{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "seven-miniature",
   "metadata": {},
   "outputs": [],
   "source": [
    "import trafilatura"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "swedish-murder",
   "metadata": {},
   "outputs": [],
   "source": [
    "downloaded = trafilatura.fetch_url('https://traffickingculture.org/encyclopedia/case-studies/giacomo-medici/')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "indie-payroll",
   "metadata": {},
   "outputs": [],
   "source": [
    "medici = trafilatura.extract(downloaded)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "cubic-rings",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "ERROR:trafilatura.downloads:retries/redirects: https://traffickingculture.org/encyclopedia/theory-and-method/ HTTPSConnectionPool(host='traffickingculture.org', port=443): Max retries exceeded with url: /encyclopedia/theory-and-method/ (Caused by ProtocolError('Connection aborted.', RemoteDisconnected('Remote end closed connection without response',)))\n",
      "ERROR:trafilatura.downloads:retries/redirects: https://traffickingculture.org/people/ HTTPSConnectionPool(host='traffickingculture.org', port=443): Max retries exceeded with url: /people/ (Caused by ProtocolError('Connection aborted.', RemoteDisconnected('Remote end closed connection without response',)))\n"
     ]
    }
   ],
   "source": [
    "!trafilatura --crawl \"https://traffickingculture.org/encyclopedia/a\" > trafficking_culture_links.txt"
   ]
  }
 ],
 "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": "3.6.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}