Search Alt (Right) Media

searchaltmedia.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import requests\n",
    "from bs4 import BeautifulSoup\n",
    "import io"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def searchaltmedia(searchstring):\n",
    "    urls = ['http://nyheteridag.se/?s=',\n",
    "           'http://avpixlat.info/?s=',\n",
    "           'http://www.friatider.se/search/node/',\n",
    "           'http://www.klarvaken.se/?s=',\n",
    "           'https://www.nordfront.se/?s=',\n",
    "           'https://www.nyanserat.nu/?s=',\n",
    "           'http://samtiden.nu/?s=']\n",
    "    \n",
    "    results = []\n",
    "\n",
    "    for u in urls:\n",
    "        r = requests.get(u + searchstring)\n",
    "        file_like_obj = io.StringIO(r.text)    \n",
    "        lines = file_like_obj.read()\n",
    "        soup = BeautifulSoup(lines, \"lxml\")\n",
    "        \n",
    "        if u == 'http://avpixlat.info/?s=':\n",
    "            posturls = soup.findAll(\"div\", { \"class\" : \"post-headline\" })\n",
    "            for p in posturls:\n",
    "                #print(p.find('a').attrs['href'])\n",
    "                results.append(p.find('a').attrs['href'])\n",
    "                \n",
    "        elif u == 'http://nyheteridag.se/?s=' :   \n",
    "            posturls = soup.findAll(\"div\", { \"class\" : \"article\" })\n",
    "            for p in posturls:\n",
    "                #print(p.find('a').attrs['href'])\n",
    "                results.append(p.find('a').attrs['href'])\n",
    "       \n",
    "        elif u == 'http://www.friatider.se/search/node/':\n",
    "            posturls = soup.findAll(\"h3\", { \"class\" : \"title\" })\n",
    "            for p in posturls:\n",
    "                #print(p.find('a').attrs['href'])\n",
    "                results.append(p.find('a').attrs['href'])\n",
    "                \n",
    "        elif u == 'http://www.klarvaken.se/?s=':\n",
    "            posturls = soup.findAll(\"span\", { \"class\" : \"posted-on\" })\n",
    "            for p in posturls:\n",
    "                #print(p.find('a').attrs['href'])\n",
    "                results.append(p.find('a').attrs['href'])\n",
    "        \n",
    "        elif u == 'https://www.nordfront.se/?s=':\n",
    "            posturls = soup.findAll(\"h2\", { \"class\" : \"post-title\" })\n",
    "            for p in posturls:\n",
    "                #print(p.find('a').attrs['href'])\n",
    "                results.append(p.find('a').attrs['href'])\n",
    "        \n",
    "        elif u == 'https://www.nyanserat.nu/?s=':\n",
    "            posturls = soup.findAll(\"h2\", { \"class\" : \"post-title\" })\n",
    "            for p in posturls:\n",
    "                #print(p.find('a').attrs['href'])\n",
    "                results.append(p.find('a').attrs['href'])\n",
    "            \n",
    "        elif u == 'http://samtiden.nu/?s=':\n",
    "            posturls = soup.findAll(\"h2\", { \"class\" : \"cb-post-title\" })\n",
    "            for p in posturls:\n",
    "                #print(p.find('a').attrs['href'])\n",
    "                results.append(p.find('a').attrs['href'])\n",
    "\n",
    "         \n",
    "    return results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['http://nyheteridag.se/rikspolischef-eliasson-kopplar-in-sapo-ska-forhindra-stod-till-sd-i-valrorelsen/',\n",
       " 'http://nyheteridag.se/fuck-trump-fuck-white-people-livesand-tortyr-av-forstandshandikappad-pa-facebook/',\n",
       " 'http://nyheteridag.se/utredningen-laggs-ner-rullstolsburen-kvinna-pa-gotland-anmalde-gruppvaldtakt-pa-toalett/',\n",
       " 'http://nyheteridag.se/timbro-chef-varnar-for-att-moderaterna-kan-gora-katastrofval/',\n",
       " 'http://avpixlat.info/2016/12/04/snoflingor-och-snoslungor/',\n",
       " 'http://www.friatider.se/s-topp-hoppar-av-i-protest-mot-migrationsverket',\n",
       " 'http://www.friatider.se/dn-halvpudlar-om-brandm-n-i-boden',\n",
       " 'http://www.friatider.se/expressen-profil-hyllar-brevb-rare-som-sl-nger-bort-sd-valsedlar',\n",
       " 'http://www.friatider.se/svd-kultur-r-tt-f-ngsla-misshagliga-konstn-rer',\n",
       " 'http://www.friatider.se/dn-h-nas-p-n-tet-efter-brandmansbluff',\n",
       " 'http://www.friatider.se/dn-lj-g-om-rasism-p-brandstation-i-boden',\n",
       " 'http://www.friatider.se/ilska-och-gr-t-p-gp-n-r-40-journalister-f-r-sparken',\n",
       " 'http://www.friatider.se/klart-f-r-le-pens-partigrupp',\n",
       " 'https://www.nordfront.se/kamparbete-i-are-kommun-2.smr',\n",
       " 'https://www.nordfront.se/dns-troll-spricker-solen.smr',\n",
       " 'https://www.nyanserat.nu/dr-frank-salter-om-det-tyska-risktagandet/']"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "searchaltmedia('ljugmedia')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python [default]",
   "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}