{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyNDvdp8livTF70SepgodBUC",
      "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/github/yubraaj11/sentence_transformer_nepali/blob/master/Dataset_Creation.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nDSUHVi0rODZ",
        "outputId": "96d8537a-fadd-40cb-cad7-3c8ed194f9eb"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Collecting bs4\n",
            "  Downloading bs4-0.0.1.tar.gz (1.1 kB)\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.10/dist-packages (from bs4) (4.11.2)\n",
            "Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.10/dist-packages (from beautifulsoup4->bs4) (2.4.1)\n",
            "Building wheels for collected packages: bs4\n",
            "  Building wheel for bs4 (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for bs4: filename=bs4-0.0.1-py3-none-any.whl size=1257 sha256=5ead9167bf44bebf34f52f8d9953fe37399437d848f5f4943d4acc8f6aa8d708\n",
            "  Stored in directory: /root/.cache/pip/wheels/25/42/45/b773edc52acb16cd2db4cf1a0b47117e2f69bb4eb300ed0e70\n",
            "Successfully built bs4\n",
            "Installing collected packages: bs4\n",
            "Successfully installed bs4-0.0.1\n"
          ]
        }
      ],
      "source": [
        "!pip install bs4"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import requests\n",
        "from bs4 import BeautifulSoup"
      ],
      "metadata": {
        "id": "Holjaclxrhcs"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# news = []\n",
        "\n",
        "# # for i in range(1, 5):\n",
        "# url = \"https://www.onlinekhabar.com/content/news/page/2\"\n",
        "\n",
        "# response = requests.get(url)\n",
        "# response = response.content\n",
        "# soup = BeautifulSoup(response, 'html.parser')\n",
        "# for titles in soup.findAll('h2'):\n",
        "#     title = titles.text\n",
        "#     print(title)\n",
        "#     # titles = grid.find('div', class_='ok-news-post')\n",
        "#     # for title in titles:\n",
        "#     #     title = soup.find('h2')\n",
        "#     #     title = title.text.strip()\n",
        "#     #     title = title.replace(u'\\xa0', u' ')\n",
        "\n",
        "#     #     print(title)\n",
        "\n",
        "#     # link = h4.find('a', href=True)\n",
        "#     # link = link.get('href')\n",
        "#     # # print(link)\n",
        "#     # link_response = requests.get(link)\n",
        "#     # link_response = link_response.content\n",
        "#     # link_soup = BeautifulSoup(link_response, 'html.parser')\n",
        "\n",
        "#     # article = link_soup.find('div', class_='ok18-single-post-content-wrap').text\n",
        "#     # article = article.replace(u'\\xa0', u' ')\n",
        "#     # article = article.replace(u'\\n', u' ')\n",
        "\n",
        "#     # # print('article:{}'.format(article))\n",
        "\n",
        "#     # # h4 = h4.strip()\n",
        "#     # # title\n",
        "#     # news.append([link, title, article])\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3kfVMU_Frstp",
        "outputId": "bd612f0a-bc0f-4435-893d-62e49b86ae04"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "ट्रेन्डिङ +\n",
            "\n",
            "\n",
            "ताजा अपडेट +\n",
            "\n",
            "काँक्राका फाइदै-फाइदा, कुन समयमा खानु राम्रो ?\n",
            "थाइराइडका बिरामीले के खाने, के नखाने ?\n",
            "बच्चामा अन्धोपनको जोखिम बढाउने आरओपी समस्या के हो ?\n",
            "फुङलिङमा सवारी दुर्घटनामा परी एक बालककाे मृत्यु\n",
            "जोर्डनका युवराज र साउदी युवतीबीचको विवाह किन छ चर्चामा ?\n",
            "स्मार्टफोनमा स्टोरेज सकिन थाल्यो ? यसो गर्नुस्\n",
            "‘शून्यकाे मूल्य’लाई उत्तम-शान्ति पुरस्कार\n",
            "‘स्टन्टबाजी जान्दिनँ, काम भइरहेको छ’\n",
            "रातो मच्छिन्द्रनाथको रथ तान्न उर्लिएको भीड (तस्वीरहरू)\n",
            "\n",
            "समाचार \n",
            "प्रचण्ड दिल्लीबाट फर्केपछि बेइजिङ भ्रमणको तयारी हुने\n",
            "वीरेन्द्रनगरकी मेयर : हुटहुटी छ, तर परिणाम देखिएन\n",
            "कक्षा १२ को ऐच्छिक नेपालीबाट भुपाल राईको कविता हटाउन दबाव\n",
            "रुकुम पश्चिममा भएको जिप दुर्घटनामा आमाछोरासहित ५ जनाको मृत्यु\n",
            "भोटो जात्राले चिडियाखानामा एकै दिन १२ हजार अवलोकनकर्ता, शुल्क आधाभन्दा कम\n",
            "नक्कली शरणार्थी मुद्दामा नेपाल राज्यकै परीक्षा\n",
            "थाइराइडका बिरामीले के खाने, के नखाने ?\n",
            "बागमतीका ३ हजार पुराना सार्वजनिक सवारी सडकबाट हट्दै\n",
            "कर्णालीमा बजेटको प्राथमिकता र सिद्धान्त : हरेक वर्ष १० हजार रोजगारी सिर्जना (पूर्णपाठ)\n",
            "वैदेशिक रोजगार मागपत्रको प्रमाणीकरण अब देशभित्रै गर्ने व्यवस्था हुँदै\n",
            "बच्चामा अन्धोपनको जोखिम बढाउने आरओपी समस्या के हो ?\n",
            "रास्वपा नेताहरु र चिनियाँ दूतावासको टोलीबीच भेटवार्ता\n",
            "गणतन्त्रको विकल्प पश्चगमन हुन सक्‍दैन : सञ्‍चारमन्त्री शर्मा\n",
            "पश्चिमी वायुको प्रभावले उपत्यकासहित देशभर वर्षा\n",
            "‘हाम्रो व्यक्तित्वमा आँच पुर्‍याइयो’\n",
            "ट्याटु पूरै हटाउन सकिन्छ ?\n",
            "कोशीमा आन्दोलनरत पहिचान पक्षधरलाई वार्तामा बोलाउन कांग्रेसको माग \n",
            "मधेश सरकारमा लोसपा पनि सहभागी, कुर्मी वनमन्त्री नियुक्त\n",
            "तम्घास बजारको सडकमा पुनः कालोपत्रे काम सुरु\n",
            "कोशीमा पहिचान पक्षधरले गरे विराटनगर केन्द्रित आन्दोलन घोषणा\n",
            "प्रहरी कुनै षड्यन्त्रको शिकार भएको छैन : गृहमन्त्री श्रेष्ठ\n",
            "ढोरपाटनका मेयरलाई एमालेले गर्‍यो प्रदेश कमिटीबाट निलम्बन\n",
            "नक्कली भुटानी शरणार्थी प्रकरणमा निष्पक्ष अनुसन्धान गर्न युवा संघको माग\n",
            "कोशी प्रदेशमा ९७ प्रतिशत घरपरिवारमा शौचालय\n",
            "पानीका स्रोत सरसफाइ गरिने पर्व सिथि नखः\n",
            "स्थानीय तहमा खटाइएका पर्यवेक्षकले एक वर्षदेखि पाएनन् पारिश्रमिक\n",
            "दाङमा वृद्धालाई कुटपिट गरी लुटपाट\n",
            "बालबच्चालाई किन धेरै रिस उठ्छ ?\n",
            "‘ई-हाजिरी’ कि ‘नो हाजिरी’ !\n",
            "जेठ १७ गते भारत भ्रमणमा जाने प्रधानमन्त्रीको तयारी\n",
            "Posts navigation\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "\n",
        "df = pd.DataFrame(news, columns=['link','title','article'])\n",
        "df"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 49
        },
        "id": "Hqx6ziKkr8C1",
        "outputId": "75b24fc5-7e67-47f2-cb10-f43d31dc05d8"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Empty DataFrame\n",
              "Columns: [link, title, article]\n",
              "Index: []"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-0ca380f9-b4fc-41ad-beb3-4444fd3ef746\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>link</th>\n",
              "      <th>title</th>\n",
              "      <th>article</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-0ca380f9-b4fc-41ad-beb3-4444fd3ef746')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-0ca380f9-b4fc-41ad-beb3-4444fd3ef746 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-0ca380f9-b4fc-41ad-beb3-4444fd3ef746');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "links = []\n",
        "for i in range(1,151):\n",
        "    url = f\"https://www.onlinekhabar.com/content/news/page/{i}\"\n",
        "    \n",
        "    homepage = requests.get(url)\n",
        "    contents = BeautifulSoup(homepage.content, 'html.parser')\n",
        "    for news in contents.findAll('div', class_='ok-news-post'):\n",
        "        links.append(news.a['href'])\n",
        "links[:5]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4g3fnsRWsIHx",
        "outputId": "b414b129-ac15-4bcf-a3c8-99113b4d1d81"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['https://www.onlinekhabar.com/2023/05/1312396',\n",
              " 'https://www.onlinekhabar.com/2023/05/1312323',\n",
              " 'https://www.onlinekhabar.com/2023/05/1312266',\n",
              " 'https://www.onlinekhabar.com/2023/05/1312637',\n",
              " 'https://www.onlinekhabar.com/2023/05/1312564']"
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from tqdm import tqdm"
      ],
      "metadata": {
        "id": "TkUuVlJu-MB6"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "news = []\n",
        "\n",
        "\n",
        "for link in tqdm(links):\n",
        "    page = requests.get(link)\n",
        "    contents = BeautifulSoup(page.content, 'html.parser')\n",
        "    for titles in contents.findAll('h1'):\n",
        "        title = titles.text\n",
        "        title = title.replace(u'\\xa0', u' ')\n",
        "        title = title.replace(u'\\n', u' ')\n",
        "\n",
        "    for articles in contents.findAll('div', class_='ok18-single-post-content-wrap'):\n",
        "        article = articles.text\n",
        "        article = article.replace(u'\\xa0', u' ')\n",
        "        article = article.replace(u'\\n', u' ')\n",
        "\n",
        "    news.append([link, title, article])\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pimKpq9f6FEy",
        "outputId": "5449c686-f2a2-4457-ec2a-9e799bf5c191"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "100%|██████████| 6000/6000 [45:37<00:00,  2.19it/s]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "news = pd.DataFrame(news, columns = ['link', 'title', 'article'])\n",
        "news"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 423
        },
        "id": "wP4DTThB7zcl",
        "outputId": "6c093431-ab88-4466-d4c0-940725cefe82"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                              link  \\\n",
              "0     https://www.onlinekhabar.com/2023/05/1312396   \n",
              "1     https://www.onlinekhabar.com/2023/05/1312323   \n",
              "2     https://www.onlinekhabar.com/2023/05/1312266   \n",
              "3     https://www.onlinekhabar.com/2023/05/1312637   \n",
              "4     https://www.onlinekhabar.com/2023/05/1312564   \n",
              "...                                            ...   \n",
              "5995  https://www.onlinekhabar.com/2023/02/1269914   \n",
              "5996  https://www.onlinekhabar.com/2023/02/1269908   \n",
              "5997  https://www.onlinekhabar.com/2023/02/1269895   \n",
              "5998  https://www.onlinekhabar.com/2023/02/1269881   \n",
              "5999  https://www.onlinekhabar.com/2023/02/1269863   \n",
              "\n",
              "                                                  title  \\\n",
              "0        काँक्राका फाइदै-फाइदा, कुन समयमा खानु राम्रो ?   \n",
              "1                थाइराइडका बिरामीले के खाने, के नखाने ?   \n",
              "2     बच्चामा अन्धोपनको जोखिम बढाउने आरओपी समस्या के...   \n",
              "3       फुङलिङमा सवारी दुर्घटनामा परी एक बालककाे मृत्यु   \n",
              "4     जोर्डनका युवराज र साउदी युवतीबीचको विवाह किन छ...   \n",
              "...                                                 ...   \n",
              "5995  ज्येष्ठ सदस्य जबरासहित ११ सांसदले बुझाएनन् सम्...   \n",
              "5996  गुल्मीमा बिभिन्न कार्यक्रम गरेर ४१ औं मगर दिवस...   \n",
              "5997             कास्कीमा ६ महिनामै बलात्कारका ३५ उजुरी   \n",
              "5998  प्रज्ञा प्रतिष्ठानका सदस्यले दोहोरो सुविधा नपाउने   \n",
              "5999  सिसडोलमा  फोहोर फाल्ने स्वास्थ्य संस्थालाई महा...   \n",
              "\n",
              "                                                article  \n",
              "0      चर्को गर्मीमा काँक्रा खानुको मज्जा नै बेग्लै ...  \n",
              "1      काठमाडौं । शरीरलाई राम्रोसँग काम गर्न विभिन्न...  \n",
              "2      सामान्य बच्चाको तुलनामा समयअगावै जन्मिएका बच्...  \n",
              "3      १२ जेठ, ताप्लेजुङ। स्कार्पियाे दुर्घटनामा बिह...  \n",
              "4      १२ जेठ, काठमाडौं । जोर्डनका युवराज हुसेन बिन ...  \n",
              "...                                                 ...  \n",
              "5995   १५ फागुन, काठमाडौं । प्रतिनिधिसभाका ११ सदस्यल...  \n",
              "5996   १५ फागुन, गुल्मी । गुल्मी जिल्ला सदरमुकाम तम्...  \n",
              "5997   १५ फागुन, पोखरा । पोखराको लेकसाइड, शान्तिनगरब...  \n",
              "5998   १५ फागुन, काठमाडौं । नेपाल प्रज्ञा प्रतिष्ठान...  \n",
              "5999   १५ फागुन, काठमाडौं । काठमाडौं महानगरपालिकाले ...  \n",
              "\n",
              "[6000 rows x 3 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-0460700e-c8b7-42fe-8d5a-3fa8b968af1a\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>link</th>\n",
              "      <th>title</th>\n",
              "      <th>article</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1312396</td>\n",
              "      <td>काँक्राका फाइदै-फाइदा, कुन समयमा खानु राम्रो ?</td>\n",
              "      <td>चर्को गर्मीमा काँक्रा खानुको मज्जा नै बेग्लै ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1312323</td>\n",
              "      <td>थाइराइडका बिरामीले के खाने, के नखाने ?</td>\n",
              "      <td>काठमाडौं । शरीरलाई राम्रोसँग काम गर्न विभिन्न...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1312266</td>\n",
              "      <td>बच्चामा अन्धोपनको जोखिम बढाउने आरओपी समस्या के...</td>\n",
              "      <td>सामान्य बच्चाको तुलनामा समयअगावै जन्मिएका बच्...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1312637</td>\n",
              "      <td>फुङलिङमा सवारी दुर्घटनामा परी एक बालककाे मृत्यु</td>\n",
              "      <td>१२ जेठ, ताप्लेजुङ। स्कार्पियाे दुर्घटनामा बिह...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1312564</td>\n",
              "      <td>जोर्डनका युवराज र साउदी युवतीबीचको विवाह किन छ...</td>\n",
              "      <td>१२ जेठ, काठमाडौं । जोर्डनका युवराज हुसेन बिन ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5995</th>\n",
              "      <td>https://www.onlinekhabar.com/2023/02/1269914</td>\n",
              "      <td>ज्येष्ठ सदस्य जबरासहित ११ सांसदले बुझाएनन् सम्...</td>\n",
              "      <td>१५ फागुन, काठमाडौं । प्रतिनिधिसभाका ११ सदस्यल...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5996</th>\n",
              "      <td>https://www.onlinekhabar.com/2023/02/1269908</td>\n",
              "      <td>गुल्मीमा बिभिन्न कार्यक्रम गरेर ४१ औं मगर दिवस...</td>\n",
              "      <td>१५ फागुन, गुल्मी । गुल्मी जिल्ला सदरमुकाम तम्...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5997</th>\n",
              "      <td>https://www.onlinekhabar.com/2023/02/1269895</td>\n",
              "      <td>कास्कीमा ६ महिनामै बलात्कारका ३५ उजुरी</td>\n",
              "      <td>१५ फागुन, पोखरा । पोखराको लेकसाइड, शान्तिनगरब...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5998</th>\n",
              "      <td>https://www.onlinekhabar.com/2023/02/1269881</td>\n",
              "      <td>प्रज्ञा प्रतिष्ठानका सदस्यले दोहोरो सुविधा नपाउने</td>\n",
              "      <td>१५ फागुन, काठमाडौं । नेपाल प्रज्ञा प्रतिष्ठान...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5999</th>\n",
              "      <td>https://www.onlinekhabar.com/2023/02/1269863</td>\n",
              "      <td>सिसडोलमा  फोहोर फाल्ने स्वास्थ्य संस्थालाई महा...</td>\n",
              "      <td>१५ फागुन, काठमाडौं । काठमाडौं महानगरपालिकाले ...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>6000 rows × 3 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-0460700e-c8b7-42fe-8d5a-3fa8b968af1a')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-0460700e-c8b7-42fe-8d5a-3fa8b968af1a button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-0460700e-c8b7-42fe-8d5a-3fa8b968af1a');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "news.drop_duplicates(subset=['title'], inplace=True)"
      ],
      "metadata": {
        "id": "JwlXY7Q1SU7D"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "news.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "22-gZ_sCSoav",
        "outputId": "39b5280d-61e5-4492-9f47-e8a2638c4d07"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(3857, 3)"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "news = news[['title', 'article','link']]\n",
        "news.insert(0, 'id', range(0, news.shape[0]))"
      ],
      "metadata": {
        "id": "kcKuRpDY-p-3"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "news.head(100)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 423
        },
        "id": "iI_-uQezSmKU",
        "outputId": "d05ab919-2ff8-4738-e706-030863915a40"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "     id                                              title  \\\n",
              "0     0     काँक्राका फाइदै-फाइदा, कुन समयमा खानु राम्रो ?   \n",
              "1     1             थाइराइडका बिरामीले के खाने, के नखाने ?   \n",
              "2     2  बच्चामा अन्धोपनको जोखिम बढाउने आरओपी समस्या के...   \n",
              "3     3    फुङलिङमा सवारी दुर्घटनामा परी एक बालककाे मृत्यु   \n",
              "4     4  जोर्डनका युवराज र साउदी युवतीबीचको विवाह किन छ...   \n",
              "..   ..                                                ...   \n",
              "117  95             भोलि काठमाडौं उपत्यकामा सार्वजनिक बिदा   \n",
              "118  96  ग्यास र बिजुली प्रयोगको शिक्षा विद्यालयकै पाठ्...   \n",
              "119  97  गौतमबुद्ध विमानस्थलबाट लक्ष्यको १० प्रतिशत मात...   \n",
              "129  98  ज्ञानेन्द्र शाहीको प्रश्न : आईजीपीलाई निलम्बन ...   \n",
              "130  99   कसरी गर्ने एन्जाइटी नियन्त्रण ? यस्ता छन् ८ उपाय   \n",
              "\n",
              "                                               article  \\\n",
              "0     चर्को गर्मीमा काँक्रा खानुको मज्जा नै बेग्लै ...   \n",
              "1     काठमाडौं । शरीरलाई राम्रोसँग काम गर्न विभिन्न...   \n",
              "2     सामान्य बच्चाको तुलनामा समयअगावै जन्मिएका बच्...   \n",
              "3     १२ जेठ, ताप्लेजुङ। स्कार्पियाे दुर्घटनामा बिह...   \n",
              "4     १२ जेठ, काठमाडौं । जोर्डनका युवराज हुसेन बिन ...   \n",
              "..                                                 ...   \n",
              "117   १० जेठ, काठमाडौं । भोटो देखाउने जात्राको अवसर...   \n",
              "118   १० जेठ, काठमाडौं । नेपाली कांग्रेसका सांसद चन...   \n",
              "119   १० जेठ, काठमाडौं । नेपालको दोस्रो अन्तर्राष्ट...   \n",
              "129   १० जेठ, काठमाडौं। राष्ट्रिय प्रजातन्त्र पार्ट...   \n",
              "130   हरेक व्यक्तिमा कुनै न कुनै तनाव त भइरहन्छ । त...   \n",
              "\n",
              "                                             link  \n",
              "0    https://www.onlinekhabar.com/2023/05/1312396  \n",
              "1    https://www.onlinekhabar.com/2023/05/1312323  \n",
              "2    https://www.onlinekhabar.com/2023/05/1312266  \n",
              "3    https://www.onlinekhabar.com/2023/05/1312637  \n",
              "4    https://www.onlinekhabar.com/2023/05/1312564  \n",
              "..                                            ...  \n",
              "117  https://www.onlinekhabar.com/2023/05/1311800  \n",
              "118  https://www.onlinekhabar.com/2023/05/1311778  \n",
              "119  https://www.onlinekhabar.com/2023/05/1311777  \n",
              "129  https://www.onlinekhabar.com/2023/05/1311764  \n",
              "130  https://www.onlinekhabar.com/2023/05/1311635  \n",
              "\n",
              "[100 rows x 4 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-532d9daf-ec50-4e0d-b3f3-a4e0062f2339\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>id</th>\n",
              "      <th>title</th>\n",
              "      <th>article</th>\n",
              "      <th>link</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0</td>\n",
              "      <td>काँक्राका फाइदै-फाइदा, कुन समयमा खानु राम्रो ?</td>\n",
              "      <td>चर्को गर्मीमा काँक्रा खानुको मज्जा नै बेग्लै ...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1312396</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>थाइराइडका बिरामीले के खाने, के नखाने ?</td>\n",
              "      <td>काठमाडौं । शरीरलाई राम्रोसँग काम गर्न विभिन्न...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1312323</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2</td>\n",
              "      <td>बच्चामा अन्धोपनको जोखिम बढाउने आरओपी समस्या के...</td>\n",
              "      <td>सामान्य बच्चाको तुलनामा समयअगावै जन्मिएका बच्...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1312266</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>3</td>\n",
              "      <td>फुङलिङमा सवारी दुर्घटनामा परी एक बालककाे मृत्यु</td>\n",
              "      <td>१२ जेठ, ताप्लेजुङ। स्कार्पियाे दुर्घटनामा बिह...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1312637</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>4</td>\n",
              "      <td>जोर्डनका युवराज र साउदी युवतीबीचको विवाह किन छ...</td>\n",
              "      <td>१२ जेठ, काठमाडौं । जोर्डनका युवराज हुसेन बिन ...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1312564</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>117</th>\n",
              "      <td>95</td>\n",
              "      <td>भोलि काठमाडौं उपत्यकामा सार्वजनिक बिदा</td>\n",
              "      <td>१० जेठ, काठमाडौं । भोटो देखाउने जात्राको अवसर...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1311800</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>118</th>\n",
              "      <td>96</td>\n",
              "      <td>ग्यास र बिजुली प्रयोगको शिक्षा विद्यालयकै पाठ्...</td>\n",
              "      <td>१० जेठ, काठमाडौं । नेपाली कांग्रेसका सांसद चन...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1311778</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>119</th>\n",
              "      <td>97</td>\n",
              "      <td>गौतमबुद्ध विमानस्थलबाट लक्ष्यको १० प्रतिशत मात...</td>\n",
              "      <td>१० जेठ, काठमाडौं । नेपालको दोस्रो अन्तर्राष्ट...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1311777</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>129</th>\n",
              "      <td>98</td>\n",
              "      <td>ज्ञानेन्द्र शाहीको प्रश्न : आईजीपीलाई निलम्बन ...</td>\n",
              "      <td>१० जेठ, काठमाडौं। राष्ट्रिय प्रजातन्त्र पार्ट...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1311764</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>130</th>\n",
              "      <td>99</td>\n",
              "      <td>कसरी गर्ने एन्जाइटी नियन्त्रण ? यस्ता छन् ८ उपाय</td>\n",
              "      <td>हरेक व्यक्तिमा कुनै न कुनै तनाव त भइरहन्छ । त...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1311635</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>100 rows × 4 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-532d9daf-ec50-4e0d-b3f3-a4e0062f2339')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-532d9daf-ec50-4e0d-b3f3-a4e0062f2339 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-532d9daf-ec50-4e0d-b3f3-a4e0062f2339');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "news.reset_index(drop=True, inplace=True)"
      ],
      "metadata": {
        "id": "LirfvTPeSnsC"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "news.head(100)"
      ],
      "metadata": {
        "id": "gOZ_BTM6SwqI",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 423
        },
        "outputId": "452bf62c-9753-4f76-c521-1e09d9205170"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "    id                                              title  \\\n",
              "0    0     काँक्राका फाइदै-फाइदा, कुन समयमा खानु राम्रो ?   \n",
              "1    1             थाइराइडका बिरामीले के खाने, के नखाने ?   \n",
              "2    2  बच्चामा अन्धोपनको जोखिम बढाउने आरओपी समस्या के...   \n",
              "3    3    फुङलिङमा सवारी दुर्घटनामा परी एक बालककाे मृत्यु   \n",
              "4    4  जोर्डनका युवराज र साउदी युवतीबीचको विवाह किन छ...   \n",
              "..  ..                                                ...   \n",
              "95  95             भोलि काठमाडौं उपत्यकामा सार्वजनिक बिदा   \n",
              "96  96  ग्यास र बिजुली प्रयोगको शिक्षा विद्यालयकै पाठ्...   \n",
              "97  97  गौतमबुद्ध विमानस्थलबाट लक्ष्यको १० प्रतिशत मात...   \n",
              "98  98  ज्ञानेन्द्र शाहीको प्रश्न : आईजीपीलाई निलम्बन ...   \n",
              "99  99   कसरी गर्ने एन्जाइटी नियन्त्रण ? यस्ता छन् ८ उपाय   \n",
              "\n",
              "                                              article  \\\n",
              "0    चर्को गर्मीमा काँक्रा खानुको मज्जा नै बेग्लै ...   \n",
              "1    काठमाडौं । शरीरलाई राम्रोसँग काम गर्न विभिन्न...   \n",
              "2    सामान्य बच्चाको तुलनामा समयअगावै जन्मिएका बच्...   \n",
              "3    १२ जेठ, ताप्लेजुङ। स्कार्पियाे दुर्घटनामा बिह...   \n",
              "4    १२ जेठ, काठमाडौं । जोर्डनका युवराज हुसेन बिन ...   \n",
              "..                                                ...   \n",
              "95   १० जेठ, काठमाडौं । भोटो देखाउने जात्राको अवसर...   \n",
              "96   १० जेठ, काठमाडौं । नेपाली कांग्रेसका सांसद चन...   \n",
              "97   १० जेठ, काठमाडौं । नेपालको दोस्रो अन्तर्राष्ट...   \n",
              "98   १० जेठ, काठमाडौं। राष्ट्रिय प्रजातन्त्र पार्ट...   \n",
              "99   हरेक व्यक्तिमा कुनै न कुनै तनाव त भइरहन्छ । त...   \n",
              "\n",
              "                                            link  \n",
              "0   https://www.onlinekhabar.com/2023/05/1312396  \n",
              "1   https://www.onlinekhabar.com/2023/05/1312323  \n",
              "2   https://www.onlinekhabar.com/2023/05/1312266  \n",
              "3   https://www.onlinekhabar.com/2023/05/1312637  \n",
              "4   https://www.onlinekhabar.com/2023/05/1312564  \n",
              "..                                           ...  \n",
              "95  https://www.onlinekhabar.com/2023/05/1311800  \n",
              "96  https://www.onlinekhabar.com/2023/05/1311778  \n",
              "97  https://www.onlinekhabar.com/2023/05/1311777  \n",
              "98  https://www.onlinekhabar.com/2023/05/1311764  \n",
              "99  https://www.onlinekhabar.com/2023/05/1311635  \n",
              "\n",
              "[100 rows x 4 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-60b8eade-dd25-4293-ae48-4a6b9c292bf0\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <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>id</th>\n",
              "      <th>title</th>\n",
              "      <th>article</th>\n",
              "      <th>link</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0</td>\n",
              "      <td>काँक्राका फाइदै-फाइदा, कुन समयमा खानु राम्रो ?</td>\n",
              "      <td>चर्को गर्मीमा काँक्रा खानुको मज्जा नै बेग्लै ...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1312396</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>थाइराइडका बिरामीले के खाने, के नखाने ?</td>\n",
              "      <td>काठमाडौं । शरीरलाई राम्रोसँग काम गर्न विभिन्न...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1312323</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2</td>\n",
              "      <td>बच्चामा अन्धोपनको जोखिम बढाउने आरओपी समस्या के...</td>\n",
              "      <td>सामान्य बच्चाको तुलनामा समयअगावै जन्मिएका बच्...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1312266</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>3</td>\n",
              "      <td>फुङलिङमा सवारी दुर्घटनामा परी एक बालककाे मृत्यु</td>\n",
              "      <td>१२ जेठ, ताप्लेजुङ। स्कार्पियाे दुर्घटनामा बिह...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1312637</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>4</td>\n",
              "      <td>जोर्डनका युवराज र साउदी युवतीबीचको विवाह किन छ...</td>\n",
              "      <td>१२ जेठ, काठमाडौं । जोर्डनका युवराज हुसेन बिन ...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1312564</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>95</th>\n",
              "      <td>95</td>\n",
              "      <td>भोलि काठमाडौं उपत्यकामा सार्वजनिक बिदा</td>\n",
              "      <td>१० जेठ, काठमाडौं । भोटो देखाउने जात्राको अवसर...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1311800</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>96</th>\n",
              "      <td>96</td>\n",
              "      <td>ग्यास र बिजुली प्रयोगको शिक्षा विद्यालयकै पाठ्...</td>\n",
              "      <td>१० जेठ, काठमाडौं । नेपाली कांग्रेसका सांसद चन...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1311778</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97</th>\n",
              "      <td>97</td>\n",
              "      <td>गौतमबुद्ध विमानस्थलबाट लक्ष्यको १० प्रतिशत मात...</td>\n",
              "      <td>१० जेठ, काठमाडौं । नेपालको दोस्रो अन्तर्राष्ट...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1311777</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>98</th>\n",
              "      <td>98</td>\n",
              "      <td>ज्ञानेन्द्र शाहीको प्रश्न : आईजीपीलाई निलम्बन ...</td>\n",
              "      <td>१० जेठ, काठमाडौं। राष्ट्रिय प्रजातन्त्र पार्ट...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1311764</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>99</th>\n",
              "      <td>99</td>\n",
              "      <td>कसरी गर्ने एन्जाइटी नियन्त्रण ? यस्ता छन् ८ उपाय</td>\n",
              "      <td>हरेक व्यक्तिमा कुनै न कुनै तनाव त भइरहन्छ । त...</td>\n",
              "      <td>https://www.onlinekhabar.com/2023/05/1311635</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>100 rows × 4 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-60b8eade-dd25-4293-ae48-4a6b9c292bf0')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-60b8eade-dd25-4293-ae48-4a6b9c292bf0 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-60b8eade-dd25-4293-ae48-4a6b9c292bf0');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "news.to_csv('3k_News.csv')"
      ],
      "metadata": {
        "id": "FCi6DotDS2zU"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "eCc5kMy3S7d3"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}