{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pdf2bib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def extract_metadata(file_path):\n",
    "    pdfextractdata = pdf2bib.pdf2bib(file_path)\n",
    "    #st.write(pdfextractdata)\n",
    "    pdfextractdata_metadata = {} if pdfextractdata.get('metadata', {}) is None else pdfextractdata.get('metadata', {})\n",
    "\n",
    "    return pdfextractdata_metadata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[pdf2bib]: Trying to extract data to generate the BibTeX entry for the file: boiteau-et-al-2024-relating-molecular-properties-to-the-persistence-of-marine-dissolved-organic-matter-with-liquid.pdf\n",
      "[pdf2bib]: Calling pdf2doi...\n",
      "[pdf2doi]: Trying to retrieve a DOI/identifier for the file: boiteau-et-al-2024-relating-molecular-properties-to-the-persistence-of-marine-dissolved-organic-matter-with-liquid.pdf\n",
      "[pdf2doi]: Method #1: Looking for a valid identifier in the document infos...\n",
      "[pdf2doi]: Validating the possible DOI 10.1021/acs.est.3c08245 via a query to dx.doi.org...\n",
      "[pdf2doi]: The DOI 10.1021/acs.est.3c08245 is validated by dx.doi.org.\n",
      "[pdf2doi]: A valid DOI was found in the document info labelled '/prism:doi'.\n",
      "[pdf2bib]: pdf2doi found a valid identifier for this paper.\n",
      "[pdf2bib]: Parsing the info returned by dx.doi.org...\n",
      "[pdf2bib]: A valid BibTeX entry was generated.\n"
     ]
    }
   ],
   "source": [
    "a = pdf2bib.pdf2bib(\"boiteau-et-al-2024-relating-molecular-properties-to-the-persistence-of-marine-dissolved-organic-matter-with-liquid.pdf\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'@article{boiteau2024relating,\\n\\ttitle = {Relating Molecular Properties to the Persistence of Marine Dissolved Organic Matter with Liquid Chromatography–Ultrahigh-Resolution Mass Spectrometry},\\n\\tpublisher = {American Chemical Society (ACS)},\\n\\turl = {http://dx.doi.org/10.1021/acs.est.3c08245},\\n\\tdoi = {10.1021/acs.est.3c08245},\\n\\tjournal = {Environmental Science & Technology},\\n\\tyear = {2024},\\n\\tmonth = {2},\\n\\tauthor = {Rene M. Boiteau and Yuri E. Corilo and William R. Kew and Christian Dewey and Maria Cristina Alvarez Rodriguez and Craig A. Carlson and Tim M. Conway}\\n}'"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "a.get(\"bibtex\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "import bibtexparser"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "parser = bibtex.Parser()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "parser = bibtexparser.bparser.BibTexParser(common_strings=True)\n",
    "bib_database = bibtexparser.loads(a.get(\"bibtex\"), parser=parser)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "def format_author_names(authors_str):\n",
    "    authors = authors_str.split(' and ')\n",
    "    formatted_authors = []\n",
    "    for author in authors:\n",
    "        parts = author.split()\n",
    "        if len(parts) == 2:  # Simple case: First Last\n",
    "            last, first = parts[1], parts[0]\n",
    "            formatted_authors.append(f\"{last}, {first[0]}.\")\n",
    "        elif len(parts) > 2:  # Handling middle names or initials\n",
    "            last = parts[-1]\n",
    "            initials = ''.join(f\"{part[0]}.\" for part in parts[:-1])\n",
    "            formatted_authors.append(f\"{last}, {initials}\")\n",
    "    if len(formatted_authors) > 1:\n",
    "        formatted_authors_str = ', '.join(formatted_authors[:-1]) + ', & ' + formatted_authors[-1]\n",
    "    else:\n",
    "        formatted_authors_str = formatted_authors[0]\n",
    "    return formatted_authors_str"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "def format_apa(entry):\n",
    "    author = format_author_names(entry.get('author', ''))\n",
    "    year = entry.get('year', '')\n",
    "    title = entry.get('title', '')\n",
    "    journal = entry.get('journal', '')\n",
    "    volume = entry.get('volume', '')\n",
    "    issue = entry.get('issue', '')\n",
    "    pages = entry.get('page', '').replace('-', '–')  # En dash for page range\n",
    "    doi = entry.get('doi', '')\n",
    "    \n",
    "    # Constructing the citation\n",
    "    apa_citation = f\"{author} {title}. {journal} {volume}, {pages} ({year}). https://doi.org/{doi}\"\n",
    "    return apa_citation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Boiteau, R.M., Corilo, Y.E., Kew, W.R., Dewey, C., Rodriguez, M.C.A., Carlson, C.A., & Conway, T.M. Relating Molecular Properties to the Persistence of Marine Dissolved Organic Matter with Liquid Chromatography–Ultrahigh-Resolution Mass Spectrometry. Environmental Science & Technology ,  (2024). https://doi.org/10.1021/acs.est.3c08245'"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "format_apa(bib_database.entries[0])"
   ]
  }
 ],
 "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": "3.10.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}