Paginated APIs with Python: Four ways!

Using paginated APIs (4 ways!).ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Paginated APIs: Four ways!\n",
    "\n",
    "1. Knowing how many pages/requests you'll need\n",
    "2. Doing what the API tells you\n",
    "3. Going until there are no more results\n",
    "4. Going until there is an error"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# https://pokeapi.co/api/v2/pokemon?limit=100"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "\n",
    "url = \"https://pokeapi.co/api/v2/pokemon?limit=100\"\n",
    "response = requests.get(url)\n",
    "data = response.json()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data['results']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "len(data['results'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://pokeapi.co/api/v2/pokemon?offset=100&limit=100\"\n",
    "response = requests.get(url)\n",
    "data = response.json()\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://pokeapi.co/api/v2/pokemon?offset=200&limit=100\"\n",
    "response = requests.get(url)\n",
    "data = response.json()\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://pokeapi.co/api/v2/pokemon?offset=1100&limit=100\"\n",
    "response = requests.get(url)\n",
    "data = response.json()\n",
    "data['results']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://pokeapi.co/api/v2/pokemon?offset=1200&limit=100\"\n",
    "response = requests.get(url)\n",
    "data = response.json()\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# https://pokeapi.co/api/v2/pokemon?offset=0&limit=100\n",
    "# https://pokeapi.co/api/v2/pokemon?offset=1100&limit=100\n",
    "\n",
    "limit = 100\n",
    "pokemon = []\n",
    "\n",
    "for page_num in range(12):\n",
    "    print(\"----\")\n",
    "    offset = page_num * limit\n",
    "    url = f\"https://pokeapi.co/api/v2/pokemon?offset={offset}&limit={limit}\"\n",
    "    print(\"Requesting\", url)\n",
    "\n",
    "    response = requests.get(url)\n",
    "    data = response.json()\n",
    "    pokemon.extend(data['results'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Method: We know how many pages we have method\n",
    "# Pros: Maybe easy to think about\n",
    "# Cons: You need to know how many pages it is, not very"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Listening to the API"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "response = requests.get(url)\n",
    "data = response.json()\n",
    "data['next']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = data['next']\n",
    "response = requests.get(url)\n",
    "data = response.json()\n",
    "data['next']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://pokeapi.co/api/v2/pokemon?limit=100\"\n",
    "pokemon = []\n",
    "\n",
    "while url:\n",
    "    print(\"----\")\n",
    "    print(\"Requesting\", url)\n",
    "\n",
    "    # Make the request\n",
    "    response = requests.get(url)\n",
    "    data = response.json()\n",
    "    \n",
    "    # Grab the new pokemon\n",
    "    pokemon.extend(data['results'])\n",
    "    \n",
    "    # Update the URL\n",
    "    url = data['next']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "len(pokemon)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Method: listening to the API\n",
    "# Pros: The API knows going on inside of it,\n",
    "#    good if you don't know how many pages/results there are\n",
    "# Cons: The API has to actually tell you the next page"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Going until there are no more results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://pokeapi.co/api/v2/pokemon?offset=1000&limit=100\"\n",
    "response = requests.get(url)\n",
    "data = response.json()\n",
    "data['results']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://pokeapi.co/api/v2/pokemon?offset=1100&limit=100\"\n",
    "response = requests.get(url)\n",
    "data = response.json()\n",
    "data['results']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://pokeapi.co/api/v2/pokemon?offset=1200&limit=100\"\n",
    "response = requests.get(url)\n",
    "data = response.json()\n",
    "data['results']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://pokeapi.co/api/v2/pokemon?limit=100\"\n",
    "pokemon = []\n",
    "offset = 0\n",
    "limit = 100\n",
    "\n",
    "while True:\n",
    "    print(\"----\")\n",
    "    url = f\"https://pokeapi.co/api/v2/pokemon?offset={offset}&limit={limit}\"\n",
    "    print(\"Requesting\", url)\n",
    "    response = requests.get(url)\n",
    "    data = response.json()\n",
    "\n",
    "    # Did we find any pokemon?\n",
    "    if len(data['results']) == 0:\n",
    "        # If not, exit the loop\n",
    "        break\n",
    "    \n",
    "    # If we did find pokemon, add them\n",
    "    # to our list and then move on to the next offset\n",
    "    pokemon.extend(data['results'])\n",
    "\n",
    "    offset = offset + 100"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Method: Going until no more results\n",
    "# Pros: Very flexible\n",
    "# Cons: Extra requests, doesn't really listen to the API, more lines of code"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Waiting until things break"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://pokeapi.co/api/v2/pokemon?limit=100\"\n",
    "pokemon = []\n",
    "offset = 0\n",
    "limit = 100\n",
    "\n",
    "while True:\n",
    "    print(\"----\")\n",
    "    url = f\"https://pokeapi.co/api/v2/pokemon?offset={offset}&limit={limit}\"\n",
    "    print(\"Requesting\", url)\n",
    "    response = requests.get(url)\n",
    "    data = response.json()\n",
    "\n",
    "    # Debug by printing out the first pokemon\n",
    "    try:\n",
    "        print(data['results'][0])        \n",
    "    except:\n",
    "        # We found an error!!!\n",
    "        print(\"There was an error! Exiting the loop\")\n",
    "        break\n",
    "    \n",
    "    # If we did find pokemon, add them\n",
    "    # to our list and then move on to the next offset\n",
    "    pokemon.extend(data['results'])\n",
    "\n",
    "    offset = offset + 100"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Method: Waiting until you hit an error with your processing\n",
    "# Pros: Super easy and flexible, good technique for scraping multiple pages\n",
    "# Cons: What if there's some OTHER error that isn't a \"you've run out of data\",\n",
    "#       looks more complicated"
   ]
  }
 ],
 "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": "3.8.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}