From 30316f0f7b69dfc17443da32fe8b7fb835f10dc3 Mon Sep 17 00:00:00 2001
From: imukoki <60528574+imukoki@users.noreply.github.com>
Date: Thu, 17 Nov 2022 19:05:17 +0200
Subject: [PATCH 1/9] Created using Colaboratory

---
 Webscraping2.ipynb | 759 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 759 insertions(+)
 create mode 100644 Webscraping2.ipynb

diff --git a/Webscraping2.ipynb b/Webscraping2.ipynb
new file mode 100644
index 0000000..e56a62e
--- /dev/null
+++ b/Webscraping2.ipynb
@@ -0,0 +1,759 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "authorship_tag": "ABX9TyOFMmAMVvajwCa+6KvYpGo9",
+      "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/imukoki/NLP-FELLOWSHIP/blob/Week-5/Webscraping2.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 62,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "L1KWrQ6slzA2",
+        "outputId": "3303657e-ca69-4e52-d309-a2fea730edc2"
+      },
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "<div class=\"card-body p-2\">\n",
+              "<a href=\"/job/organizational-development-and-accountability-advisor\"><h5 class=\"card-title\"><span class=\"field field--name-title field--type-string field--label-hidden\">​​​​​​​Organizational Development and Accountability Advisor</span>\n",
+              "</h5></a>\n",
+              "<p class=\"card-text\">\n",
+              "<a href=\"/employer/trocaire\">Trócaire</a>  |\n",
+              "              Published on 17-11-2022 |\n",
+              "              Deadline <time class=\"datetime\" datetime=\"2022-11-30T15:00:00Z\">30-11-2022</time>\n",
+              "<br/>\n",
+              "                              Senior (5+ years of experience)<br/>\n",
+              "<span class=\"badge badge-primary\">Job</span>\n",
+              "</p>\n",
+              "</div>"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 62
+        }
+      ],
+      "source": [
+        "import requests\n",
+        "from bs4 import BeautifulSoup\n",
+        "link = 'https://www.jobinrwanda.com'\n",
+        "content = requests.get(link).content\n",
+        "raw_content = BeautifulSoup(content, 'html.parser').find_all('div', class_='card-body p-2')\n",
+        "raw_content[0]"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "raw_content[0].find('a')['href']"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 36
+        },
+        "id": "yV0112WCqg8B",
+        "outputId": "8e4b1426-75aa-4756-f0ee-8b58edf5ba28"
+      },
+      "execution_count": 63,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "'/job/organizational-development-and-accountability-advisor'"
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "string"
+            }
+          },
+          "metadata": {},
+          "execution_count": 63
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "raw_content[0].find('span').getText() # Title of each job alert\n",
+        "raw_content[0].find('a')['href'] # Link to the content of each job title\n",
+        "raw_content[0].find('p').find('a')['href'] # Link to the institution that has posted the advert\n",
+        "raw_content[0].find('p').find('a').getText() # This is the name of the company\n",
+        "raw_content[0].find('p').find('span').getText() # Type of advert"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 36
+        },
+        "id": "_1IwLEoQq4h3",
+        "outputId": "12407498-c823-4573-9f45-8870a352e8d8"
+      },
+      "execution_count": 64,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "'Job'"
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "string"
+            }
+          },
+          "metadata": {},
+          "execution_count": 64
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import pandas as pd\n",
+        "df = pd.DataFrame(columns=['link','title','company_link','company','job_type'])\n",
+        "\n",
+        "def parse_content(adverts):\n",
+        "  link = []\n",
+        "  title = []\n",
+        "  company = []\n",
+        "  company_link = []\n",
+        "  job_type = []\n",
+        "  for advert in adverts:\n",
+        "    link.append('https://www.jobinrwanda.com' + advert.find('a')['href'])\n",
+        "    title.append(advert.find('span').getText())\n",
+        "    company.append(advert.find('p').find('a').getText())\n",
+        "    company_link.append(advert.find('p').find('a')['href'])\n",
+        "    job_type.append(advert.find('p').find('span').getText())\n",
+        "  return link, title, company, company_link, job_type"
+      ],
+      "metadata": {
+        "id": "fHrMvcfUun8Q"
+      },
+      "execution_count": 65,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "link = 'https://www.jobinrwanda.com'\n",
+        "content = requests.get(link).content\n",
+        "raw_content = BeautifulSoup(content, 'html.parser').find_all('div', class_='card-body p-2')\n",
+        "df['link'], df['title'], df['company'], df['company_link'], df['job_type'] = parse_content(raw_content)\n",
+        "df"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 424
+        },
+        "id": "5vePYScS2ctx",
+        "outputId": "a0cc239f-599c-40d0-ce39-6ccc020d1480"
+      },
+      "execution_count": 66,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "                                                  link  \\\n",
+              "0    https://www.jobinrwanda.com/job/organizational...   \n",
+              "1    https://www.jobinrwanda.com/job/monitoring-inc...   \n",
+              "2    https://www.jobinrwanda.com/job/resource-mobil...   \n",
+              "3    https://www.jobinrwanda.com/job/request-propos...   \n",
+              "4    https://www.jobinrwanda.com/job/finance-manage...   \n",
+              "..                                                 ...   \n",
+              "187   https://www.jobinrwanda.com/job/rwanda-tree-lead   \n",
+              "188  https://www.jobinrwanda.com/index.php/job/rwan...   \n",
+              "189  https://www.jobinrwanda.com/job/it-operations-...   \n",
+              "190  https://www.jobinrwanda.com/job/rwanda-seed-in...   \n",
+              "191  https://www.jobinrwanda.com/job/senior-busines...   \n",
+              "\n",
+              "                                                 title  \\\n",
+              "0    ​​​​​​​Organizational Development and Accounta...   \n",
+              "1           Monitoring, Inclusion and Learning Advisor   \n",
+              "2              Resource Mobilization and Grant Manager   \n",
+              "3    Request for Proposals for Electronic Logistics...   \n",
+              "4                                      Finance Manager   \n",
+              "..                                                 ...   \n",
+              "187                                   Rwanda Tree Lead   \n",
+              "188                  Rwanda Potato Seed Venture Lead   \n",
+              "189                       IT Operations Senior Manager   \n",
+              "190                 Rwanda Seed Innovation Centre Lead   \n",
+              "191                            Senior Business Analyst   \n",
+              "\n",
+              "                              company_link                        company  \\\n",
+              "0                       /employer/trocaire                       Trócaire   \n",
+              "1                       /employer/trocaire                       Trócaire   \n",
+              "2                       /employer/trocaire                       Trócaire   \n",
+              "3    /employer/chemonics-international-inc  Chemonics International Inc.    \n",
+              "4                /employer/womens-bakery-1             The Women's Bakery   \n",
+              "..                                     ...                            ...   \n",
+              "187                /employer/one-acre-fund                  One Acre Fund   \n",
+              "188      /index.php/employer/one-acre-fund                  One Acre Fund   \n",
+              "189                /employer/one-acre-fund                  One Acre Fund   \n",
+              "190                /employer/one-acre-fund                  One Acre Fund   \n",
+              "191                /employer/one-acre-fund                  One Acre Fund   \n",
+              "\n",
+              "    job_type  \n",
+              "0        Job  \n",
+              "1        Job  \n",
+              "2        Job  \n",
+              "3     Tender  \n",
+              "4        Job  \n",
+              "..       ...  \n",
+              "187      Job  \n",
+              "188      Job  \n",
+              "189      Job  \n",
+              "190      Job  \n",
+              "191      Job  \n",
+              "\n",
+              "[192 rows x 5 columns]"
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-55d41326-6131-4965-abaf-80f737e2ef1f\">\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>company_link</th>\n",
+              "      <th>company</th>\n",
+              "      <th>job_type</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/organizational...</td>\n",
+              "      <td>​​​​​​​Organizational Development and Accounta...</td>\n",
+              "      <td>/employer/trocaire</td>\n",
+              "      <td>Trócaire</td>\n",
+              "      <td>Job</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/monitoring-inc...</td>\n",
+              "      <td>Monitoring, Inclusion and Learning Advisor</td>\n",
+              "      <td>/employer/trocaire</td>\n",
+              "      <td>Trócaire</td>\n",
+              "      <td>Job</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/resource-mobil...</td>\n",
+              "      <td>Resource Mobilization and Grant Manager</td>\n",
+              "      <td>/employer/trocaire</td>\n",
+              "      <td>Trócaire</td>\n",
+              "      <td>Job</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/request-propos...</td>\n",
+              "      <td>Request for Proposals for Electronic Logistics...</td>\n",
+              "      <td>/employer/chemonics-international-inc</td>\n",
+              "      <td>Chemonics International Inc.</td>\n",
+              "      <td>Tender</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/finance-manage...</td>\n",
+              "      <td>Finance Manager</td>\n",
+              "      <td>/employer/womens-bakery-1</td>\n",
+              "      <td>The Women's Bakery</td>\n",
+              "      <td>Job</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>...</th>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>187</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/rwanda-tree-lead</td>\n",
+              "      <td>Rwanda Tree Lead</td>\n",
+              "      <td>/employer/one-acre-fund</td>\n",
+              "      <td>One Acre Fund</td>\n",
+              "      <td>Job</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>188</th>\n",
+              "      <td>https://www.jobinrwanda.com/index.php/job/rwan...</td>\n",
+              "      <td>Rwanda Potato Seed Venture Lead</td>\n",
+              "      <td>/index.php/employer/one-acre-fund</td>\n",
+              "      <td>One Acre Fund</td>\n",
+              "      <td>Job</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>189</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/it-operations-...</td>\n",
+              "      <td>IT Operations Senior Manager</td>\n",
+              "      <td>/employer/one-acre-fund</td>\n",
+              "      <td>One Acre Fund</td>\n",
+              "      <td>Job</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>190</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/rwanda-seed-in...</td>\n",
+              "      <td>Rwanda Seed Innovation Centre Lead</td>\n",
+              "      <td>/employer/one-acre-fund</td>\n",
+              "      <td>One Acre Fund</td>\n",
+              "      <td>Job</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>191</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/senior-busines...</td>\n",
+              "      <td>Senior Business Analyst</td>\n",
+              "      <td>/employer/one-acre-fund</td>\n",
+              "      <td>One Acre Fund</td>\n",
+              "      <td>Job</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "<p>192 rows × 5 columns</p>\n",
+              "</div>\n",
+              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-55d41326-6131-4965-abaf-80f737e2ef1f')\"\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-55d41326-6131-4965-abaf-80f737e2ef1f 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-55d41326-6131-4965-abaf-80f737e2ef1f');\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": 66
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def get_description(job_link):\n",
+        "  job_description_raw_content = requests.get(job_link).content # request raw content\n",
+        "  job_description_bs = BeautifulSoup(job_description_raw_content, 'html.parser')\n",
+        "  employer_description = job_description_bs.find_all('div', class_='employer-description')[0].getText()\n",
+        "\n",
+        "  describe = job_description_bs.find_all('div', class_='clearfix text-formatted field field--name-field-job-full-description field--type-text-long field--label-hidden field__item')\n",
+        "  return employer_description\n"
+      ],
+      "metadata": {
+        "id": "YDXK8fZX7ohf"
+      },
+      "execution_count": 67,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Adding description\n",
+        "descr = []\n",
+        "for index in range(len(df)):\n",
+        "  try:\n",
+        "    descr.append(get_description(df['link'][index]))\n",
+        "  except IndexError:\n",
+        "    descr.append('NA')\n",
+        "df['description'] = descr\n",
+        "df\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 641
+        },
+        "id": "6GIEX9he4kIS",
+        "outputId": "17bf7376-90d2-428a-f868-e1f253ffe302"
+      },
+      "execution_count": 68,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "                                                  link  \\\n",
+              "0    https://www.jobinrwanda.com/job/organizational...   \n",
+              "1    https://www.jobinrwanda.com/job/monitoring-inc...   \n",
+              "2    https://www.jobinrwanda.com/job/resource-mobil...   \n",
+              "3    https://www.jobinrwanda.com/job/request-propos...   \n",
+              "4    https://www.jobinrwanda.com/job/finance-manage...   \n",
+              "..                                                 ...   \n",
+              "187   https://www.jobinrwanda.com/job/rwanda-tree-lead   \n",
+              "188  https://www.jobinrwanda.com/index.php/job/rwan...   \n",
+              "189  https://www.jobinrwanda.com/job/it-operations-...   \n",
+              "190  https://www.jobinrwanda.com/job/rwanda-seed-in...   \n",
+              "191  https://www.jobinrwanda.com/job/senior-busines...   \n",
+              "\n",
+              "                                                 title  \\\n",
+              "0    ​​​​​​​Organizational Development and Accounta...   \n",
+              "1           Monitoring, Inclusion and Learning Advisor   \n",
+              "2              Resource Mobilization and Grant Manager   \n",
+              "3    Request for Proposals for Electronic Logistics...   \n",
+              "4                                      Finance Manager   \n",
+              "..                                                 ...   \n",
+              "187                                   Rwanda Tree Lead   \n",
+              "188                  Rwanda Potato Seed Venture Lead   \n",
+              "189                       IT Operations Senior Manager   \n",
+              "190                 Rwanda Seed Innovation Centre Lead   \n",
+              "191                            Senior Business Analyst   \n",
+              "\n",
+              "                              company_link                        company  \\\n",
+              "0                       /employer/trocaire                       Trócaire   \n",
+              "1                       /employer/trocaire                       Trócaire   \n",
+              "2                       /employer/trocaire                       Trócaire   \n",
+              "3    /employer/chemonics-international-inc  Chemonics International Inc.    \n",
+              "4                /employer/womens-bakery-1             The Women's Bakery   \n",
+              "..                                     ...                            ...   \n",
+              "187                /employer/one-acre-fund                  One Acre Fund   \n",
+              "188      /index.php/employer/one-acre-fund                  One Acre Fund   \n",
+              "189                /employer/one-acre-fund                  One Acre Fund   \n",
+              "190                /employer/one-acre-fund                  One Acre Fund   \n",
+              "191                /employer/one-acre-fund                  One Acre Fund   \n",
+              "\n",
+              "    job_type                                        description  \n",
+              "0        Job  \\nTrócaire is the official overseas developmen...  \n",
+              "1        Job  \\nTrócaire is the official overseas developmen...  \n",
+              "2        Job  \\nTrócaire is the official overseas developmen...  \n",
+              "3     Tender                                                 NA  \n",
+              "4        Job                                                 NA  \n",
+              "..       ...                                                ...  \n",
+              "187      Job  \\nFounded in 2006, One Acre Fund supplies 1 mi...  \n",
+              "188      Job  \\nFounded in 2006, One Acre Fund supplies 1 mi...  \n",
+              "189      Job  \\nFounded in 2006, One Acre Fund supplies 1 mi...  \n",
+              "190      Job  \\nFounded in 2006, One Acre Fund supplies 1 mi...  \n",
+              "191      Job  \\nFounded in 2006, One Acre Fund supplies 1 mi...  \n",
+              "\n",
+              "[192 rows x 6 columns]"
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-4f805548-e0db-4b05-b35e-ec101a7ac48d\">\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>company_link</th>\n",
+              "      <th>company</th>\n",
+              "      <th>job_type</th>\n",
+              "      <th>description</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/organizational...</td>\n",
+              "      <td>​​​​​​​Organizational Development and Accounta...</td>\n",
+              "      <td>/employer/trocaire</td>\n",
+              "      <td>Trócaire</td>\n",
+              "      <td>Job</td>\n",
+              "      <td>\\nTrócaire is the official overseas developmen...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/monitoring-inc...</td>\n",
+              "      <td>Monitoring, Inclusion and Learning Advisor</td>\n",
+              "      <td>/employer/trocaire</td>\n",
+              "      <td>Trócaire</td>\n",
+              "      <td>Job</td>\n",
+              "      <td>\\nTrócaire is the official overseas developmen...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/resource-mobil...</td>\n",
+              "      <td>Resource Mobilization and Grant Manager</td>\n",
+              "      <td>/employer/trocaire</td>\n",
+              "      <td>Trócaire</td>\n",
+              "      <td>Job</td>\n",
+              "      <td>\\nTrócaire is the official overseas developmen...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/request-propos...</td>\n",
+              "      <td>Request for Proposals for Electronic Logistics...</td>\n",
+              "      <td>/employer/chemonics-international-inc</td>\n",
+              "      <td>Chemonics International Inc.</td>\n",
+              "      <td>Tender</td>\n",
+              "      <td>NA</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/finance-manage...</td>\n",
+              "      <td>Finance Manager</td>\n",
+              "      <td>/employer/womens-bakery-1</td>\n",
+              "      <td>The Women's Bakery</td>\n",
+              "      <td>Job</td>\n",
+              "      <td>NA</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>...</th>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>187</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/rwanda-tree-lead</td>\n",
+              "      <td>Rwanda Tree Lead</td>\n",
+              "      <td>/employer/one-acre-fund</td>\n",
+              "      <td>One Acre Fund</td>\n",
+              "      <td>Job</td>\n",
+              "      <td>\\nFounded in 2006, One Acre Fund supplies 1 mi...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>188</th>\n",
+              "      <td>https://www.jobinrwanda.com/index.php/job/rwan...</td>\n",
+              "      <td>Rwanda Potato Seed Venture Lead</td>\n",
+              "      <td>/index.php/employer/one-acre-fund</td>\n",
+              "      <td>One Acre Fund</td>\n",
+              "      <td>Job</td>\n",
+              "      <td>\\nFounded in 2006, One Acre Fund supplies 1 mi...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>189</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/it-operations-...</td>\n",
+              "      <td>IT Operations Senior Manager</td>\n",
+              "      <td>/employer/one-acre-fund</td>\n",
+              "      <td>One Acre Fund</td>\n",
+              "      <td>Job</td>\n",
+              "      <td>\\nFounded in 2006, One Acre Fund supplies 1 mi...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>190</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/rwanda-seed-in...</td>\n",
+              "      <td>Rwanda Seed Innovation Centre Lead</td>\n",
+              "      <td>/employer/one-acre-fund</td>\n",
+              "      <td>One Acre Fund</td>\n",
+              "      <td>Job</td>\n",
+              "      <td>\\nFounded in 2006, One Acre Fund supplies 1 mi...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>191</th>\n",
+              "      <td>https://www.jobinrwanda.com/job/senior-busines...</td>\n",
+              "      <td>Senior Business Analyst</td>\n",
+              "      <td>/employer/one-acre-fund</td>\n",
+              "      <td>One Acre Fund</td>\n",
+              "      <td>Job</td>\n",
+              "      <td>\\nFounded in 2006, One Acre Fund supplies 1 mi...</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "<p>192 rows × 6 columns</p>\n",
+              "</div>\n",
+              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-4f805548-e0db-4b05-b35e-ec101a7ac48d')\"\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-4f805548-e0db-4b05-b35e-ec101a7ac48d 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-4f805548-e0db-4b05-b35e-ec101a7ac48d');\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": 68
+        }
+      ]
+    }
+  ]
+}
\ No newline at end of file

From 658af1fa1b12c030f64a58a3fcdaca275be9a14f Mon Sep 17 00:00:00 2001
From: imukoki <60528574+imukoki@users.noreply.github.com>
Date: Mon, 21 Nov 2022 23:17:09 +0200
Subject: [PATCH 2/9] Update README.md

---
 README.md | 26 +++++++++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 9de005d..7608c3c 100644
--- a/README.md
+++ b/README.md
@@ -1 +1,25 @@
-# NLP-FELLOWSHIP
+# Web scraping
+
+## Description
+The objective of this project is to scrap the job opportunities posted on [here] (https://www.jobinrwanda.com) using the requests library to interact with the API. A library called BeautifulSoup to extract the meaningful content from the html which is obtained when the request library interacts with the API.
+
+
+## Code
+Below is the code that is used to extract the required information from the jobs posts:
+
+* Title of each job
+`content.find('span').getText()`
+* Link to the content of each job title
+`content.find('a')['href']` 
+* Link to the institution that has posted the advert
+`content.find('p').find('a')['href']` 
+* Name of the company
+`content.find('p').find('a').getText()`
+* Type of advert
+`content.find('p').find('span').getText()`
+* Company description
+`content.find_all('div', class_='employer-description')[0].getText()`
+
+## Output
+Below is the dataframe that was created from the scrapped data
+![Company](https://user-images.githubusercontent.com/60528574/203159813-a73e32a1-7e57-476d-8e9e-6c9735df4df1.PNG)

From abc8e7c31ec6a79a1bddbd04206e00cd840c35ef Mon Sep 17 00:00:00 2001
From: imukoki <60528574+imukoki@users.noreply.github.com>
Date: Mon, 21 Nov 2022 23:18:01 +0200
Subject: [PATCH 3/9] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 7608c3c..242f85f 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
 # Web scraping
 
 ## Description
-The objective of this project is to scrap the job opportunities posted on [here] (https://www.jobinrwanda.com) using the requests library to interact with the API. A library called BeautifulSoup to extract the meaningful content from the html which is obtained when the request library interacts with the API.
+The objective of this project is to scrap the job opportunities posted on ([here] (https://www.jobinrwanda.com)) using the requests library to interact with the API. A library called BeautifulSoup to extract the meaningful content from the html which is obtained when the request library interacts with the API.
 
 
 ## Code

From cf8969160e6e45e4d900dee2e8ef898a03f3227c Mon Sep 17 00:00:00 2001
From: imukoki <60528574+imukoki@users.noreply.github.com>
Date: Mon, 21 Nov 2022 23:19:36 +0200
Subject: [PATCH 4/9] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 242f85f..b64d5d8 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
 # Web scraping
 
 ## Description
-The objective of this project is to scrap the job opportunities posted on ([here] (https://www.jobinrwanda.com)) using the requests library to interact with the API. A library called BeautifulSoup to extract the meaningful content from the html which is obtained when the request library interacts with the API.
+The objective of this project is to scrap the job opportunities posted [here] (https://www.jobinrwanda.com) using the requests library to interact with the API. A library called BeautifulSoup to extract the meaningful content from the html which is obtained when the request library interacts with the API.
 
 
 ## Code

From 3486e39e9aef97dfa748557ae1ad6a67812fc255 Mon Sep 17 00:00:00 2001
From: imukoki <60528574+imukoki@users.noreply.github.com>
Date: Mon, 21 Nov 2022 23:20:26 +0200
Subject: [PATCH 5/9] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index b64d5d8..e372c3f 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
 # Web scraping
 
 ## Description
-The objective of this project is to scrap the job opportunities posted [here] (https://www.jobinrwanda.com) using the requests library to interact with the API. A library called BeautifulSoup to extract the meaningful content from the html which is obtained when the request library interacts with the API.
+The objective of this project is to scrap the job opportunities posted (https://www.jobinrwanda.com) using the requests library to interact with the API. A library called BeautifulSoup to extract the meaningful content from the html which is obtained when the request library interacts with the API.
 
 
 ## Code

From 6977eafe5ee5bc789bac12174e446e3f2733aca4 Mon Sep 17 00:00:00 2001
From: imukoki <60528574+imukoki@users.noreply.github.com>
Date: Mon, 21 Nov 2022 23:21:56 +0200
Subject: [PATCH 6/9] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index e372c3f..c2cfe73 100644
--- a/README.md
+++ b/README.md
@@ -1,7 +1,7 @@
 # Web scraping
 
 ## Description
-The objective of this project is to scrap the job opportunities posted (https://www.jobinrwanda.com) using the requests library to interact with the API. A library called BeautifulSoup to extract the meaningful content from the html which is obtained when the request library interacts with the API.
+The objective of this project is to scrap the job opportunities posted [here](https://www.jobinrwanda.com) using the requests library to interact with the API. A library called BeautifulSoup to extract the meaningful content from the html which is obtained when the request library interacts with the API.
 
 
 ## Code

From 9fc7bfbe9d0eaa10749083d34fde27f8033056a1 Mon Sep 17 00:00:00 2001
From: imukoki <60528574+imukoki@users.noreply.github.com>
Date: Mon, 21 Nov 2022 23:31:41 +0200
Subject: [PATCH 7/9] Update README.md

---
 README.md | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/README.md b/README.md
index c2cfe73..4e98090 100644
--- a/README.md
+++ b/README.md
@@ -23,3 +23,18 @@ Below is the code that is used to extract the required information from the jobs
 ## Output
 Below is the dataframe that was created from the scrapped data
 ![Company](https://user-images.githubusercontent.com/60528574/203159813-a73e32a1-7e57-476d-8e9e-6c9735df4df1.PNG)
+
+# Text to features
+The other objective of the project was to convert a list of sentences to features. Text to features is the process of converting tokens to numbers. This is because the machine only works with numbers. Moreover, for manipulation of text, the tokens need to be in digit form to apply any transformations.
+
+The input of the function will be the matrix of tokens and output will be matrix with digits.
+
+## Simplest form of featurization
+The simplest way is to assign each unique text a number starting from 0 and increase by one until all the text has been assigned numbers
+
+## Bag Of Words (BoW)
+* Split the sentences into words
+* Create a dictionary with all unique words and their indices
+* Create a vector, size same as the total number of unique words
+* For every word in a sentence, get the index and add 1.
+* The result will be a vector for each sentence with length same as all the unique words in all sentences, with frequency of each word in one particular sentence. If a word is not in that sentence, the frequency is 0

From ec125a036d4096b7e66b76ee8ed294fa5754b477 Mon Sep 17 00:00:00 2001
From: imukoki <60528574+imukoki@users.noreply.github.com>
Date: Mon, 21 Nov 2022 23:34:24 +0200
Subject: [PATCH 8/9] Update README.md

---
 README.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/README.md b/README.md
index 4e98090..b76892a 100644
--- a/README.md
+++ b/README.md
@@ -29,6 +29,8 @@ The other objective of the project was to convert a list of sentences to feature
 
 The input of the function will be the matrix of tokens and output will be matrix with digits.
 
+Two ways of converting text to features were used in the project which are the simplest form of featurization and bag of words (BOW)
+
 ## Simplest form of featurization
 The simplest way is to assign each unique text a number starting from 0 and increase by one until all the text has been assigned numbers
 

From 86b4689202589b5268e516f0caf41fe653d20278 Mon Sep 17 00:00:00 2001
From: imukoki <60528574+imukoki@users.noreply.github.com>
Date: Tue, 22 Nov 2022 00:01:12 +0200
Subject: [PATCH 9/9] Update README.md

---
 README.md | 15 ---------------
 1 file changed, 15 deletions(-)

diff --git a/README.md b/README.md
index b76892a..ad26bad 100644
--- a/README.md
+++ b/README.md
@@ -24,19 +24,4 @@ Below is the code that is used to extract the required information from the jobs
 Below is the dataframe that was created from the scrapped data
 ![Company](https://user-images.githubusercontent.com/60528574/203159813-a73e32a1-7e57-476d-8e9e-6c9735df4df1.PNG)
 
-# Text to features
-The other objective of the project was to convert a list of sentences to features. Text to features is the process of converting tokens to numbers. This is because the machine only works with numbers. Moreover, for manipulation of text, the tokens need to be in digit form to apply any transformations.
 
-The input of the function will be the matrix of tokens and output will be matrix with digits.
-
-Two ways of converting text to features were used in the project which are the simplest form of featurization and bag of words (BOW)
-
-## Simplest form of featurization
-The simplest way is to assign each unique text a number starting from 0 and increase by one until all the text has been assigned numbers
-
-## Bag Of Words (BoW)
-* Split the sentences into words
-* Create a dictionary with all unique words and their indices
-* Create a vector, size same as the total number of unique words
-* For every word in a sentence, get the index and add 1.
-* The result will be a vector for each sentence with length same as all the unique words in all sentences, with frequency of each word in one particular sentence. If a word is not in that sentence, the frequency is 0