{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "KoiuqPnaQL9Z"
   },
   "source": [
    "# COVID-19 Literature Publication Times extracted from PubMed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "W4-_oZ4KQpTr"
   },
   "outputs": [],
   "source": [
    "import lzma\n",
    "import urllib.request\n",
    "\n",
    "import pandas\n",
    "import tqdm.notebook\n",
    "from pubmedpy.eutilities import download_pubmed_ids"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "KYSST0tvP6Q_"
   },
   "source": [
    "Download articles that are part of [LitCovid](https://www.ncbi.nlm.nih.gov/research/coronavirus/):\n",
    "\n",
    "> **Keep up with the latest coronavirus research**  \n",
    "Qingyu Chen, Alexis Allot, Zhiyong Lu  \n",
    "*Nature* (2020-03-10) <https://doi.org/ggq9fd>  \n",
    "DOI: [10.1038/d41586-020-00694-1](https://doi.org/10.1038/d41586-020-00694-1) · PMID: [32157233](https://www.ncbi.nlm.nih.gov/pubmed/32157233)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'attachment; filename=05272020.litcovid.export.tsv'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "url = \"https://www.ncbi.nlm.nih.gov/research/coronavirus-api/export/tsv\"\n",
    "_filename, headers = urllib.request.urlretrieve(url, filename=\"data/litcovid.tsv\")\n",
    "# show dated filename\n",
    "headers.get(\"Content-Disposition\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "colab_type": "code",
    "id": "-BzMAdh8Pk_s",
    "outputId": "83145bbc-4a24-4bfe-acc9-7ea43016af21"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>pmid</th>\n",
       "      <th>title</th>\n",
       "      <th>journal</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>32450607</td>\n",
       "      <td>Gastrointestinal: Bowel ischemia in a suspecte...</td>\n",
       "      <td>J Gastroenterol Hepatol</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>32450565</td>\n",
       "      <td>Novel Coronavirus-Induced Right Ventricular Fa...</td>\n",
       "      <td>Cardiology</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>32450560</td>\n",
       "      <td>COVID-19, Low-Molecular-Weight Heparin, and He...</td>\n",
       "      <td>Kidney Blood Press Res</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>32450492</td>\n",
       "      <td>Mental health and COVID-19 in Nepal: A case of...</td>\n",
       "      <td>Asian J Psychiatr</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>32450477</td>\n",
       "      <td>Hardware versus heartware: The need to address...</td>\n",
       "      <td>J Clin Anesth</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       pmid                                              title  \\\n",
       "0  32450607  Gastrointestinal: Bowel ischemia in a suspecte...   \n",
       "1  32450565  Novel Coronavirus-Induced Right Ventricular Fa...   \n",
       "2  32450560  COVID-19, Low-Molecular-Weight Heparin, and He...   \n",
       "3  32450492  Mental health and COVID-19 in Nepal: A case of...   \n",
       "4  32450477  Hardware versus heartware: The need to address...   \n",
       "\n",
       "                   journal  \n",
       "0  J Gastroenterol Hepatol  \n",
       "1               Cardiology  \n",
       "2   Kidney Blood Press Res  \n",
       "3        Asian J Psychiatr  \n",
       "4            J Clin Anesth  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "litcovid_df = pandas.read_table(\"data/litcovid.tsv\", comment=\"#\")\n",
    "litcovid_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "ld1rcf9XQEFQ",
    "outputId": "800209fc-a8a5-4d19-8f8a-7e3ce283acd4"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "16,405 articles in litcovid.tsv\n"
     ]
    }
   ],
   "source": [
    "print(f'{len(litcovid_df):,} articles in litcovid.tsv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "2kQ9lrGYa4Li"
   },
   "outputs": [],
   "source": [
    "path = \"data/litcovid-esummaries.xml.xz\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 83,
     "referenced_widgets": [
      "22e49cf0280d40bb8a0061686cb7e107",
      "30ce2c66e12b4bfba400058e5ccb75b7",
      "26dc39c2a5bb4a9b9fc4fbd39deb2dda",
      "960e519c1af74b49b48979d8ffd22135",
      "51ee38b2a1724256aa50a38b64497d51",
      "3c2086081e9d49be81e2c0825440b87e",
      "cc361014924b4767bf8729b08ecfe2d8",
      "2587e775e07f4829903d669be5998611"
     ]
    },
    "colab_type": "code",
    "id": "cXFIYDrRRiQD",
    "outputId": "4c7d8d72-c148-442d-fee0-fbdf38837b4a"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "16,405\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "36ba6bcca9f94eaabcabd84987b8173c",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(FloatProgress(value=0.0, max=16405.0), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING:root:1 successive error: 200 IDs[32355056 … 32358406] threw HTTPSConnectionPool(host='eutils.ncbi.nlm.nih.gov', port=443): Max retries exceeded with url: /entrez/eutils/esummary.fcgi?db=pubmed&id=32355056%2C32355099%2C32355107%2C32355114%2C32355115%2C32355116%2C32355117%2C32355118%2C32355119%2C32355131%2C32355132%2C32355222%2C32355243%2C32355260%2C32355296%2C32355299%2C32355328%2C32355329%2C32355330%2C32355392%2C32355394%2C32355415%2C32355424%2C32355435%2C32355447%2C32355450%2C32355509%2C32355510%2C32355546%2C32355547%2C32355555%2C32355556%2C32355564%2C32355606%2C32355607%2C32355634%2C32355638%2C32355651%2C32355653%2C32355658%2C32355659%2C32355694%2C32355837%2C32355863%2C32355869%2C32355889%2C32355892%2C32355904%2C32355949%2C32355961%2C32355962%2C32355982%2C32355985%2C32356025%2C32356031%2C32356032%2C32356040%2C32356047%2C32356096%2C32356161%2C32356164%2C32356225%2C32356251%2C32356252%2C32356294%2C32356298%2C32356301%2C32356302%2C32356307%2C32356322%2C32356356%2C32356382%2C32356422%2C32356423%2C32356460%2C32356508%2C32356510%2C32356516%2C32356569%2C32356573%2C32356577%2C32356578%2C32356580%2C32356583%2C32356590%2C32356601%2C32356603%2C32356625%2C32356626%2C32356627%2C32356628%2C32356639%2C32356640%2C32356641%2C32356642%2C32356654%2C32356672%2C32356698%2C32356760%2C32356761%2C32356777%2C32356849%2C32356857%2C32356858%2C32356863%2C32356866%2C32356867%2C32356869%2C32356871%2C32356896%2C32356900%2C32356908%2C32356910%2C32356926%2C32356927%2C32356944%2C32356945%2C32356955%2C32357070%2C32357072%2C32357074%2C32357084%2C32357086%2C32357206%2C32357209%2C32357210%2C32357257%2C32357273%2C32357275%2C32357277%2C32357281%2C32357288%2C32357307%2C32357377%2C32357378%2C32357379%2C32357380%2C32357381%2C32357424%2C32357457%2C32357471%2C32357503%2C32357545%2C32357553%2C32357575%2C32357582%2C32357655%2C32357675%2C32357808%2C32357883%2C32357949%2C32357950%2C32357952%2C32357954%2C32357957%2C32357959%2C32357975%2C32357976%2C32357977%2C32357978%2C32357994%2C32357995%2C32357996%2C32357997%2C32357998%2C32358044%2C32358045%2C32358057%2C32358098%2C32358099%2C32358105%2C32358107%2C32358120%2C32358121%2C32358130%2C32358131%2C32358134%2C32358142%2C32358176%2C32358180%2C32358202%2C32358203%2C32358216%2C32358217%2C32358218%2C32358227%2C32358228%2C32358229%2C32358230%2C32358231%2C32358232%2C32358233%2C32358234%2C32358250%2C32358303%2C32358311%2C32358312%2C32358325%2C32358326%2C32358406&rettype=xml (Caused by NewConnectionError('<urllib3.connection.HTTPSConnection object at 0x7f3764988280>: Failed to establish a new connection: [Errno -2] Name or service not known'))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "pubmed_ids = sorted(map(int, litcovid_df.pmid))\n",
    "print(f'{len(pubmed_ids):,}')\n",
    "\n",
    "with lzma.open(path, 'wt') as write_file:\n",
    "    download_pubmed_ids(\n",
    "        pubmed_ids, write_file, endpoint='esummary',\n",
    "        retmax=200, retmin=50, sleep=0, error_sleep=1,\n",
    "        tqdm=tqdm.notebook.tqdm,\n",
    "    )"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "covid-publication-times.ipynb",
   "provenance": []
  },
  "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": "3.8.2"
  },
  "widgets": {
   "application/vnd.jupyter.widget-state+json": {
    "22e49cf0280d40bb8a0061686cb7e107": {
     "model_module": "@jupyter-widgets/controls",
     "model_name": "HBoxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HBoxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HBoxView",
      "box_style": "",
      "children": [
       "IPY_MODEL_26dc39c2a5bb4a9b9fc4fbd39deb2dda",
       "IPY_MODEL_960e519c1af74b49b48979d8ffd22135"
      ],
      "layout": "IPY_MODEL_30ce2c66e12b4bfba400058e5ccb75b7"
     }
    },
    "2587e775e07f4829903d669be5998611": {
     "model_module": "@jupyter-widgets/base",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "26dc39c2a5bb4a9b9fc4fbd39deb2dda": {
     "model_module": "@jupyter-widgets/controls",
     "model_name": "FloatProgressModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "FloatProgressModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "ProgressView",
      "bar_style": "success",
      "description": "100%",
      "description_tooltip": null,
      "layout": "IPY_MODEL_3c2086081e9d49be81e2c0825440b87e",
      "max": 10,
      "min": 0,
      "orientation": "horizontal",
      "style": "IPY_MODEL_51ee38b2a1724256aa50a38b64497d51",
      "value": 10
     }
    },
    "30ce2c66e12b4bfba400058e5ccb75b7": {
     "model_module": "@jupyter-widgets/base",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "3c2086081e9d49be81e2c0825440b87e": {
     "model_module": "@jupyter-widgets/base",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "51ee38b2a1724256aa50a38b64497d51": {
     "model_module": "@jupyter-widgets/controls",
     "model_name": "ProgressStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ProgressStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "bar_color": null,
      "description_width": "initial"
     }
    },
    "960e519c1af74b49b48979d8ffd22135": {
     "model_module": "@jupyter-widgets/controls",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_2587e775e07f4829903d669be5998611",
      "placeholder": "​",
      "style": "IPY_MODEL_cc361014924b4767bf8729b08ecfe2d8",
      "value": " 10/10 [03:24&lt;00:00, 20.48s/articles]"
     }
    },
    "cc361014924b4767bf8729b08ecfe2d8": {
     "model_module": "@jupyter-widgets/controls",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    }
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}