{
 "cells": [
{
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "14 - CV Lattes para avaliação\n"
     ]
    }
   ],
   "source": [
    "#importar lista e lattes do arquivo listalattes.xlsx\n",
    "list_lattes = pd.read_excel('listalattes.xlsx', header= None, index_col= None)   \n",
    "list_lattes = list_lattes[0]\n",
    "print(len(list_lattes), '- CV Lattes para avaliação')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Linhas Prod de  Andreza Portella Ribeiro :  37\n",
      "Linhas Prod de  Carlos Leite de Souza :  53\n",
      "Linhas Prod de  Cintia Elisa de Castro Marino :  0\n",
      "Linhas Prod de  Cristiano Capellani Quaresma :  17\n",
      "Linhas Prod de  Diego de Melo Conti :  13\n",
      "Linhas Prod de  Heidy Rodriguez Ramos :  40\n",
      "Linhas Prod de  Humberto Dantas de Mizuca :  52\n",
      "Linhas Prod de  João Alexandre Paschoalin Filho :  34\n",
      "Linhas Prod de  José Eduardo Storopoli :  19\n",
      "Linhas Prod de  Jose Ricardo Marar :  1\n",
      "Linhas Prod de  Luís Fernando Massonetto :  11\n",
      "Linhas Prod de  Maurício Lamano Ferreira :  39\n",
      "Linhas Prod de  Tatiana Tucunduva Philippi Cortese :  17\n",
      "Linhas Prod de  Wilson Levy Braga da Silva Neto :  28\n"
     ]
    }
   ],
   "source": [
    "prod_df = pd.DataFrame()\n",
    "for row in list_lattes:\n",
    "    url = row\n",
    "    page = requests.get(url)\n",
    "    #Parse o HTML\n",
    "    soup = BeautifulSoup(page.text, 'html.parser')\n",
    "    #Achar nome do titular do CV Lattes\n",
    "    name = soup.find(class_='nome')\n",
    "    name = name.text\n",
    "    #Achar todos os artigos completos publicados em periodicos\n",
    "    tb = soup.find_all('div', class_='artigo-completo') \n",
    "    #fazer uma lista com cada um dos anos e ISSN\n",
    "    ano=[]\n",
    "    for i in tb:\n",
    "        inf_ano = i.find_all('span', class_='informacao-artigo')[2]\n",
    "        ano.append(inf_ano.text)\n",
    "    issn=[]\n",
    "    for i in tb:\n",
    "        try:\n",
    "            inf_issn = i.img.get('data-issn')\n",
    "        except AttributeError:\n",
    "            issn.append(None)\n",
    "        else:\n",
    "            issn.append(inf_issn)\n",
    "    #fazer uma lista com cada um dos artigos completos\n",
    "    prod = []\n",
    "    for i in tb:\n",
    "        prod.append(i.text)\n",
    "    print('Linhas Prod de ', name, ': ', len(prod))\n",
    "    #remover duplicados de cada artigo\n",
    "    prod = [re.sub('\\n\\d{1,2}\\.', '', i) for i in prod]\n",
    "    prod = [re.sub('\\n', '', i) for i in prod]\n",
    "    prod = [re.sub('.*\\.\\d{4}', '',i) for i in prod]\n",
    "    prod = [re.sub('\\d{1,2}\\w*\\,\\s\\w*\\B\\d{4}', '',i) for i in prod]\n",
    "    prod = [re.sub('\\d{1,2}\\w{2,}\\s\\w{2,}\\d{4}', '',i) for i in prod]\n",
    "    prod = [re.sub('\\w{2,}\\s\\w{2,}\\,\\s[\\wÀ-ú]*\\d{4}', '',i) for i in prod]\n",
    "    prod = [re.sub('\\w{2,}\\,\\s[\\wÀ-ú]*\\s[\\wÀ-ú]*\\d{4}', '',i) for i in prod]\n",
    "    #duplicar o nome para o tamanho da lista dos artigos publicados\n",
    "    name_list = [name] * len(prod)\n",
    "    new_df = pd.DataFrame(\n",
    "    {'Nome': name_list,\n",
    "     'Ano': ano,\n",
    "     'ArtigosCompletos': prod,\n",
    "     'ISSN': issn\n",
    "    })\n",
    "    prod_df = prod_df.append(new_df, ignore_index=True)"
   ]
  }
  ],
    "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}