zotero_remove_eprint_extra.ipynb

zotero_remove_eprint_extra.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyMN2Bb29302uSN0wMr39SHs",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/kleinlennart/17721697b03b9e4c3e00417e189c20a8/zotero_remove_eprint_extra.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# https://github.com/urschrei/pyzotero\n",
        "!pip install pyzotero"
      ],
      "metadata": {
        "id": "9744xJ9I7ft1"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "99s3W0fI3c-A"
      },
      "outputs": [],
      "source": [
        "import json\n",
        "import os\n",
        "import re\n",
        "\n",
        "from pyzotero import zotero"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Zotero API Setup\n",
        "\n",
        "**library_id**\n",
        "\n",
        "- Got to https://www.zotero.org/settings/keys (i.e., `Home > Settings > Feeds/API`)\n",
        "- \"Your userID for use in API calls is XXXXXXX\"\n",
        "\n",
        "**api_key**\n",
        "\n",
        "- Create a new API key here: https://www.zotero.org/settings/keys/new\n",
        "- Make sure to also tick \"Allow write access\""
      ],
      "metadata": {
        "id": "cOu-5nKS-Bu8"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "library_id = \"INSERT-YOUR-LIBRARY-ID\"\n",
        "api_key = \"INSERT-YOUR-API-KEY\"\n",
        "\n",
        "library_type = \"user\" # or \"group\"\n",
        "\n",
        "zot = zotero.Zotero(library_id, library_type, api_key)"
      ],
      "metadata": {
        "id": "FZSiMHL-6-aP"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Getting Data"
      ],
      "metadata": {
        "id": "XlhRncUP-EnU"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "## Test API\n",
        "# items = zot.top(limit=5)\n",
        "# items"
      ],
      "metadata": {
        "id": "HU66UOmx9Dnn"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "## Get all items (and save to json)\n",
        "all_items = zot.everything(zot.top())\n",
        "\n",
        "# with open(\"data/all_items.json\", \"w\") as file:\n",
        "#     json.dump(all_items, file)"
      ],
      "metadata": {
        "id": "oCcyTPIj7BoQ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "## Reload data if need be\n",
        "# with open(\"../data/all_items.json\", \"r\") as file:\n",
        "#    all_items = json.load(file)"
      ],
      "metadata": {
        "id": "Tz9MAiBz9LO5"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "len(all_items)"
      ],
      "metadata": {
        "id": "QlTQGK8t8LfH"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Find and remove '_eprint'"
      ],
      "metadata": {
        "id": "Sfr-DVu29vbE"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "## Find all items with \"_eprint\" in extra field\n",
        "eprint_elements = [\n",
        "    item for item in all_items if \"_eprint:\" in item.get(\"data\", {}).get(\"extra\", \"\")\n",
        "]\n",
        "len(eprint_elements)"
      ],
      "metadata": {
        "id": "qiGaHOtB7F1S"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "## Remove _eprint data\n",
        "pattern = r\"_eprint:[^\\n]*\\n\"\n",
        "\n",
        "for item in eprint_elements:\n",
        "    item['data']['extra'] = re.sub(pattern, \"\", item['data']['extra'])"
      ],
      "metadata": {
        "id": "f2gadiz89spv"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Update library with API"
      ],
      "metadata": {
        "id": "sw8q8iIR93tQ"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "## First only try updating one itme\n",
        "# CAUTION: uncomment to avoid accidental API write runs\n",
        "# single_item = eprint_elements[0]\n",
        "# single_item[\"data\"][\"extra\"]\n",
        "# single_item[\"key\"] # search in Zotero\n",
        "\n",
        "# zot.update_item(single_item)"
      ],
      "metadata": {
        "id": "u8ZXm6KE7O8H"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# zot.update_items(eprint_elements)"
      ],
      "metadata": {
        "id": "M1ssbB89-Qq7"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}