prototyping-times/mediawiki-api/mediawiki-api-download-images.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Download Images from one Wikipage\n",
    "\n",
    "(using the Mediawiki API)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import urllib\n",
    "import json\n",
    "from IPython.display import JSON # iPython JSON renderer\n",
    "import sys"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### API request > list of image filenames"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "wiki = 'https://pzwiki.wdka.nl/mw-mediadesign' # no slash at the end!\n",
    "page = 'Category:Situationist_Times'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = f'{ wiki }/api.php?action=parse&prop=images&page={ page }&format=json'\n",
    "response = urllib.request.urlopen(url).read()\n",
    "data = json.loads(response)\n",
    "JSON(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "images = data['parse']['images']\n",
    "# images = ['FILENAME.jpg', 'FILENAME2.jpg']\n",
    "\n",
    "# We have our variable \"images\"\n",
    "print(images)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Downloading the image files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Let's loop through this list and download each image!\n",
    "for filename in images:\n",
    "    print('Downloading:', filename)\n",
    "    \n",
    "    filename = filename.replace(' ', '_') # let's replace spaces again with _\n",
    "    filename = filename.replace('.jpg', '').replace('.gif', '').replace('.png','').replace('.jpeg','').replace('.JPG','').replace('.JPEG','') # and let's remove the file extension\n",
    "    \n",
    "    # first we search for the full filename of the image\n",
    "    url = f'https://pzwiki.wdka.nl/mw-mediadesign/api.php?action=query&list=allimages&aifrom={ filename }&format=json'\n",
    "    response = urllib.request.urlopen(url).read()\n",
    "    data = json.loads(response)\n",
    "    \n",
    "    # we select the first search result\n",
    "    # (assuming that this is the image we are looking for)\n",
    "    image = data['query']['allimages'][0]\n",
    "    \n",
    "    # then we download the image\n",
    "    image_url = image['url']\n",
    "    image_filename = image['name']\n",
    "    image_response = urllib.request.urlopen(image_url).read()\n",
    "    \n",
    "    # and we save it as a file\n",
    "    out = open(image_filename, 'wb') \n",
    "    out.write(image_response)\n",
    "    out.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}