-title').text\n",
    "    excerpt = article.find('section', class_='post-card-excerpt').p.text\n",
    "    author = article.find('span', class_='post-card-author').a.text\n",
    "    return {\n",
    "        \"title\": title,\n",
    "        \"excerpt\": excerpt,\n",
    "        \"author\": author\n",
    "    }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Making use of list comprehension instead of loops\n",
    "blog_posts = [get_post_details(post) for post in posts ];"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'author': u'Bolaji Olajide',\n",
       "  'excerpt': u'What is recursion? Recursion is a method where the solution to a problem depends on solutions to smaller instances of the same problem (as opposed to iteration). The approach can be applied to',\n",
       "  'title': u'Recursion For Beginners'},\n",
       " {'author': u'Bolaji Olajide',\n",
       "  'excerpt': u'One of the amazing things about the Python language is the use of decorators to alter functionality. Decorators are used to extend functions without actually modifying them directly.',\n",
       "  'title': u'Creating a Simple Python Decorator'},\n",
       " {'author': u'Bolaji Olajide',\n",
       "  'excerpt': u'Learning is the process of acquiring new or modifying existing knowledge, behaviors, skills, values, or preferences.',\n",
       "  'title': u'The Art of Learning\\u200a\\u2014\\u200aMy Learning Process'}]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "blog_posts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "blog_posts = []\n",
    "for post in posts:\n",
    "    blog_posts.append(get_post_details(post))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[{'author': u'Bolaji Olajide',\n",
       "  'excerpt': u'What is recursion? Recursion is a method where the solution to a problem depends on solutions to smaller instances of the same problem (as opposed to iteration). The approach can be applied to',\n",
       "  'title': u'Recursion For Beginners'},\n",
       " {'author': u'Bolaji Olajide',\n",
       "  'excerpt': u'One of the amazing things about the Python language is the use of decorators to alter functionality. Decorators are used to extend functions without actually modifying them directly.',\n",
       "  'title': u'Creating a Simple Python Decorator'},\n",
       " {'author': u'Bolaji Olajide',\n",
       "  'excerpt': u'Learning is the process of acquiring new or modifying existing knowledge, behaviors, skills, values, or preferences.',\n",
       "  'title': u'The Art of Learning\\u200a\\u2014\\u200aMy Learning Process'}]"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "blog_posts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}