├── README.md
├── LICENSE
├── Segmentation.ipynb
├── Log File Analysis.ipynb
├── Internal Link Analysis.ipynb
└── Google_PyTrends.ipynb


/README.md:
--------------------------------------------------------------------------------
 1 | # python-for-seo
 2 | 
 3 | Hello! 
 4 | 
 5 | This is a small collection of beginner friendly python scripts for performing data analysis for the purpose of SEO. Please read [this article](https://www.searchenginejournal.com/7-example-projects-to-get-started-with-python-for-seo/389336/) to find out more.
 6 | 
 7 | If you have any questions or would like some data to play around with, please feel free to reach out to me via email - ruth.everett@deepcrawl.com or on twitter [@rvtheverett](https://twitter.com/rvtheverett) 
 8 | 
 9 | I hope to add more scripts soon :) 
10 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
 1 | MIT License
 2 | 
 3 | Copyright (c) 2020 rvth
 4 | 
 5 | Permission is hereby granted, free of charge, to any person obtaining a copy
 6 | of this software and associated documentation files (the "Software"), to deal
 7 | in the Software without restriction, including without limitation the rights
 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 | 
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 | 
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 | 


--------------------------------------------------------------------------------
/Segmentation.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": null,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "# Importing all needed libraries\n",
 10 |     "import pandas as pd\n",
 11 |     "from google.colab import files\n",
 12 |     "import io\n",
 13 |     "import re"
 14 |    ]
 15 |   },
 16 |   {
 17 |    "cell_type": "code",
 18 |    "execution_count": null,
 19 |    "metadata": {},
 20 |    "outputs": [],
 21 |    "source": [
 22 |     "# Upload crawl data\n",
 23 |     "df = pd.read_csv('/Users/rutheverett/Downloads/file-path')"
 24 |    ]
 25 |   },
 26 |   {
 27 |    "cell_type": "code",
 28 |    "execution_count": null,
 29 |    "metadata": {},
 30 |    "outputs": [],
 31 |    "source": [
 32 |     "# Define your own custom regex segments\n",
 33 |     "\n",
 34 |     "segment_definitions = [\n",
 35 |     "    [(r'\\/blog\\/'), 'Blog'],\n",
 36 |     "    [(r'\\/technical-seo-library\\/'), 'Technical SEO Library'],\n",
 37 |     "    [(r'\\/hangout-library\\/'), 'Hangout Library'],\n",
 38 |     "    [(r'\\/guides\\/'), 'Guides'],\n",
 39 |     "    [(r'\\/case-studies\\/'), 'Case Studies'],\n",
 40 |     "    [(r'\\/why-'), 'Solutions'],\n",
 41 |     "    ]\n",
 42 |     "\n",
 43 |     "use_segment_definitions = True\n",
 44 |     "\n",
 45 |     "def get_segment(url):\n",
 46 |     "    \n",
 47 |     "    if use_segment_definitions == True:\n",
 48 |     "        for segment_definition in segment_definitions:\n",
 49 |     "            if re.findall(segment_definition[0], url):\n",
 50 |     "                return segment_definition[1]\n",
 51 |     "        return 'Other'\n",
 52 |     "\n",
 53 |     "# Add a segment column, and assign each URL a segment   \n",
 54 |     "df['segment'] = df['url'].apply(lambda x: get_segment(x))"
 55 |    ]
 56 |   },
 57 |   {
 58 |    "cell_type": "code",
 59 |    "execution_count": null,
 60 |    "metadata": {},
 61 |    "outputs": [],
 62 |    "source": [
 63 |     "# Function to create a segment from a URL\n",
 64 |     "def get_segment(url):\n",
 65 |     "  \n",
 66 |     "        slug = re.search(r'https?:\\/\\/.*?\\//?([^\\/]*)\\/', url)\n",
 67 |     "        if slug:\n",
 68 |     "            return slug.group(1)\n",
 69 |     "        else:\n",
 70 |     "            return 'None'\n",
 71 |     "\n",
 72 |     "# Add a segment column, and assign each URL a segment   \n",
 73 |     "df['segment'] = df['url'].apply(lambda x: get_segment(x))"
 74 |    ]
 75 |   },
 76 |   {
 77 |    "cell_type": "code",
 78 |    "execution_count": null,
 79 |    "metadata": {},
 80 |    "outputs": [],
 81 |    "source": [
 82 |     "df.head(10)"
 83 |    ]
 84 |   }
 85 |  ],
 86 |  "metadata": {
 87 |   "kernelspec": {
 88 |    "display_name": "Python 3",
 89 |    "language": "python",
 90 |    "name": "python3"
 91 |   },
 92 |   "language_info": {
 93 |    "codemirror_mode": {
 94 |     "name": "ipython",
 95 |     "version": 3
 96 |    },
 97 |    "file_extension": ".py",
 98 |    "mimetype": "text/x-python",
 99 |    "name": "python",
100 |    "nbconvert_exporter": "python",
101 |    "pygments_lexer": "ipython3",
102 |    "version": "3.7.6"
103 |   }
104 |  },
105 |  "nbformat": 4,
106 |  "nbformat_minor": 4
107 | }
108 | 


--------------------------------------------------------------------------------
/Log File Analysis.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 18,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "import pandas as pd\n",
 10 |     "import numpy as np\n",
 11 |     "import requests\n",
 12 |     "import re\n",
 13 |     "import seaborn as sns\n",
 14 |     "import matplotlib.pyplot as plt"
 15 |    ]
 16 |   },
 17 |   {
 18 |    "cell_type": "code",
 19 |    "execution_count": 20,
 20 |    "metadata": {},
 21 |    "outputs": [],
 22 |    "source": [
 23 |     "#upload data\n",
 24 |     "data = ('/Users/rutheverett/Downloads/www-deepcrawl-com_12-10-2020_All_Pages_basic.csv')\n",
 25 |     "#select colums \n",
 26 |     "columns = ['url',\n",
 27 |     "           'log_requests_total',\n",
 28 |     "           'log_requests_desktop',\n",
 29 |     "           'log_requests_mobile',\n",
 30 |     "           'indexable',\n",
 31 |     "           'http_status_code',\n",
 32 |     "           'primary_page',\n",
 33 |     "           'duplicate_page', \n",
 34 |     "           'search_console_total_clicks',\n",
 35 |     "           'level',\n",
 36 |     "           'links_in_count']\n",
 37 |     "#read in data colums \n",
 38 |     "df = pd.read_csv(data , usecols=columns)\n",
 39 |     "df.head(10)"
 40 |    ]
 41 |   },
 42 |   {
 43 |    "cell_type": "code",
 44 |    "execution_count": null,
 45 |    "metadata": {},
 46 |    "outputs": [],
 47 |    "source": [
 48 |     "#Segment URLs \n",
 49 |     "segment_definitions = [\n",
 50 |     "    [(r'\\/blog\\/'), 'Blog'],\n",
 51 |     "    [(r'\\/technical-seo-library\\/'), 'Technical SEO Library'],\n",
 52 |     "    [(r'\\/hangout-library\\/'), 'Hangout Library'],\n",
 53 |     "    [(r'\\/guides\\/'), 'Guides'],\n",
 54 |     "    [(r'\\/case-studies\\/'), 'Case Studies'],\n",
 55 |     "    [(r'\\/why-'), 'Solutions'],\n",
 56 |     "    ]\n",
 57 |     "\n",
 58 |     "use_segment_definitions = True\n",
 59 |     "\n",
 60 |     "def get_segment(url):\n",
 61 |     "    \n",
 62 |     "    if use_segment_definitions == True:\n",
 63 |     "        for segment_definition in segment_definitions:\n",
 64 |     "            if re.findall(segment_definition[0], url):\n",
 65 |     "                return segment_definition[1]\n",
 66 |     "        return 'Other'\n",
 67 |     "\n",
 68 |     "df['segment'] = df['url'].apply(lambda x: get_segment(x))\n",
 69 |     "\n",
 70 |     "# Replace NaN with 0\n",
 71 |     "df['search_console_total_clicks'].replace(np.nan, 0, inplace=True)\n",
 72 |     "df['log_requests_total'].replace(np.nan, 0, inplace=True)\n",
 73 |     "df['log_requests_mobile'].replace(np.nan, 0, inplace=True)\n",
 74 |     "df['log_requests_desktop'].replace(np.nan, 0, inplace=True)\n",
 75 |     "df['level'].replace(np.nan, 0, inplace=True)"
 76 |    ]
 77 |   },
 78 |   {
 79 |    "cell_type": "code",
 80 |    "execution_count": null,
 81 |    "metadata": {},
 82 |    "outputs": [],
 83 |    "source": [
 84 |     "#Create pivot table with total log file requests for each segment\n",
 85 |     "total_log_requests = df.pivot_table(index='segment', values=['url', 'log_requests_total', 'log_requests_mobile', 'log_requests_desktop'], aggfunc={'url':len, 'log_requests_total':sum, 'log_requests_mobile':sum, 'log_requests_desktop':sum})\n",
 86 |     "total_log_requests['percent_of_total_log_requests']= (total_log_requests['log_requests_total']/total_log_requests['log_requests_total'].sum()).apply('{:.2%}'.format)\n",
 87 |     "#Reset Index\n",
 88 |     "new_total_log_requests = total_log_requests.reset_index('segment')\n",
 89 |     "new_total_log_requests"
 90 |    ]
 91 |   },
 92 |   {
 93 |    "cell_type": "code",
 94 |    "execution_count": null,
 95 |    "metadata": {},
 96 |    "outputs": [],
 97 |    "source": [
 98 |     "#Create bar chart for total requests per category\n",
 99 |     "sns.barplot(data=new_pivot, x='segment', y='log_requests_total')\n",
100 |     "plt.xticks(rotation=90)\n",
101 |     "plt.show()"
102 |    ]
103 |   },
104 |   {
105 |    "cell_type": "code",
106 |    "execution_count": null,
107 |    "metadata": {},
108 |    "outputs": [],
109 |    "source": [
110 |     "#Create bar chart for total mobile requests per category\n",
111 |     "sns.barplot(data=new_pivot, x='segment', y='log_requests_mobile')\n",
112 |     "plt.xticks(rotation=90)\n",
113 |     "plt.show()"
114 |    ]
115 |   },
116 |   {
117 |    "cell_type": "code",
118 |    "execution_count": null,
119 |    "metadata": {},
120 |    "outputs": [],
121 |    "source": [
122 |     "#Create bar chart for total desktop requests per category\n",
123 |     "sns.barplot(data=new_pivot, x='segment', y='log_requests_desktop')\n",
124 |     "plt.xticks(rotation=90)\n",
125 |     "plt.show()"
126 |    ]
127 |   },
128 |   {
129 |    "cell_type": "code",
130 |    "execution_count": null,
131 |    "metadata": {},
132 |    "outputs": [],
133 |    "source": [
134 |     "#Create pivot table with total log file requests for indexability status \n",
135 |     "indexable_log_file = df.pivot_table(index='indexable', values=['url', 'log_requests_total', 'log_requests_mobile', 'log_requests_desktop'], aggfunc={'url':len, 'log_requests_total':sum, 'log_requests_mobile':sum, 'log_requests_desktop':sum})\n",
136 |     "indexable_log_file['percent_of_total_log_requests']= (indexable_log_file['log_requests_total']/indexable_log_file['log_requests_total'].sum()).apply('{:.2%}'.format)\n",
137 |     "indexable_log_file"
138 |    ]
139 |   },
140 |   {
141 |    "cell_type": "code",
142 |    "execution_count": null,
143 |    "metadata": {},
144 |    "outputs": [],
145 |    "source": [
146 |     "# Function to create a pivot table with a variable number of indexes\n",
147 |     "\n",
148 |     "def pivot_table(df, indexes):\n",
149 |     "    pivot_table = df.pivot_table(index=indexes, values=['url', 'log_requests_total'], aggfunc={'url':len, 'log_requests_total':sum})\n",
150 |     "\n",
151 |     "    pivot_table = pivot_table.sort_values('log_requests_total', ascending=False)\n",
152 |     "    pivot_table['percent_of_total_log_requests']= (pivot_table['log_requests_total']/pivot_table['log_requests_total'].sum()).apply('{:.2%}'.format)\n",
153 |     "    pivot_table['average_log_requests_per_url']= (pivot_table['log_requests_total']/pivot_table['url']).apply('{:.1f}'.format)\n",
154 |     "    pivot_table['log_requests_total'] = (pivot_table['log_requests_total']).apply('{:,.0f}'.format)\n",
155 |     "    pivot_table['url'] = (pivot_table['url']).apply('{:,}'.format)\n",
156 |     "    pivot_table = pivot_table.rename({'url': 'url_count'}, axis='columns')\n",
157 |     "\n",
158 |     "    return pivot_table"
159 |    ]
160 |   },
161 |   {
162 |    "cell_type": "code",
163 |    "execution_count": null,
164 |    "metadata": {},
165 |    "outputs": [],
166 |    "source": [
167 |     "#Create pivot table with total log file requests for status code\n",
168 |     "pivot_status = pivot_table(df, ['category', 'http_status_code'])\n",
169 |     "pivot_status"
170 |    ]
171 |   },
172 |   {
173 |    "cell_type": "code",
174 |    "execution_count": null,
175 |    "metadata": {},
176 |    "outputs": [],
177 |    "source": [
178 |     "#Create pivot table with total log file requests for 200 status code, indexable pages - you can change these to be any status code and either indexable or non-indexable\n",
179 |     "df_200 = df[(df.http_status_code == 200)]\n",
180 |     "\n",
181 |     "pivot_indexable = pivot_table(df_200, ['category', 'indexable'])\n",
182 |     "pivot_indexable"
183 |    ]
184 |   },
185 |   {
186 |    "cell_type": "markdown",
187 |    "metadata": {},
188 |    "source": [
189 |     "If you would like to see how log file requests have changed over 6 months: "
190 |    ]
191 |   },
192 |   {
193 |    "cell_type": "code",
194 |    "execution_count": null,
195 |    "metadata": {},
196 |    "outputs": [],
197 |    "source": [
198 |     "#upload multiple dfs \n",
199 |     "june_df = pd.read_csv(june , usecols=columns)\n",
200 |     "july_df = pd.read_csv(july , usecols=columns)\n",
201 |     "aug_df = pd.read_csv(aug , usecols=columns) \n",
202 |     "sep_df = pd.read_csv(sep , usecols=columns)\n",
203 |     "oct_df = pd.read_csv(oct , usecols=columns)\n",
204 |     "nov_df = pd.read_csv(nov , usecols=columns)\n",
205 |     "\n",
206 |     "june_df['month'] = 'May'\n",
207 |     "july_df['month'] = 'June'\n",
208 |     "aug_df['month'] = 'July'\n",
209 |     "sep_df['month'] = 'August'\n",
210 |     "oct_df['month'] = 'September'\n",
211 |     "nov_df['month'] = 'October'\n",
212 |     "\n",
213 |     "#concatenate dataframes together\n",
214 |     "df_all = pd.concat(objs =[june_df, july_df, aug_df, sep_df, oct_df, nov_df], ignore_index=True)"
215 |    ]
216 |   },
217 |   {
218 |    "cell_type": "code",
219 |    "execution_count": null,
220 |    "metadata": {},
221 |    "outputs": [],
222 |    "source": [
223 |     "#create pivot table to store all data\n",
224 |     "def pivot_table(df, indexes):\n",
225 |     "    pivot_table = df.pivot_table(index=indexes, values=['url', 'log_requests_total'], aggfunc={'url':len, 'log_requests_total':sum})\n",
226 |     "\n",
227 |     "    pivot_table = pivot_table.sort_values('log_requests_total', ascending=False)\n",
228 |     "    pivot_table['percent_of_total_log_requests']= (pivot_table['log_requests_total']/pivot_table['log_requests_total'].sum()).apply('{:.2%}'.format)\n",
229 |     "    pivot_table['average_log_requests_per_url']= (pivot_table['log_requests_total']/pivot_table['url']).apply('{:.1f}'.format)\n",
230 |     "    pivot_table['log_requests_total'] = (pivot_table['log_requests_total']).apply('{:,.0f}'.format)\n",
231 |     "    pivot_table['url'] = (pivot_table['url']).apply('{:,}'.format)\n",
232 |     "    pivot_table = pivot_table.rename({'url': 'url_count'}, axis='columns')\n",
233 |     "\n",
234 |     "    return pivot_table"
235 |    ]
236 |   },
237 |   {
238 |    "cell_type": "code",
239 |    "execution_count": null,
240 |    "metadata": {},
241 |    "outputs": [],
242 |    "source": [
243 |     "#create pivot table to get count of log file requests for each month\n",
244 |     "pivot_table_total = df.pivot_table(index='month', values=['url', 'log_requests_total', 'log_requests_mobile', 'log_requests_desktop'], aggfunc={'url':len, 'log_requests_total':sum, 'log_requests_mobile':sum, 'log_requests_desktop':sum})\n",
245 |     "pivot_table_total \n",
246 |     "\n",
247 |     "#reset index to get months in order\n",
248 |     "new_index = ['May', 'June', 'July', 'August', 'September', 'October']\n",
249 |     "new_pivot = pivot_table_total.reindex(new_index)\n",
250 |     "new_pivot"
251 |    ]
252 |   },
253 |   {
254 |    "cell_type": "code",
255 |    "execution_count": null,
256 |    "metadata": {},
257 |    "outputs": [],
258 |    "source": [
259 |     "#create line graph to show log requests over time \n",
260 |     "sns.lineplot(x = \"month\", y = \"log_requests_total\", data=new_pivot)\n",
261 |     "plt.show()"
262 |    ]
263 |   }
264 |  ],
265 |  "metadata": {
266 |   "kernelspec": {
267 |    "display_name": "Python 3",
268 |    "language": "python",
269 |    "name": "python3"
270 |   },
271 |   "language_info": {
272 |    "codemirror_mode": {
273 |     "name": "ipython",
274 |     "version": 3
275 |    },
276 |    "file_extension": ".py",
277 |    "mimetype": "text/x-python",
278 |    "name": "python",
279 |    "nbconvert_exporter": "python",
280 |    "pygments_lexer": "ipython3",
281 |    "version": "3.7.6"
282 |   }
283 |  },
284 |  "nbformat": 4,
285 |  "nbformat_minor": 4
286 | }
287 | 


--------------------------------------------------------------------------------
/Internal Link Analysis.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "metadata": {},
  7 |    "outputs": [],
  8 |    "source": [
  9 |     "import pandas as pd\n",
 10 |     "import re\n",
 11 |     "import numpy as np\n",
 12 |     "import requests\n",
 13 |     "import urllib\n",
 14 |     "import io"
 15 |    ]
 16 |   },
 17 |   {
 18 |    "cell_type": "code",
 19 |    "execution_count": 3,
 20 |    "metadata": {},
 21 |    "outputs": [],
 22 |    "source": [
 23 |     "#insert crawl csv \n",
 24 |     "data = ('/Users/rutheverett/Downloads/www-deepcrawl-com_12-10-2020_All_Pages_basic.csv')\n",
 25 |     "#update to include columns you would like to include from csv \n",
 26 |     "columns = ['url', 'level', 'http_status_code', 'indexable', 'links_in_count', 'followed_links_in_count', 'links_out_count', 'deeprank', 'backlink_count', 'backlink_domain_count']\n",
 27 |     "df = pd.read_csv(data , usecols=columns)"
 28 |    ]
 29 |   },
 30 |   {
 31 |    "cell_type": "code",
 32 |    "execution_count": 7,
 33 |    "metadata": {},
 34 |    "outputs": [
 35 |     {
 36 |      "data": {
 37 |       "text/html": [
 38 |        "<div>\n",
 39 |        "<style scoped>\n",
 40 |        "    .dataframe tbody tr th:only-of-type {\n",
 41 |        "        vertical-align: middle;\n",
 42 |        "    }\n",
 43 |        "\n",
 44 |        "    .dataframe tbody tr th {\n",
 45 |        "        vertical-align: top;\n",
 46 |        "    }\n",
 47 |        "\n",
 48 |        "    .dataframe thead th {\n",
 49 |        "        text-align: right;\n",
 50 |        "    }\n",
 51 |        "</style>\n",
 52 |        "<table border=\"1\" class=\"dataframe\">\n",
 53 |        "  <thead>\n",
 54 |        "    <tr style=\"text-align: right;\">\n",
 55 |        "      <th></th>\n",
 56 |        "      <th>deeprank</th>\n",
 57 |        "      <th>level</th>\n",
 58 |        "      <th>url</th>\n",
 59 |        "      <th>http_status_code</th>\n",
 60 |        "      <th>indexable</th>\n",
 61 |        "      <th>links_in_count</th>\n",
 62 |        "      <th>links_out_count</th>\n",
 63 |        "      <th>followed_links_in_count</th>\n",
 64 |        "      <th>backlink_count</th>\n",
 65 |        "      <th>backlink_domain_count</th>\n",
 66 |        "      <th>segment</th>\n",
 67 |        "    </tr>\n",
 68 |        "  </thead>\n",
 69 |        "  <tbody>\n",
 70 |        "    <tr>\n",
 71 |        "      <th>0</th>\n",
 72 |        "      <td>2.13</td>\n",
 73 |        "      <td>3</td>\n",
 74 |        "      <td>https://www.deepcrawl.com/knowledge/technical-...</td>\n",
 75 |        "      <td>200</td>\n",
 76 |        "      <td>True</td>\n",
 77 |        "      <td>3</td>\n",
 78 |        "      <td>88</td>\n",
 79 |        "      <td>3</td>\n",
 80 |        "      <td>NaN</td>\n",
 81 |        "      <td>NaN</td>\n",
 82 |        "      <td>Technical SEO Library</td>\n",
 83 |        "    </tr>\n",
 84 |        "    <tr>\n",
 85 |        "      <th>1</th>\n",
 86 |        "      <td>2.55</td>\n",
 87 |        "      <td>3</td>\n",
 88 |        "      <td>https://www.deepcrawl.com/knowledge/guides/sch...</td>\n",
 89 |        "      <td>200</td>\n",
 90 |        "      <td>True</td>\n",
 91 |        "      <td>6</td>\n",
 92 |        "      <td>114</td>\n",
 93 |        "      <td>6</td>\n",
 94 |        "      <td>NaN</td>\n",
 95 |        "      <td>NaN</td>\n",
 96 |        "      <td>Guides</td>\n",
 97 |        "    </tr>\n",
 98 |        "    <tr>\n",
 99 |        "      <th>2</th>\n",
100 |        "      <td>2.19</td>\n",
101 |        "      <td>3</td>\n",
102 |        "      <td>https://www.deepcrawl.com/knowledge/technical-...</td>\n",
103 |        "      <td>200</td>\n",
104 |        "      <td>True</td>\n",
105 |        "      <td>1</td>\n",
106 |        "      <td>93</td>\n",
107 |        "      <td>1</td>\n",
108 |        "      <td>NaN</td>\n",
109 |        "      <td>NaN</td>\n",
110 |        "      <td>Technical SEO Library</td>\n",
111 |        "    </tr>\n",
112 |        "    <tr>\n",
113 |        "      <th>3</th>\n",
114 |        "      <td>2.51</td>\n",
115 |        "      <td>3</td>\n",
116 |        "      <td>https://www.deepcrawl.com/knowledge/guides/seg...</td>\n",
117 |        "      <td>200</td>\n",
118 |        "      <td>True</td>\n",
119 |        "      <td>1</td>\n",
120 |        "      <td>92</td>\n",
121 |        "      <td>1</td>\n",
122 |        "      <td>NaN</td>\n",
123 |        "      <td>NaN</td>\n",
124 |        "      <td>Guides</td>\n",
125 |        "    </tr>\n",
126 |        "    <tr>\n",
127 |        "      <th>4</th>\n",
128 |        "      <td>2.57</td>\n",
129 |        "      <td>3</td>\n",
130 |        "      <td>https://www.deepcrawl.com/blog/events/go-red-c...</td>\n",
131 |        "      <td>200</td>\n",
132 |        "      <td>True</td>\n",
133 |        "      <td>13</td>\n",
134 |        "      <td>108</td>\n",
135 |        "      <td>13</td>\n",
136 |        "      <td>NaN</td>\n",
137 |        "      <td>NaN</td>\n",
138 |        "      <td>Blog</td>\n",
139 |        "    </tr>\n",
140 |        "    <tr>\n",
141 |        "      <th>5</th>\n",
142 |        "      <td>2.07</td>\n",
143 |        "      <td>3</td>\n",
144 |        "      <td>https://www.deepcrawl.com/knowledge/technical-...</td>\n",
145 |        "      <td>200</td>\n",
146 |        "      <td>True</td>\n",
147 |        "      <td>2</td>\n",
148 |        "      <td>86</td>\n",
149 |        "      <td>2</td>\n",
150 |        "      <td>NaN</td>\n",
151 |        "      <td>NaN</td>\n",
152 |        "      <td>Technical SEO Library</td>\n",
153 |        "    </tr>\n",
154 |        "    <tr>\n",
155 |        "      <th>6</th>\n",
156 |        "      <td>2.07</td>\n",
157 |        "      <td>3</td>\n",
158 |        "      <td>https://www.deepcrawl.com/knowledge/technical-...</td>\n",
159 |        "      <td>200</td>\n",
160 |        "      <td>True</td>\n",
161 |        "      <td>2</td>\n",
162 |        "      <td>86</td>\n",
163 |        "      <td>2</td>\n",
164 |        "      <td>NaN</td>\n",
165 |        "      <td>NaN</td>\n",
166 |        "      <td>Technical SEO Library</td>\n",
167 |        "    </tr>\n",
168 |        "    <tr>\n",
169 |        "      <th>7</th>\n",
170 |        "      <td>2.59</td>\n",
171 |        "      <td>3</td>\n",
172 |        "      <td>https://www.deepcrawl.com/knowledge/technical-...</td>\n",
173 |        "      <td>200</td>\n",
174 |        "      <td>True</td>\n",
175 |        "      <td>5</td>\n",
176 |        "      <td>97</td>\n",
177 |        "      <td>5</td>\n",
178 |        "      <td>NaN</td>\n",
179 |        "      <td>NaN</td>\n",
180 |        "      <td>Technical SEO Library</td>\n",
181 |        "    </tr>\n",
182 |        "    <tr>\n",
183 |        "      <th>8</th>\n",
184 |        "      <td>2.55</td>\n",
185 |        "      <td>3</td>\n",
186 |        "      <td>https://www.deepcrawl.com/knowledge/guides/ren...</td>\n",
187 |        "      <td>200</td>\n",
188 |        "      <td>True</td>\n",
189 |        "      <td>6</td>\n",
190 |        "      <td>94</td>\n",
191 |        "      <td>6</td>\n",
192 |        "      <td>NaN</td>\n",
193 |        "      <td>NaN</td>\n",
194 |        "      <td>Guides</td>\n",
195 |        "    </tr>\n",
196 |        "    <tr>\n",
197 |        "      <th>9</th>\n",
198 |        "      <td>2.17</td>\n",
199 |        "      <td>3</td>\n",
200 |        "      <td>https://www.deepcrawl.com/knowledge/technical-...</td>\n",
201 |        "      <td>200</td>\n",
202 |        "      <td>True</td>\n",
203 |        "      <td>2</td>\n",
204 |        "      <td>100</td>\n",
205 |        "      <td>2</td>\n",
206 |        "      <td>NaN</td>\n",
207 |        "      <td>NaN</td>\n",
208 |        "      <td>Technical SEO Library</td>\n",
209 |        "    </tr>\n",
210 |        "  </tbody>\n",
211 |        "</table>\n",
212 |        "</div>"
213 |       ],
214 |       "text/plain": [
215 |        "   deeprank  level                                                url  \\\n",
216 |        "0      2.13      3  https://www.deepcrawl.com/knowledge/technical-...   \n",
217 |        "1      2.55      3  https://www.deepcrawl.com/knowledge/guides/sch...   \n",
218 |        "2      2.19      3  https://www.deepcrawl.com/knowledge/technical-...   \n",
219 |        "3      2.51      3  https://www.deepcrawl.com/knowledge/guides/seg...   \n",
220 |        "4      2.57      3  https://www.deepcrawl.com/blog/events/go-red-c...   \n",
221 |        "5      2.07      3  https://www.deepcrawl.com/knowledge/technical-...   \n",
222 |        "6      2.07      3  https://www.deepcrawl.com/knowledge/technical-...   \n",
223 |        "7      2.59      3  https://www.deepcrawl.com/knowledge/technical-...   \n",
224 |        "8      2.55      3  https://www.deepcrawl.com/knowledge/guides/ren...   \n",
225 |        "9      2.17      3  https://www.deepcrawl.com/knowledge/technical-...   \n",
226 |        "\n",
227 |        "   http_status_code  indexable  links_in_count  links_out_count  \\\n",
228 |        "0               200       True               3               88   \n",
229 |        "1               200       True               6              114   \n",
230 |        "2               200       True               1               93   \n",
231 |        "3               200       True               1               92   \n",
232 |        "4               200       True              13              108   \n",
233 |        "5               200       True               2               86   \n",
234 |        "6               200       True               2               86   \n",
235 |        "7               200       True               5               97   \n",
236 |        "8               200       True               6               94   \n",
237 |        "9               200       True               2              100   \n",
238 |        "\n",
239 |        "   followed_links_in_count  backlink_count  backlink_domain_count  \\\n",
240 |        "0                        3             NaN                    NaN   \n",
241 |        "1                        6             NaN                    NaN   \n",
242 |        "2                        1             NaN                    NaN   \n",
243 |        "3                        1             NaN                    NaN   \n",
244 |        "4                       13             NaN                    NaN   \n",
245 |        "5                        2             NaN                    NaN   \n",
246 |        "6                        2             NaN                    NaN   \n",
247 |        "7                        5             NaN                    NaN   \n",
248 |        "8                        6             NaN                    NaN   \n",
249 |        "9                        2             NaN                    NaN   \n",
250 |        "\n",
251 |        "                 segment  \n",
252 |        "0  Technical SEO Library  \n",
253 |        "1                 Guides  \n",
254 |        "2  Technical SEO Library  \n",
255 |        "3                 Guides  \n",
256 |        "4                   Blog  \n",
257 |        "5  Technical SEO Library  \n",
258 |        "6  Technical SEO Library  \n",
259 |        "7  Technical SEO Library  \n",
260 |        "8                 Guides  \n",
261 |        "9  Technical SEO Library  "
262 |       ]
263 |      },
264 |      "execution_count": 7,
265 |      "metadata": {},
266 |      "output_type": "execute_result"
267 |     }
268 |    ],
269 |    "source": [
270 |     "#read first 10 rows\n",
271 |     "df.head(10)"
272 |    ]
273 |   },
274 |   {
275 |    "cell_type": "code",
276 |    "execution_count": 8,
277 |    "metadata": {},
278 |    "outputs": [],
279 |    "source": [
280 |     "#set up segments \n",
281 |     "segment_definitions = [\n",
282 |     "    [(r'\\/blog\\/'), 'Blog'],\n",
283 |     "    [(r'\\/technical-seo-library\\/'), 'Technical SEO Library'],\n",
284 |     "    [(r'\\/hangout-library\\/'), 'Hangout Library'],\n",
285 |     "    [(r'\\/guides\\/'), 'Guides'],\n",
286 |     "    [(r'\\/case-studies\\/'), 'Case Studies'],\n",
287 |     "    [(r'\\/why-'), 'Solutions'],\n",
288 |     "    ]\n",
289 |     "\n",
290 |     "use_segment_definitions = True\n",
291 |     "\n",
292 |     "def get_segment(url):\n",
293 |     "    \n",
294 |     "    if use_segment_definitions == True:\n",
295 |     "        for segment_definition in segment_definitions:\n",
296 |     "            if re.findall(segment_definition[0], url):\n",
297 |     "                return segment_definition[1]\n",
298 |     "        return 'Other'\n",
299 |     "\n",
300 |     "#apply segmentation to all URLs in dataframe \n",
301 |     "df['segment'] = df['url'].apply(lambda x: get_segment(x))"
302 |    ]
303 |   },
304 |   {
305 |    "cell_type": "code",
306 |    "execution_count": 10,
307 |    "metadata": {},
308 |    "outputs": [
309 |     {
310 |      "data": {
311 |       "text/html": [
312 |        "<div>\n",
313 |        "<style scoped>\n",
314 |        "    .dataframe tbody tr th:only-of-type {\n",
315 |        "        vertical-align: middle;\n",
316 |        "    }\n",
317 |        "\n",
318 |        "    .dataframe tbody tr th {\n",
319 |        "        vertical-align: top;\n",
320 |        "    }\n",
321 |        "\n",
322 |        "    .dataframe thead th {\n",
323 |        "        text-align: right;\n",
324 |        "    }\n",
325 |        "</style>\n",
326 |        "<table border=\"1\" class=\"dataframe\">\n",
327 |        "  <thead>\n",
328 |        "    <tr style=\"text-align: right;\">\n",
329 |        "      <th></th>\n",
330 |        "      <th>followed_links_in_count</th>\n",
331 |        "      <th>links_in_count</th>\n",
332 |        "      <th>links_out_count</th>\n",
333 |        "      <th>url</th>\n",
334 |        "    </tr>\n",
335 |        "    <tr>\n",
336 |        "      <th>segment</th>\n",
337 |        "      <th></th>\n",
338 |        "      <th></th>\n",
339 |        "      <th></th>\n",
340 |        "      <th></th>\n",
341 |        "    </tr>\n",
342 |        "  </thead>\n",
343 |        "  <tbody>\n",
344 |        "    <tr>\n",
345 |        "      <th>Blog</th>\n",
346 |        "      <td>19742</td>\n",
347 |        "      <td>19742</td>\n",
348 |        "      <td>77002</td>\n",
349 |        "      <td>737</td>\n",
350 |        "    </tr>\n",
351 |        "    <tr>\n",
352 |        "      <th>Case Studies</th>\n",
353 |        "      <td>117</td>\n",
354 |        "      <td>117</td>\n",
355 |        "      <td>924</td>\n",
356 |        "      <td>10</td>\n",
357 |        "    </tr>\n",
358 |        "    <tr>\n",
359 |        "      <th>Guides</th>\n",
360 |        "      <td>4127</td>\n",
361 |        "      <td>4127</td>\n",
362 |        "      <td>4967</td>\n",
363 |        "      <td>67</td>\n",
364 |        "    </tr>\n",
365 |        "    <tr>\n",
366 |        "      <th>Hangout Library</th>\n",
367 |        "      <td>8019</td>\n",
368 |        "      <td>8019</td>\n",
369 |        "      <td>45261</td>\n",
370 |        "      <td>406</td>\n",
371 |        "    </tr>\n",
372 |        "    <tr>\n",
373 |        "      <th>Other</th>\n",
374 |        "      <td>37050</td>\n",
375 |        "      <td>37050</td>\n",
376 |        "      <td>5498</td>\n",
377 |        "      <td>88</td>\n",
378 |        "    </tr>\n",
379 |        "    <tr>\n",
380 |        "      <th>Solutions</th>\n",
381 |        "      <td>5143</td>\n",
382 |        "      <td>5143</td>\n",
383 |        "      <td>392</td>\n",
384 |        "      <td>6</td>\n",
385 |        "    </tr>\n",
386 |        "    <tr>\n",
387 |        "      <th>Technical SEO Library</th>\n",
388 |        "      <td>2699</td>\n",
389 |        "      <td>2699</td>\n",
390 |        "      <td>2924</td>\n",
391 |        "      <td>33</td>\n",
392 |        "    </tr>\n",
393 |        "  </tbody>\n",
394 |        "</table>\n",
395 |        "</div>"
396 |       ],
397 |       "text/plain": [
398 |        "                       followed_links_in_count  links_in_count  \\\n",
399 |        "segment                                                          \n",
400 |        "Blog                                     19742           19742   \n",
401 |        "Case Studies                               117             117   \n",
402 |        "Guides                                    4127            4127   \n",
403 |        "Hangout Library                           8019            8019   \n",
404 |        "Other                                    37050           37050   \n",
405 |        "Solutions                                 5143            5143   \n",
406 |        "Technical SEO Library                     2699            2699   \n",
407 |        "\n",
408 |        "                       links_out_count  url  \n",
409 |        "segment                                      \n",
410 |        "Blog                             77002  737  \n",
411 |        "Case Studies                       924   10  \n",
412 |        "Guides                            4967   67  \n",
413 |        "Hangout Library                  45261  406  \n",
414 |        "Other                             5498   88  \n",
415 |        "Solutions                          392    6  \n",
416 |        "Technical SEO Library             2924   33  "
417 |       ]
418 |      },
419 |      "execution_count": 10,
420 |      "metadata": {},
421 |      "output_type": "execute_result"
422 |     }
423 |    ],
424 |    "source": [
425 |     "#create pivot table to get a count of internal links to each segment \n",
426 |     "total_internal_links = pd.pivot_table(df, index='segment', values=['url', 'links_in_count', 'followed_links_in_count', 'links_out_count'], aggfunc={'url':len, 'links_in_count':np.sum, 'followed_links_in_count':np.sum, 'links_out_count':np.sum})\n",
427 |     "total_internal_links"
428 |    ]
429 |   },
430 |   {
431 |    "cell_type": "code",
432 |    "execution_count": 15,
433 |    "metadata": {},
434 |    "outputs": [
435 |     {
436 |      "data": {
437 |       "text/html": [
438 |        "<div>\n",
439 |        "<style scoped>\n",
440 |        "    .dataframe tbody tr th:only-of-type {\n",
441 |        "        vertical-align: middle;\n",
442 |        "    }\n",
443 |        "\n",
444 |        "    .dataframe tbody tr th {\n",
445 |        "        vertical-align: top;\n",
446 |        "    }\n",
447 |        "\n",
448 |        "    .dataframe thead th {\n",
449 |        "        text-align: right;\n",
450 |        "    }\n",
451 |        "</style>\n",
452 |        "<table border=\"1\" class=\"dataframe\">\n",
453 |        "  <thead>\n",
454 |        "    <tr style=\"text-align: right;\">\n",
455 |        "      <th></th>\n",
456 |        "      <th>followed_links_in_count</th>\n",
457 |        "      <th>links_in_count</th>\n",
458 |        "      <th>links_out_count</th>\n",
459 |        "      <th>url</th>\n",
460 |        "    </tr>\n",
461 |        "    <tr>\n",
462 |        "      <th>segment</th>\n",
463 |        "      <th></th>\n",
464 |        "      <th></th>\n",
465 |        "      <th></th>\n",
466 |        "      <th></th>\n",
467 |        "    </tr>\n",
468 |        "  </thead>\n",
469 |        "  <tbody>\n",
470 |        "    <tr>\n",
471 |        "      <th>Blog</th>\n",
472 |        "      <td>26.8</td>\n",
473 |        "      <td>26.8</td>\n",
474 |        "      <td>104.5</td>\n",
475 |        "      <td>737</td>\n",
476 |        "    </tr>\n",
477 |        "    <tr>\n",
478 |        "      <th>Case Studies</th>\n",
479 |        "      <td>11.7</td>\n",
480 |        "      <td>11.7</td>\n",
481 |        "      <td>92.4</td>\n",
482 |        "      <td>10</td>\n",
483 |        "    </tr>\n",
484 |        "    <tr>\n",
485 |        "      <th>Guides</th>\n",
486 |        "      <td>61.6</td>\n",
487 |        "      <td>61.6</td>\n",
488 |        "      <td>74.1</td>\n",
489 |        "      <td>67</td>\n",
490 |        "    </tr>\n",
491 |        "    <tr>\n",
492 |        "      <th>Hangout Library</th>\n",
493 |        "      <td>19.8</td>\n",
494 |        "      <td>19.8</td>\n",
495 |        "      <td>111.5</td>\n",
496 |        "      <td>406</td>\n",
497 |        "    </tr>\n",
498 |        "    <tr>\n",
499 |        "      <th>Other</th>\n",
500 |        "      <td>421.0</td>\n",
501 |        "      <td>421.0</td>\n",
502 |        "      <td>62.5</td>\n",
503 |        "      <td>88</td>\n",
504 |        "    </tr>\n",
505 |        "    <tr>\n",
506 |        "      <th>Solutions</th>\n",
507 |        "      <td>857.2</td>\n",
508 |        "      <td>857.2</td>\n",
509 |        "      <td>65.3</td>\n",
510 |        "      <td>6</td>\n",
511 |        "    </tr>\n",
512 |        "    <tr>\n",
513 |        "      <th>Technical SEO Library</th>\n",
514 |        "      <td>81.8</td>\n",
515 |        "      <td>81.8</td>\n",
516 |        "      <td>88.6</td>\n",
517 |        "      <td>33</td>\n",
518 |        "    </tr>\n",
519 |        "  </tbody>\n",
520 |        "</table>\n",
521 |        "</div>"
522 |       ],
523 |       "text/plain": [
524 |        "                      followed_links_in_count links_in_count links_out_count  \\\n",
525 |        "segment                                                                        \n",
526 |        "Blog                                     26.8           26.8           104.5   \n",
527 |        "Case Studies                             11.7           11.7            92.4   \n",
528 |        "Guides                                   61.6           61.6            74.1   \n",
529 |        "Hangout Library                          19.8           19.8           111.5   \n",
530 |        "Other                                   421.0          421.0            62.5   \n",
531 |        "Solutions                               857.2          857.2            65.3   \n",
532 |        "Technical SEO Library                    81.8           81.8            88.6   \n",
533 |        "\n",
534 |        "                       url  \n",
535 |        "segment                     \n",
536 |        "Blog                   737  \n",
537 |        "Case Studies            10  \n",
538 |        "Guides                  67  \n",
539 |        "Hangout Library        406  \n",
540 |        "Other                   88  \n",
541 |        "Solutions                6  \n",
542 |        "Technical SEO Library   33  "
543 |       ]
544 |      },
545 |      "execution_count": 15,
546 |      "metadata": {},
547 |      "output_type": "execute_result"
548 |     }
549 |    ],
550 |    "source": [
551 |     "#create pivot table to get an of internal links to each segment \n",
552 |     "average_internal_links = pd.pivot_table(df, index='segment', values=['url', 'links_in_count', 'followed_links_in_count', 'links_out_count'], aggfunc={'url':len, 'links_in_count':np.mean, 'followed_links_in_count':np.mean, 'links_out_count':np.mean})\n",
553 |     "average_internal_links['followed_links_in_count'] = (average_internal_links['followed_links_in_count']).apply('{:.1f}'.format)\n",
554 |     "average_internal_links['links_in_count'] = (average_internal_links['links_in_count']).apply('{:.1f}'.format)\n",
555 |     "average_internal_links['links_out_count'] = (average_internal_links['links_out_count']).apply('{:.1f}'.format)\n",
556 |     "average_internal_links"
557 |    ]
558 |   },
559 |   {
560 |    "cell_type": "code",
561 |    "execution_count": 17,
562 |    "metadata": {},
563 |    "outputs": [
564 |     {
565 |      "data": {
566 |       "text/html": [
567 |        "<div>\n",
568 |        "<style scoped>\n",
569 |        "    .dataframe tbody tr th:only-of-type {\n",
570 |        "        vertical-align: middle;\n",
571 |        "    }\n",
572 |        "\n",
573 |        "    .dataframe tbody tr th {\n",
574 |        "        vertical-align: top;\n",
575 |        "    }\n",
576 |        "\n",
577 |        "    .dataframe thead th {\n",
578 |        "        text-align: right;\n",
579 |        "    }\n",
580 |        "</style>\n",
581 |        "<table border=\"1\" class=\"dataframe\">\n",
582 |        "  <thead>\n",
583 |        "    <tr style=\"text-align: right;\">\n",
584 |        "      <th></th>\n",
585 |        "      <th>deeprank</th>\n",
586 |        "      <th>followed_links_in_count</th>\n",
587 |        "      <th>level</th>\n",
588 |        "      <th>links_in_count</th>\n",
589 |        "      <th>links_out_count</th>\n",
590 |        "      <th>url</th>\n",
591 |        "    </tr>\n",
592 |        "    <tr>\n",
593 |        "      <th>segment</th>\n",
594 |        "      <th></th>\n",
595 |        "      <th></th>\n",
596 |        "      <th></th>\n",
597 |        "      <th></th>\n",
598 |        "      <th></th>\n",
599 |        "      <th></th>\n",
600 |        "    </tr>\n",
601 |        "  </thead>\n",
602 |        "  <tbody>\n",
603 |        "    <tr>\n",
604 |        "      <th>Blog</th>\n",
605 |        "      <td>1.7</td>\n",
606 |        "      <td>26.8</td>\n",
607 |        "      <td>4.9</td>\n",
608 |        "      <td>26.8</td>\n",
609 |        "      <td>104.5</td>\n",
610 |        "      <td>737</td>\n",
611 |        "    </tr>\n",
612 |        "    <tr>\n",
613 |        "      <th>Case Studies</th>\n",
614 |        "      <td>3.9</td>\n",
615 |        "      <td>11.7</td>\n",
616 |        "      <td>2.2</td>\n",
617 |        "      <td>11.7</td>\n",
618 |        "      <td>92.4</td>\n",
619 |        "      <td>10</td>\n",
620 |        "    </tr>\n",
621 |        "    <tr>\n",
622 |        "      <th>Guides</th>\n",
623 |        "      <td>1.8</td>\n",
624 |        "      <td>61.6</td>\n",
625 |        "      <td>3.8</td>\n",
626 |        "      <td>61.6</td>\n",
627 |        "      <td>74.1</td>\n",
628 |        "      <td>67</td>\n",
629 |        "    </tr>\n",
630 |        "    <tr>\n",
631 |        "      <th>Hangout Library</th>\n",
632 |        "      <td>1.5</td>\n",
633 |        "      <td>19.8</td>\n",
634 |        "      <td>4.6</td>\n",
635 |        "      <td>19.8</td>\n",
636 |        "      <td>111.5</td>\n",
637 |        "      <td>406</td>\n",
638 |        "    </tr>\n",
639 |        "    <tr>\n",
640 |        "      <th>Other</th>\n",
641 |        "      <td>2.9</td>\n",
642 |        "      <td>421.0</td>\n",
643 |        "      <td>3.5</td>\n",
644 |        "      <td>421.0</td>\n",
645 |        "      <td>62.5</td>\n",
646 |        "      <td>88</td>\n",
647 |        "    </tr>\n",
648 |        "    <tr>\n",
649 |        "      <th>Solutions</th>\n",
650 |        "      <td>5.7</td>\n",
651 |        "      <td>857.2</td>\n",
652 |        "      <td>2.8</td>\n",
653 |        "      <td>857.2</td>\n",
654 |        "      <td>65.3</td>\n",
655 |        "      <td>6</td>\n",
656 |        "    </tr>\n",
657 |        "    <tr>\n",
658 |        "      <th>Technical SEO Library</th>\n",
659 |        "      <td>2.3</td>\n",
660 |        "      <td>81.8</td>\n",
661 |        "      <td>3.2</td>\n",
662 |        "      <td>81.8</td>\n",
663 |        "      <td>88.6</td>\n",
664 |        "      <td>33</td>\n",
665 |        "    </tr>\n",
666 |        "  </tbody>\n",
667 |        "</table>\n",
668 |        "</div>"
669 |       ],
670 |       "text/plain": [
671 |        "                      deeprank followed_links_in_count level links_in_count  \\\n",
672 |        "segment                                                                       \n",
673 |        "Blog                       1.7                    26.8   4.9           26.8   \n",
674 |        "Case Studies               3.9                    11.7   2.2           11.7   \n",
675 |        "Guides                     1.8                    61.6   3.8           61.6   \n",
676 |        "Hangout Library            1.5                    19.8   4.6           19.8   \n",
677 |        "Other                      2.9                   421.0   3.5          421.0   \n",
678 |        "Solutions                  5.7                   857.2   2.8          857.2   \n",
679 |        "Technical SEO Library      2.3                    81.8   3.2           81.8   \n",
680 |        "\n",
681 |        "                      links_out_count  url  \n",
682 |        "segment                                     \n",
683 |        "Blog                            104.5  737  \n",
684 |        "Case Studies                     92.4   10  \n",
685 |        "Guides                           74.1   67  \n",
686 |        "Hangout Library                 111.5  406  \n",
687 |        "Other                            62.5   88  \n",
688 |        "Solutions                        65.3    6  \n",
689 |        "Technical SEO Library            88.6   33  "
690 |       ]
691 |      },
692 |      "execution_count": 17,
693 |      "metadata": {},
694 |      "output_type": "execute_result"
695 |     }
696 |    ],
697 |    "source": [
698 |     "#Additional step using Level and DeepRank to find averages for segments \n",
699 |     "averages = pd.pivot_table(df, index='segment', values=['url', 'links_in_count', 'followed_links_in_count', 'links_out_count', 'deeprank', 'level'], aggfunc={'url':len, 'links_in_count':np.mean, 'followed_links_in_count':np.mean, 'links_out_count':np.mean, 'deeprank':np.mean, 'level':np.mean })\n",
700 |     "averages['followed_links_in_count'] = (averages['followed_links_in_count']).apply('{:.1f}'.format)\n",
701 |     "averages['links_in_count'] = (averages['links_in_count']).apply('{:.1f}'.format)\n",
702 |     "averages['links_out_count'] = (averages['links_out_count']).apply('{:.1f}'.format)\n",
703 |     "averages['deeprank'] = (averages['deeprank']).apply('{:.1f}'.format)\n",
704 |     "averages['level'] = (averages['level']).apply('{:.1f}'.format)\n",
705 |     "averages"
706 |    ]
707 |   }
708 |  ],
709 |  "metadata": {
710 |   "kernelspec": {
711 |    "display_name": "Python 3",
712 |    "language": "python",
713 |    "name": "python3"
714 |   },
715 |   "language_info": {
716 |    "codemirror_mode": {
717 |     "name": "ipython",
718 |     "version": 3
719 |    },
720 |    "file_extension": ".py",
721 |    "mimetype": "text/x-python",
722 |    "name": "python",
723 |    "nbconvert_exporter": "python",
724 |    "pygments_lexer": "ipython3",
725 |    "version": "3.7.6"
726 |   }
727 |  },
728 |  "nbformat": 4,
729 |  "nbformat_minor": 4
730 | }
731 | 


--------------------------------------------------------------------------------
/Google_PyTrends.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |   "nbformat": 4,
   3 |   "nbformat_minor": 0,
   4 |   "metadata": {
   5 |     "colab": {
   6 |       "name": "Google PyTrends.ipynb",
   7 |       "provenance": [],
   8 |       "authorship_tag": "ABX9TyMGgzeL+4WEsGTAZ02tWGnt",
   9 |       "include_colab_link": true
  10 |     },
  11 |     "kernelspec": {
  12 |       "name": "python3",
  13 |       "display_name": "Python 3"
  14 |     }
  15 |   },
  16 |   "cells": [
  17 |     {
  18 |       "cell_type": "markdown",
  19 |       "metadata": {
  20 |         "id": "view-in-github",
  21 |         "colab_type": "text"
  22 |       },
  23 |       "source": [
  24 |         "<a href=\"https://colab.research.google.com/github/rvth/python-for-seo/blob/main/Google_PyTrends.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
  25 |       ]
  26 |     },
  27 |     {
  28 |       "cell_type": "code",
  29 |       "metadata": {
  30 |         "id": "fSO8-J6LwFJe",
  31 |         "colab": {
  32 |           "base_uri": "https://localhost:8080/",
  33 |           "height": 221
  34 |         },
  35 |         "outputId": "455f1e60-9d31-4d56-d3f1-8aab75ade8b7"
  36 |       },
  37 |       "source": [
  38 |         "!pip install pytrends\n",
  39 |         "from pytrends.request import TrendReq\n",
  40 |         "pytrends = TrendReq()\n",
  41 |         "import pandas as pd                       \n",
  42 |         "import time\n",
  43 |         "import datetime\n",
  44 |         "from datetime import datetime, date, time"
  45 |       ],
  46 |       "execution_count": null,
  47 |       "outputs": [
  48 |         {
  49 |           "output_type": "stream",
  50 |           "text": [
  51 |             "Requirement already satisfied: pytrends in /usr/local/lib/python3.6/dist-packages (4.7.3)\n",
  52 |             "Requirement already satisfied: requests in /usr/local/lib/python3.6/dist-packages (from pytrends) (2.23.0)\n",
  53 |             "Requirement already satisfied: lxml in /usr/local/lib/python3.6/dist-packages (from pytrends) (4.2.6)\n",
  54 |             "Requirement already satisfied: pandas>=0.25 in /usr/local/lib/python3.6/dist-packages (from pytrends) (1.0.5)\n",
  55 |             "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests->pytrends) (1.24.3)\n",
  56 |             "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests->pytrends) (2020.6.20)\n",
  57 |             "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests->pytrends) (3.0.4)\n",
  58 |             "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests->pytrends) (2.10)\n",
  59 |             "Requirement already satisfied: python-dateutil>=2.6.1 in /usr/local/lib/python3.6/dist-packages (from pandas>=0.25->pytrends) (2.8.1)\n",
  60 |             "Requirement already satisfied: numpy>=1.13.3 in /usr/local/lib/python3.6/dist-packages (from pandas>=0.25->pytrends) (1.18.5)\n",
  61 |             "Requirement already satisfied: pytz>=2017.2 in /usr/local/lib/python3.6/dist-packages (from pandas>=0.25->pytrends) (2018.9)\n",
  62 |             "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.6/dist-packages (from python-dateutil>=2.6.1->pandas>=0.25->pytrends) (1.15.0)\n"
  63 |           ],
  64 |           "name": "stdout"
  65 |         }
  66 |       ]
  67 |     },
  68 |     {
  69 |       "cell_type": "markdown",
  70 |       "metadata": {
  71 |         "id": "9L4sqRuxwWsr"
  72 |       },
  73 |       "source": [
  74 |         "Interest over Time\n"
  75 |       ]
  76 |     },
  77 |     {
  78 |       "cell_type": "code",
  79 |       "metadata": {
  80 |         "id": "PHapqWBUwMUp",
  81 |         "colab": {
  82 |           "base_uri": "https://localhost:8080/",
  83 |           "height": 450
  84 |         },
  85 |         "outputId": "aab7786f-c01b-401b-e58d-a0fde6c53922"
  86 |       },
  87 |       "source": [
  88 |         "kw_list = [\"labrador\", \"german shepherd\", \"staffordshire bull terrier\", \"rottweiler\", \"husky\"]\n",
  89 |         "pytrends.build_payload(kw_list, timeframe='today 3-m')\n",
  90 |         "over_time = pytrends.interest_over_time()\n",
  91 |         "over_time_df = pd.DataFrame(over_time)\n",
  92 |         "over_time_df.drop(columns= 'isPartial') "
  93 |       ],
  94 |       "execution_count": null,
  95 |       "outputs": [
  96 |         {
  97 |           "output_type": "execute_result",
  98 |           "data": {
  99 |             "text/html": [
 100 |               "<div>\n",
 101 |               "<style scoped>\n",
 102 |               "    .dataframe tbody tr th:only-of-type {\n",
 103 |               "        vertical-align: middle;\n",
 104 |               "    }\n",
 105 |               "\n",
 106 |               "    .dataframe tbody tr th {\n",
 107 |               "        vertical-align: top;\n",
 108 |               "    }\n",
 109 |               "\n",
 110 |               "    .dataframe thead th {\n",
 111 |               "        text-align: right;\n",
 112 |               "    }\n",
 113 |               "</style>\n",
 114 |               "<table border=\"1\" class=\"dataframe\">\n",
 115 |               "  <thead>\n",
 116 |               "    <tr style=\"text-align: right;\">\n",
 117 |               "      <th></th>\n",
 118 |               "      <th>labrador</th>\n",
 119 |               "      <th>german shepherd</th>\n",
 120 |               "      <th>staffordshire bull terrier</th>\n",
 121 |               "      <th>rottweiler</th>\n",
 122 |               "      <th>husky</th>\n",
 123 |               "    </tr>\n",
 124 |               "    <tr>\n",
 125 |               "      <th>date</th>\n",
 126 |               "      <th></th>\n",
 127 |               "      <th></th>\n",
 128 |               "      <th></th>\n",
 129 |               "      <th></th>\n",
 130 |               "      <th></th>\n",
 131 |               "    </tr>\n",
 132 |               "  </thead>\n",
 133 |               "  <tbody>\n",
 134 |               "    <tr>\n",
 135 |               "      <th>2020-05-05</th>\n",
 136 |               "      <td>67</td>\n",
 137 |               "      <td>48</td>\n",
 138 |               "      <td>3</td>\n",
 139 |               "      <td>38</td>\n",
 140 |               "      <td>75</td>\n",
 141 |               "    </tr>\n",
 142 |               "    <tr>\n",
 143 |               "      <th>2020-05-06</th>\n",
 144 |               "      <td>67</td>\n",
 145 |               "      <td>49</td>\n",
 146 |               "      <td>4</td>\n",
 147 |               "      <td>36</td>\n",
 148 |               "      <td>77</td>\n",
 149 |               "    </tr>\n",
 150 |               "    <tr>\n",
 151 |               "      <th>2020-05-07</th>\n",
 152 |               "      <td>68</td>\n",
 153 |               "      <td>45</td>\n",
 154 |               "      <td>4</td>\n",
 155 |               "      <td>38</td>\n",
 156 |               "      <td>81</td>\n",
 157 |               "    </tr>\n",
 158 |               "    <tr>\n",
 159 |               "      <th>2020-05-08</th>\n",
 160 |               "      <td>70</td>\n",
 161 |               "      <td>46</td>\n",
 162 |               "      <td>5</td>\n",
 163 |               "      <td>38</td>\n",
 164 |               "      <td>82</td>\n",
 165 |               "    </tr>\n",
 166 |               "    <tr>\n",
 167 |               "      <th>2020-05-09</th>\n",
 168 |               "      <td>80</td>\n",
 169 |               "      <td>56</td>\n",
 170 |               "      <td>5</td>\n",
 171 |               "      <td>47</td>\n",
 172 |               "      <td>89</td>\n",
 173 |               "    </tr>\n",
 174 |               "    <tr>\n",
 175 |               "      <th>...</th>\n",
 176 |               "      <td>...</td>\n",
 177 |               "      <td>...</td>\n",
 178 |               "      <td>...</td>\n",
 179 |               "      <td>...</td>\n",
 180 |               "      <td>...</td>\n",
 181 |               "    </tr>\n",
 182 |               "    <tr>\n",
 183 |               "      <th>2020-07-29</th>\n",
 184 |               "      <td>66</td>\n",
 185 |               "      <td>41</td>\n",
 186 |               "      <td>4</td>\n",
 187 |               "      <td>38</td>\n",
 188 |               "      <td>74</td>\n",
 189 |               "    </tr>\n",
 190 |               "    <tr>\n",
 191 |               "      <th>2020-07-30</th>\n",
 192 |               "      <td>62</td>\n",
 193 |               "      <td>43</td>\n",
 194 |               "      <td>4</td>\n",
 195 |               "      <td>36</td>\n",
 196 |               "      <td>73</td>\n",
 197 |               "    </tr>\n",
 198 |               "    <tr>\n",
 199 |               "      <th>2020-07-31</th>\n",
 200 |               "      <td>63</td>\n",
 201 |               "      <td>45</td>\n",
 202 |               "      <td>4</td>\n",
 203 |               "      <td>39</td>\n",
 204 |               "      <td>75</td>\n",
 205 |               "    </tr>\n",
 206 |               "    <tr>\n",
 207 |               "      <th>2020-08-01</th>\n",
 208 |               "      <td>80</td>\n",
 209 |               "      <td>49</td>\n",
 210 |               "      <td>4</td>\n",
 211 |               "      <td>46</td>\n",
 212 |               "      <td>87</td>\n",
 213 |               "    </tr>\n",
 214 |               "    <tr>\n",
 215 |               "      <th>2020-08-02</th>\n",
 216 |               "      <td>85</td>\n",
 217 |               "      <td>50</td>\n",
 218 |               "      <td>4</td>\n",
 219 |               "      <td>51</td>\n",
 220 |               "      <td>91</td>\n",
 221 |               "    </tr>\n",
 222 |               "  </tbody>\n",
 223 |               "</table>\n",
 224 |               "<p>90 rows × 5 columns</p>\n",
 225 |               "</div>"
 226 |             ],
 227 |             "text/plain": [
 228 |               "            labrador  german shepherd  ...  rottweiler  husky\n",
 229 |               "date                                   ...                   \n",
 230 |               "2020-05-05        67               48  ...          38     75\n",
 231 |               "2020-05-06        67               49  ...          36     77\n",
 232 |               "2020-05-07        68               45  ...          38     81\n",
 233 |               "2020-05-08        70               46  ...          38     82\n",
 234 |               "2020-05-09        80               56  ...          47     89\n",
 235 |               "...              ...              ...  ...         ...    ...\n",
 236 |               "2020-07-29        66               41  ...          38     74\n",
 237 |               "2020-07-30        62               43  ...          36     73\n",
 238 |               "2020-07-31        63               45  ...          39     75\n",
 239 |               "2020-08-01        80               49  ...          46     87\n",
 240 |               "2020-08-02        85               50  ...          51     91\n",
 241 |               "\n",
 242 |               "[90 rows x 5 columns]"
 243 |             ]
 244 |           },
 245 |           "metadata": {
 246 |             "tags": []
 247 |           },
 248 |           "execution_count": 2
 249 |         }
 250 |       ]
 251 |     },
 252 |     {
 253 |       "cell_type": "markdown",
 254 |       "metadata": {
 255 |         "id": "b2nZpHS11rfr"
 256 |       },
 257 |       "source": [
 258 |         "Related Queries"
 259 |       ]
 260 |     },
 261 |     {
 262 |       "cell_type": "code",
 263 |       "metadata": {
 264 |         "id": "Cr1Hvyc83oUT"
 265 |       },
 266 |       "source": [
 267 |         "kw_list=['giant panda', 'tiger', 'polar bear', 'penguin']\n",
 268 |         "pytrends.build_payload(kw_list, timeframe='today 3-m')"
 269 |       ],
 270 |       "execution_count": null,
 271 |       "outputs": []
 272 |     },
 273 |     {
 274 |       "cell_type": "code",
 275 |       "metadata": {
 276 |         "id": "-TYnwuM-0tX4",
 277 |         "colab": {
 278 |           "base_uri": "https://localhost:8080/",
 279 |           "height": 1000
 280 |         },
 281 |         "outputId": "f49741fd-a69b-4d10-cf2f-3d179b3564b2"
 282 |       },
 283 |       "source": [
 284 |         "related_queries = pytrends.related_queries()\n",
 285 |         "related_queries.values()"
 286 |       ],
 287 |       "execution_count": null,
 288 |       "outputs": [
 289 |         {
 290 |           "output_type": "execute_result",
 291 |           "data": {
 292 |             "text/plain": [
 293 |               "dict_values([{'top':                          query  value\n",
 294 |               "0              the giant panda    100\n",
 295 |               "1               giant panda 3d     85\n",
 296 |               "2                        tiger     55\n",
 297 |               "3            giant panda facts     27\n",
 298 |               "4                    red panda     25\n",
 299 |               "5                   3d animals     25\n",
 300 |               "6                     tiger 3d     25\n",
 301 |               "7                        shark     23\n",
 302 |               "8                         lion     23\n",
 303 |               "9          giant panda habitat     23\n",
 304 |               "10                        duck     15\n",
 305 |               "11                   alligator     13\n",
 306 |               "12           google 3d animals     10\n",
 307 |               "13          endangered species      8\n",
 308 |               "14  giant panda facts for kids      5\n",
 309 |               "15           giant panda fargo      3, 'rising':                         query  value\n",
 310 |               "0  giant panda facts for kids    250\n",
 311 |               "1         giant panda habitat     50\n",
 312 |               "2             the giant panda     40}, {'top':                         query  value\n",
 313 |               "0                   the tiger    100\n",
 314 |               "1                 tiger woods     74\n",
 315 |               "2                  tiger king     68\n",
 316 |               "3                tiger shroff     40\n",
 317 |               "4                 giant tiger     28\n",
 318 |               "5                 tiger movie     23\n",
 319 |               "6                        lion     20\n",
 320 |               "7                   tiger eye     19\n",
 321 |               "8                 white tiger     16\n",
 322 |               "9                tiger flying     16\n",
 323 |               "10                 tiger phil     15\n",
 324 |               "11              tiger triumph     14\n",
 325 |               "12                    triumph     13\n",
 326 |               "13                   3d tiger     13\n",
 327 |               "14                black tiger     12\n",
 328 |               "15           eye of the tiger     12\n",
 329 |               "16             tiger onitsuka     12\n",
 330 |               "17                      shark     11\n",
 331 |               "18                tiger shark     10\n",
 332 |               "19               daniel tiger     10\n",
 333 |               "20                        cat     10\n",
 334 |               "21                  tiger cat     10\n",
 335 |               "22                tiger video     10\n",
 336 |               "23                  tiger 800      9\n",
 337 |               "24  romance of tiger and rose      9, 'rising':                                       query  value\n",
 338 |               "0           tiger woods peyton manning date  22550\n",
 339 |               "1                 romance of tiger and rose  16400\n",
 340 |               "2             the romance of tiger and rose  15100\n",
 341 |               "3   the romance of tiger and rose dramacool   7150\n",
 342 |               "4              tiger phil peyton brady date   5950\n",
 343 |               "5              tiger king challenge bitlife   4500\n",
 344 |               "6                tiger phil match 2020 date   3450\n",
 345 |               "7                  tiger vs phil match 2020   3350\n",
 346 |               "8                       memorial tournament   2750\n",
 347 |               "9                          tiger phil match   2250\n",
 348 |               "10                               tiger luxx   2050\n",
 349 |               "11                            tiger vs phil   1850\n",
 350 |               "12                     tiger and phil match   1750\n",
 351 |               "13    the romance of tiger and rose ซับ ไทย   1550\n",
 352 |               "14                  international tiger day   1400\n",
 353 |               "15                               tiger phil   1200\n",
 354 |               "16               how to watch tiger vs phil   1150\n",
 355 |               "17             international tiger day 2020   1150\n",
 356 |               "18               tiger woods phil mickelson   1000\n",
 357 |               "19                           phil mickelson    950\n",
 358 |               "20                  nicolas cage tiger king    650\n",
 359 |               "21                           flying tiger 2    600\n",
 360 |               "22                            tiger brokers    550\n",
 361 |               "23              roy horn tiger attack video    500\n",
 362 |               "24                             tiger muskie    450}, {'top':                                  query  value\n",
 363 |               "0                       the polar bear    100\n",
 364 |               "1                          polar bears     51\n",
 365 |               "2                                bears     49\n",
 366 |               "3                 minecraft polar bear     31\n",
 367 |               "4                         grizzly bear     30\n",
 368 |               "5                     white polar bear     22\n",
 369 |               "6                      polar bear baby     20\n",
 370 |               "7                 coca cola polar bear     19\n",
 371 |               "8                           black bear     19\n",
 372 |               "9                                panda     17\n",
 373 |               "10                      polar bear dog     17\n",
 374 |               "11                               tiger     16\n",
 375 |               "12                     polar bear skin     16\n",
 376 |               "13                          brown bear     14\n",
 377 |               "14  coca cola polar bear playing cards     14\n",
 378 |               "15                    polar bear facts     14\n",
 379 |               "16               polar bear population     13\n",
 380 |               "17                  polar bear habitat     13\n",
 381 |               "18                     polar bear size     12\n",
 382 |               "19           tame polar bear minecraft     12\n",
 383 |               "20                                lion     12\n",
 384 |               "21                      polar bear fur     12\n",
 385 |               "22                  polar bear coolers     12\n",
 386 |               "23                     polar bear shot     11\n",
 387 |               "24              polar bear adaptations     10, 'rising':                                        query   value\n",
 388 |               "0         coca cola polar bear playing cards  149100\n",
 389 |               "1                           polar bear leura   11650\n",
 390 |               "2                           hyped polar bear    5650\n",
 391 |               "3                       polar bear 45 cooler    4100\n",
 392 |               "4                       coca cola polar bear     450\n",
 393 |               "5                         polar bear coolers     350\n",
 394 |               "6                         bonjour polar bear     350\n",
 395 |               "7                          polar bear cooler     250\n",
 396 |               "8                            polar bear hull     250\n",
 397 |               "9                 polar bear provincial park     190\n",
 398 |               "10                       adopt me polar bear     180\n",
 399 |               "11                polar bear heating and air     180\n",
 400 |               "12                      hortensja polar bear     170\n",
 401 |               "13                         shaved polar bear     170\n",
 402 |               "14                 polar bear stuffed animal     150\n",
 403 |               "15     how much does a polar bear weigh joke     120\n",
 404 |               "16  do you know how much a polar bear weighs     120\n",
 405 |               "17                     polar bear skin color     120\n",
 406 |               "18                            polar bear toy     110\n",
 407 |               "19                           polar bear roar     110\n",
 408 |               "20                wolverine kills polar bear     110\n",
 409 |               "21                       the polar bear king      70\n",
 410 |               "22                    polar bear skin colour      70\n",
 411 |               "23                polar bear size comparison      60\n",
 412 |               "24                       maya the polar bear      60}, {'top':                            query  value\n",
 413 |               "0                   penguin club    100\n",
 414 |               "1                           club     99\n",
 415 |               "2                  penguin movie     30\n",
 416 |               "3                    the penguin     25\n",
 417 |               "4         club penguin rewritten     11\n",
 418 |               "5            club penguin online      8\n",
 419 |               "6            penguin tamil movie      8\n",
 420 |               "7                   penguin 2020      7\n",
 421 |               "8             super club penguin      7\n",
 422 |               "9                       penguins      5\n",
 423 |               "10                batman penguin      5\n",
 424 |               "11                  baby penguin      5\n",
 425 |               "12               emperor penguin      5\n",
 426 |               "13                penguin review      5\n",
 427 |               "14                google penguin      4\n",
 428 |               "15                 penguin books      4\n",
 429 |               "16        penguin movie download      4\n",
 430 |               "17                  penguin game      4\n",
 431 |               "18                  free penguin      3\n",
 432 |               "19          penguin movie review      3\n",
 433 |               "20          penguin random house      3\n",
 434 |               "21              original penguin      3\n",
 435 |               "22  penguin tamil movie download      3\n",
 436 |               "23              penguin classics      3\n",
 437 |               "24                penguin island      3, 'rising':                                      query  value\n",
 438 |               "0             penguin tamil movie download  92100\n",
 439 |               "1                     penguin movie telugu  62450\n",
 440 |               "2          penguin movie download in tamil  47800\n",
 441 |               "3                             tamilrockers  47000\n",
 442 |               "4                      penguin tamil movie  39750\n",
 443 |               "5               penguin movie amazon prime  29450\n",
 444 |               "6                 penguin tamil full movie  28300\n",
 445 |               "7   penguin movie download in tamilrockers  21500\n",
 446 |               "8                                tamilyogi  21450\n",
 447 |               "9                        tamilyogi penguin  21000\n",
 448 |               "10                    penguin movie rating  19600\n",
 449 |               "11                                moviesda  17400\n",
 450 |               "12                        ponmagal vandhal  14200\n",
 451 |               "13             penguin full movie in tamil  13450\n",
 452 |               "14                penguin tamil movie cast  10650\n",
 453 |               "15                             kuttymovies   9550\n",
 454 |               "16                    penguin movie review   9350\n",
 455 |               "17             penguin tamil movie trailer   8900\n",
 456 |               "18                  penguin movie download   8350\n",
 457 |               "19                           gulabo sitabo   6250\n",
 458 |               "20                     baby penguin cm son   6200\n",
 459 |               "21                                isaimini   5450\n",
 460 |               "22                                tamilgun   4700\n",
 461 |               "23                               movierulz   4050\n",
 462 |               "24                  penguin keerthy suresh   4050}])"
 463 |             ]
 464 |           },
 465 |           "metadata": {
 466 |             "tags": []
 467 |           },
 468 |           "execution_count": 4
 469 |         }
 470 |       ]
 471 |     },
 472 |     {
 473 |       "cell_type": "code",
 474 |       "metadata": {
 475 |         "id": "UZ9glkas0uXS",
 476 |         "colab": {
 477 |           "base_uri": "https://localhost:8080/",
 478 |           "height": 142
 479 |         },
 480 |         "outputId": "92a8c913-b5e3-4439-f789-828a9f297d08"
 481 |       },
 482 |       "source": [
 483 |         "related_queries.get('giant panda').get('rising')"
 484 |       ],
 485 |       "execution_count": null,
 486 |       "outputs": [
 487 |         {
 488 |           "output_type": "execute_result",
 489 |           "data": {
 490 |             "text/html": [
 491 |               "<div>\n",
 492 |               "<style scoped>\n",
 493 |               "    .dataframe tbody tr th:only-of-type {\n",
 494 |               "        vertical-align: middle;\n",
 495 |               "    }\n",
 496 |               "\n",
 497 |               "    .dataframe tbody tr th {\n",
 498 |               "        vertical-align: top;\n",
 499 |               "    }\n",
 500 |               "\n",
 501 |               "    .dataframe thead th {\n",
 502 |               "        text-align: right;\n",
 503 |               "    }\n",
 504 |               "</style>\n",
 505 |               "<table border=\"1\" class=\"dataframe\">\n",
 506 |               "  <thead>\n",
 507 |               "    <tr style=\"text-align: right;\">\n",
 508 |               "      <th></th>\n",
 509 |               "      <th>query</th>\n",
 510 |               "      <th>value</th>\n",
 511 |               "    </tr>\n",
 512 |               "  </thead>\n",
 513 |               "  <tbody>\n",
 514 |               "    <tr>\n",
 515 |               "      <th>0</th>\n",
 516 |               "      <td>giant panda facts for kids</td>\n",
 517 |               "      <td>250</td>\n",
 518 |               "    </tr>\n",
 519 |               "    <tr>\n",
 520 |               "      <th>1</th>\n",
 521 |               "      <td>giant panda habitat</td>\n",
 522 |               "      <td>50</td>\n",
 523 |               "    </tr>\n",
 524 |               "    <tr>\n",
 525 |               "      <th>2</th>\n",
 526 |               "      <td>the giant panda</td>\n",
 527 |               "      <td>40</td>\n",
 528 |               "    </tr>\n",
 529 |               "  </tbody>\n",
 530 |               "</table>\n",
 531 |               "</div>"
 532 |             ],
 533 |             "text/plain": [
 534 |               "                        query  value\n",
 535 |               "0  giant panda facts for kids    250\n",
 536 |               "1         giant panda habitat     50\n",
 537 |               "2             the giant panda     40"
 538 |             ]
 539 |           },
 540 |           "metadata": {
 541 |             "tags": []
 542 |           },
 543 |           "execution_count": 5
 544 |         }
 545 |       ]
 546 |     },
 547 |     {
 548 |       "cell_type": "code",
 549 |       "metadata": {
 550 |         "id": "qVdQpZ2G03MR",
 551 |         "colab": {
 552 |           "base_uri": "https://localhost:8080/",
 553 |           "height": 824
 554 |         },
 555 |         "outputId": "17e1db83-8b88-4597-f24b-a17e623da461"
 556 |       },
 557 |       "source": [
 558 |         "related_queries.get('tiger').get('top')"
 559 |       ],
 560 |       "execution_count": null,
 561 |       "outputs": [
 562 |         {
 563 |           "output_type": "execute_result",
 564 |           "data": {
 565 |             "text/html": [
 566 |               "<div>\n",
 567 |               "<style scoped>\n",
 568 |               "    .dataframe tbody tr th:only-of-type {\n",
 569 |               "        vertical-align: middle;\n",
 570 |               "    }\n",
 571 |               "\n",
 572 |               "    .dataframe tbody tr th {\n",
 573 |               "        vertical-align: top;\n",
 574 |               "    }\n",
 575 |               "\n",
 576 |               "    .dataframe thead th {\n",
 577 |               "        text-align: right;\n",
 578 |               "    }\n",
 579 |               "</style>\n",
 580 |               "<table border=\"1\" class=\"dataframe\">\n",
 581 |               "  <thead>\n",
 582 |               "    <tr style=\"text-align: right;\">\n",
 583 |               "      <th></th>\n",
 584 |               "      <th>query</th>\n",
 585 |               "      <th>value</th>\n",
 586 |               "    </tr>\n",
 587 |               "  </thead>\n",
 588 |               "  <tbody>\n",
 589 |               "    <tr>\n",
 590 |               "      <th>0</th>\n",
 591 |               "      <td>the tiger</td>\n",
 592 |               "      <td>100</td>\n",
 593 |               "    </tr>\n",
 594 |               "    <tr>\n",
 595 |               "      <th>1</th>\n",
 596 |               "      <td>tiger woods</td>\n",
 597 |               "      <td>74</td>\n",
 598 |               "    </tr>\n",
 599 |               "    <tr>\n",
 600 |               "      <th>2</th>\n",
 601 |               "      <td>tiger king</td>\n",
 602 |               "      <td>68</td>\n",
 603 |               "    </tr>\n",
 604 |               "    <tr>\n",
 605 |               "      <th>3</th>\n",
 606 |               "      <td>tiger shroff</td>\n",
 607 |               "      <td>40</td>\n",
 608 |               "    </tr>\n",
 609 |               "    <tr>\n",
 610 |               "      <th>4</th>\n",
 611 |               "      <td>giant tiger</td>\n",
 612 |               "      <td>28</td>\n",
 613 |               "    </tr>\n",
 614 |               "    <tr>\n",
 615 |               "      <th>5</th>\n",
 616 |               "      <td>tiger movie</td>\n",
 617 |               "      <td>23</td>\n",
 618 |               "    </tr>\n",
 619 |               "    <tr>\n",
 620 |               "      <th>6</th>\n",
 621 |               "      <td>lion</td>\n",
 622 |               "      <td>20</td>\n",
 623 |               "    </tr>\n",
 624 |               "    <tr>\n",
 625 |               "      <th>7</th>\n",
 626 |               "      <td>tiger eye</td>\n",
 627 |               "      <td>19</td>\n",
 628 |               "    </tr>\n",
 629 |               "    <tr>\n",
 630 |               "      <th>8</th>\n",
 631 |               "      <td>white tiger</td>\n",
 632 |               "      <td>16</td>\n",
 633 |               "    </tr>\n",
 634 |               "    <tr>\n",
 635 |               "      <th>9</th>\n",
 636 |               "      <td>tiger flying</td>\n",
 637 |               "      <td>16</td>\n",
 638 |               "    </tr>\n",
 639 |               "    <tr>\n",
 640 |               "      <th>10</th>\n",
 641 |               "      <td>tiger phil</td>\n",
 642 |               "      <td>15</td>\n",
 643 |               "    </tr>\n",
 644 |               "    <tr>\n",
 645 |               "      <th>11</th>\n",
 646 |               "      <td>tiger triumph</td>\n",
 647 |               "      <td>14</td>\n",
 648 |               "    </tr>\n",
 649 |               "    <tr>\n",
 650 |               "      <th>12</th>\n",
 651 |               "      <td>triumph</td>\n",
 652 |               "      <td>13</td>\n",
 653 |               "    </tr>\n",
 654 |               "    <tr>\n",
 655 |               "      <th>13</th>\n",
 656 |               "      <td>3d tiger</td>\n",
 657 |               "      <td>13</td>\n",
 658 |               "    </tr>\n",
 659 |               "    <tr>\n",
 660 |               "      <th>14</th>\n",
 661 |               "      <td>black tiger</td>\n",
 662 |               "      <td>12</td>\n",
 663 |               "    </tr>\n",
 664 |               "    <tr>\n",
 665 |               "      <th>15</th>\n",
 666 |               "      <td>eye of the tiger</td>\n",
 667 |               "      <td>12</td>\n",
 668 |               "    </tr>\n",
 669 |               "    <tr>\n",
 670 |               "      <th>16</th>\n",
 671 |               "      <td>tiger onitsuka</td>\n",
 672 |               "      <td>12</td>\n",
 673 |               "    </tr>\n",
 674 |               "    <tr>\n",
 675 |               "      <th>17</th>\n",
 676 |               "      <td>shark</td>\n",
 677 |               "      <td>11</td>\n",
 678 |               "    </tr>\n",
 679 |               "    <tr>\n",
 680 |               "      <th>18</th>\n",
 681 |               "      <td>tiger shark</td>\n",
 682 |               "      <td>10</td>\n",
 683 |               "    </tr>\n",
 684 |               "    <tr>\n",
 685 |               "      <th>19</th>\n",
 686 |               "      <td>daniel tiger</td>\n",
 687 |               "      <td>10</td>\n",
 688 |               "    </tr>\n",
 689 |               "    <tr>\n",
 690 |               "      <th>20</th>\n",
 691 |               "      <td>cat</td>\n",
 692 |               "      <td>10</td>\n",
 693 |               "    </tr>\n",
 694 |               "    <tr>\n",
 695 |               "      <th>21</th>\n",
 696 |               "      <td>tiger cat</td>\n",
 697 |               "      <td>10</td>\n",
 698 |               "    </tr>\n",
 699 |               "    <tr>\n",
 700 |               "      <th>22</th>\n",
 701 |               "      <td>tiger video</td>\n",
 702 |               "      <td>10</td>\n",
 703 |               "    </tr>\n",
 704 |               "    <tr>\n",
 705 |               "      <th>23</th>\n",
 706 |               "      <td>tiger 800</td>\n",
 707 |               "      <td>9</td>\n",
 708 |               "    </tr>\n",
 709 |               "    <tr>\n",
 710 |               "      <th>24</th>\n",
 711 |               "      <td>romance of tiger and rose</td>\n",
 712 |               "      <td>9</td>\n",
 713 |               "    </tr>\n",
 714 |               "  </tbody>\n",
 715 |               "</table>\n",
 716 |               "</div>"
 717 |             ],
 718 |             "text/plain": [
 719 |               "                        query  value\n",
 720 |               "0                   the tiger    100\n",
 721 |               "1                 tiger woods     74\n",
 722 |               "2                  tiger king     68\n",
 723 |               "3                tiger shroff     40\n",
 724 |               "4                 giant tiger     28\n",
 725 |               "5                 tiger movie     23\n",
 726 |               "6                        lion     20\n",
 727 |               "7                   tiger eye     19\n",
 728 |               "8                 white tiger     16\n",
 729 |               "9                tiger flying     16\n",
 730 |               "10                 tiger phil     15\n",
 731 |               "11              tiger triumph     14\n",
 732 |               "12                    triumph     13\n",
 733 |               "13                   3d tiger     13\n",
 734 |               "14                black tiger     12\n",
 735 |               "15           eye of the tiger     12\n",
 736 |               "16             tiger onitsuka     12\n",
 737 |               "17                      shark     11\n",
 738 |               "18                tiger shark     10\n",
 739 |               "19               daniel tiger     10\n",
 740 |               "20                        cat     10\n",
 741 |               "21                  tiger cat     10\n",
 742 |               "22                tiger video     10\n",
 743 |               "23                  tiger 800      9\n",
 744 |               "24  romance of tiger and rose      9"
 745 |             ]
 746 |           },
 747 |           "metadata": {
 748 |             "tags": []
 749 |           },
 750 |           "execution_count": 6
 751 |         }
 752 |       ]
 753 |     },
 754 |     {
 755 |       "cell_type": "markdown",
 756 |       "metadata": {
 757 |         "id": "RKOMZiyH1t1Z"
 758 |       },
 759 |       "source": [
 760 |         "Suggestions"
 761 |       ]
 762 |     },
 763 |     {
 764 |       "cell_type": "code",
 765 |       "metadata": {
 766 |         "id": "9HDCc7E53w12",
 767 |         "colab": {
 768 |           "base_uri": "https://localhost:8080/",
 769 |           "height": 204
 770 |         },
 771 |         "outputId": "d60a5fe8-bd5f-4bff-f863-af78bb6e02e5"
 772 |       },
 773 |       "source": [
 774 |         "suggestions = pytrends.suggestions(keyword='nintendo switch')\n",
 775 |         "suggestions_df = pd.DataFrame(suggestions)\n",
 776 |         "suggestions_df.drop(columns= 'mid') "
 777 |       ],
 778 |       "execution_count": null,
 779 |       "outputs": [
 780 |         {
 781 |           "output_type": "execute_result",
 782 |           "data": {
 783 |             "text/html": [
 784 |               "<div>\n",
 785 |               "<style scoped>\n",
 786 |               "    .dataframe tbody tr th:only-of-type {\n",
 787 |               "        vertical-align: middle;\n",
 788 |               "    }\n",
 789 |               "\n",
 790 |               "    .dataframe tbody tr th {\n",
 791 |               "        vertical-align: top;\n",
 792 |               "    }\n",
 793 |               "\n",
 794 |               "    .dataframe thead th {\n",
 795 |               "        text-align: right;\n",
 796 |               "    }\n",
 797 |               "</style>\n",
 798 |               "<table border=\"1\" class=\"dataframe\">\n",
 799 |               "  <thead>\n",
 800 |               "    <tr style=\"text-align: right;\">\n",
 801 |               "      <th></th>\n",
 802 |               "      <th>title</th>\n",
 803 |               "      <th>type</th>\n",
 804 |               "    </tr>\n",
 805 |               "  </thead>\n",
 806 |               "  <tbody>\n",
 807 |               "    <tr>\n",
 808 |               "      <th>0</th>\n",
 809 |               "      <td>Nintendo Switch</td>\n",
 810 |               "      <td>Video game console</td>\n",
 811 |               "    </tr>\n",
 812 |               "    <tr>\n",
 813 |               "      <th>1</th>\n",
 814 |               "      <td>Nintendo Switch Online</td>\n",
 815 |               "      <td>Topic</td>\n",
 816 |               "    </tr>\n",
 817 |               "    <tr>\n",
 818 |               "      <th>2</th>\n",
 819 |               "      <td>Joy-Con</td>\n",
 820 |               "      <td>Game controller</td>\n",
 821 |               "    </tr>\n",
 822 |               "    <tr>\n",
 823 |               "      <th>3</th>\n",
 824 |               "      <td>Celeste</td>\n",
 825 |               "      <td>Video game</td>\n",
 826 |               "    </tr>\n",
 827 |               "    <tr>\n",
 828 |               "      <th>4</th>\n",
 829 |               "      <td>Nintendo Switch system software</td>\n",
 830 |               "      <td>Operating system</td>\n",
 831 |               "    </tr>\n",
 832 |               "  </tbody>\n",
 833 |               "</table>\n",
 834 |               "</div>"
 835 |             ],
 836 |             "text/plain": [
 837 |               "                             title                type\n",
 838 |               "0                  Nintendo Switch  Video game console\n",
 839 |               "1           Nintendo Switch Online               Topic\n",
 840 |               "2                          Joy-Con     Game controller\n",
 841 |               "3                          Celeste          Video game\n",
 842 |               "4  Nintendo Switch system software    Operating system"
 843 |             ]
 844 |           },
 845 |           "metadata": {
 846 |             "tags": []
 847 |           },
 848 |           "execution_count": 31
 849 |         }
 850 |       ]
 851 |     },
 852 |     {
 853 |       "cell_type": "markdown",
 854 |       "metadata": {
 855 |         "id": "LRq5Pd8_S8e2"
 856 |       },
 857 |       "source": [
 858 |         "Trending Searches\n"
 859 |       ]
 860 |     },
 861 |     {
 862 |       "cell_type": "code",
 863 |       "metadata": {
 864 |         "id": "_LBLsKO1D0Q_",
 865 |         "colab": {
 866 |           "base_uri": "https://localhost:8080/",
 867 |           "height": 669
 868 |         },
 869 |         "outputId": "9d2fcc9e-633a-4f0d-9282-aa248aeb0d9f"
 870 |       },
 871 |       "source": [
 872 |         "trend = pytrends.trending_searches(pn='united_kingdom')\n",
 873 |         "uk_trend_df = pd.DataFrame(trend)\n",
 874 |         "uk_trend_df"
 875 |       ],
 876 |       "execution_count": null,
 877 |       "outputs": [
 878 |         {
 879 |           "output_type": "execute_result",
 880 |           "data": {
 881 |             "text/html": [
 882 |               "<div>\n",
 883 |               "<style scoped>\n",
 884 |               "    .dataframe tbody tr th:only-of-type {\n",
 885 |               "        vertical-align: middle;\n",
 886 |               "    }\n",
 887 |               "\n",
 888 |               "    .dataframe tbody tr th {\n",
 889 |               "        vertical-align: top;\n",
 890 |               "    }\n",
 891 |               "\n",
 892 |               "    .dataframe thead th {\n",
 893 |               "        text-align: right;\n",
 894 |               "    }\n",
 895 |               "</style>\n",
 896 |               "<table border=\"1\" class=\"dataframe\">\n",
 897 |               "  <thead>\n",
 898 |               "    <tr style=\"text-align: right;\">\n",
 899 |               "      <th></th>\n",
 900 |               "      <th>0</th>\n",
 901 |               "    </tr>\n",
 902 |               "  </thead>\n",
 903 |               "  <tbody>\n",
 904 |               "    <tr>\n",
 905 |               "      <th>0</th>\n",
 906 |               "      <td>COVID-19 prevention</td>\n",
 907 |               "    </tr>\n",
 908 |               "    <tr>\n",
 909 |               "      <th>1</th>\n",
 910 |               "      <td>Aberdeen</td>\n",
 911 |               "    </tr>\n",
 912 |               "    <tr>\n",
 913 |               "      <th>2</th>\n",
 914 |               "      <td>Jamie Dornan</td>\n",
 915 |               "    </tr>\n",
 916 |               "    <tr>\n",
 917 |               "      <th>3</th>\n",
 918 |               "      <td>Gary Barlow</td>\n",
 919 |               "    </tr>\n",
 920 |               "    <tr>\n",
 921 |               "      <th>4</th>\n",
 922 |               "      <td>Angel Gomes</td>\n",
 923 |               "    </tr>\n",
 924 |               "    <tr>\n",
 925 |               "      <th>5</th>\n",
 926 |               "      <td>Football</td>\n",
 927 |               "    </tr>\n",
 928 |               "    <tr>\n",
 929 |               "      <th>6</th>\n",
 930 |               "      <td>Caroline Flack</td>\n",
 931 |               "    </tr>\n",
 932 |               "    <tr>\n",
 933 |               "      <th>7</th>\n",
 934 |               "      <td>FBG Duck</td>\n",
 935 |               "    </tr>\n",
 936 |               "    <tr>\n",
 937 |               "      <th>8</th>\n",
 938 |               "      <td>Jamal Lewis</td>\n",
 939 |               "    </tr>\n",
 940 |               "    <tr>\n",
 941 |               "      <th>9</th>\n",
 942 |               "      <td>BREAKING news</td>\n",
 943 |               "    </tr>\n",
 944 |               "    <tr>\n",
 945 |               "      <th>10</th>\n",
 946 |               "      <td>Hiroshima</td>\n",
 947 |               "    </tr>\n",
 948 |               "    <tr>\n",
 949 |               "      <th>11</th>\n",
 950 |               "      <td>Beirut</td>\n",
 951 |               "    </tr>\n",
 952 |               "    <tr>\n",
 953 |               "      <th>12</th>\n",
 954 |               "      <td>Brentford</td>\n",
 955 |               "    </tr>\n",
 956 |               "    <tr>\n",
 957 |               "      <th>13</th>\n",
 958 |               "      <td>Kemar Roofe</td>\n",
 959 |               "    </tr>\n",
 960 |               "    <tr>\n",
 961 |               "      <th>14</th>\n",
 962 |               "      <td>England vs Ireland</td>\n",
 963 |               "    </tr>\n",
 964 |               "    <tr>\n",
 965 |               "      <th>15</th>\n",
 966 |               "      <td>Virgin Atlantic</td>\n",
 967 |               "    </tr>\n",
 968 |               "    <tr>\n",
 969 |               "      <th>16</th>\n",
 970 |               "      <td>Will Young</td>\n",
 971 |               "    </tr>\n",
 972 |               "    <tr>\n",
 973 |               "      <th>17</th>\n",
 974 |               "      <td>Brian Black</td>\n",
 975 |               "    </tr>\n",
 976 |               "    <tr>\n",
 977 |               "      <th>18</th>\n",
 978 |               "      <td>Fall Guys</td>\n",
 979 |               "    </tr>\n",
 980 |               "    <tr>\n",
 981 |               "      <th>19</th>\n",
 982 |               "      <td>Jonathan Swan</td>\n",
 983 |               "    </tr>\n",
 984 |               "  </tbody>\n",
 985 |               "</table>\n",
 986 |               "</div>"
 987 |             ],
 988 |             "text/plain": [
 989 |               "                      0\n",
 990 |               "0   COVID-19 prevention\n",
 991 |               "1              Aberdeen\n",
 992 |               "2          Jamie Dornan\n",
 993 |               "3           Gary Barlow\n",
 994 |               "4           Angel Gomes\n",
 995 |               "5              Football\n",
 996 |               "6        Caroline Flack\n",
 997 |               "7              FBG Duck\n",
 998 |               "8           Jamal Lewis\n",
 999 |               "9         BREAKING news\n",
1000 |               "10            Hiroshima\n",
1001 |               "11               Beirut\n",
1002 |               "12            Brentford\n",
1003 |               "13          Kemar Roofe\n",
1004 |               "14   England vs Ireland\n",
1005 |               "15      Virgin Atlantic\n",
1006 |               "16           Will Young\n",
1007 |               "17          Brian Black\n",
1008 |               "18            Fall Guys\n",
1009 |               "19        Jonathan Swan"
1010 |             ]
1011 |           },
1012 |           "metadata": {
1013 |             "tags": []
1014 |           },
1015 |           "execution_count": 26
1016 |         }
1017 |       ]
1018 |     },
1019 |     {
1020 |       "cell_type": "markdown",
1021 |       "metadata": {
1022 |         "id": "0itrtRU8S-1D"
1023 |       },
1024 |       "source": [
1025 |         "Interest by Region"
1026 |       ]
1027 |     },
1028 |     {
1029 |       "cell_type": "code",
1030 |       "metadata": {
1031 |         "id": "WWG1Dpm7Q1UE",
1032 |         "colab": {
1033 |           "base_uri": "https://localhost:8080/",
1034 |           "height": 204
1035 |         },
1036 |         "outputId": "477192b9-35a8-4006-eaac-1d5e08319018"
1037 |       },
1038 |       "source": [
1039 |         "pytrends.build_payload(kw_list=['coronavirus'], geo='GB') \n",
1040 |         "region_df = pytrends.interest_by_region(resolution='REGION', inc_low_vol=True)\n",
1041 |         "\n",
1042 |         "region_df.head(10)"
1043 |       ],
1044 |       "execution_count": null,
1045 |       "outputs": [
1046 |         {
1047 |           "output_type": "execute_result",
1048 |           "data": {
1049 |             "text/html": [
1050 |               "<div>\n",
1051 |               "<style scoped>\n",
1052 |               "    .dataframe tbody tr th:only-of-type {\n",
1053 |               "        vertical-align: middle;\n",
1054 |               "    }\n",
1055 |               "\n",
1056 |               "    .dataframe tbody tr th {\n",
1057 |               "        vertical-align: top;\n",
1058 |               "    }\n",
1059 |               "\n",
1060 |               "    .dataframe thead th {\n",
1061 |               "        text-align: right;\n",
1062 |               "    }\n",
1063 |               "</style>\n",
1064 |               "<table border=\"1\" class=\"dataframe\">\n",
1065 |               "  <thead>\n",
1066 |               "    <tr style=\"text-align: right;\">\n",
1067 |               "      <th></th>\n",
1068 |               "      <th>coronavirus</th>\n",
1069 |               "    </tr>\n",
1070 |               "    <tr>\n",
1071 |               "      <th>geoName</th>\n",
1072 |               "      <th></th>\n",
1073 |               "    </tr>\n",
1074 |               "  </thead>\n",
1075 |               "  <tbody>\n",
1076 |               "    <tr>\n",
1077 |               "      <th>England</th>\n",
1078 |               "      <td>97</td>\n",
1079 |               "    </tr>\n",
1080 |               "    <tr>\n",
1081 |               "      <th>Northern Ireland</th>\n",
1082 |               "      <td>96</td>\n",
1083 |               "    </tr>\n",
1084 |               "    <tr>\n",
1085 |               "      <th>Scotland</th>\n",
1086 |               "      <td>96</td>\n",
1087 |               "    </tr>\n",
1088 |               "    <tr>\n",
1089 |               "      <th>Wales</th>\n",
1090 |               "      <td>100</td>\n",
1091 |               "    </tr>\n",
1092 |               "  </tbody>\n",
1093 |               "</table>\n",
1094 |               "</div>"
1095 |             ],
1096 |             "text/plain": [
1097 |               "                  coronavirus\n",
1098 |               "geoName                      \n",
1099 |               "England                    97\n",
1100 |               "Northern Ireland           96\n",
1101 |               "Scotland                   96\n",
1102 |               "Wales                     100"
1103 |             ]
1104 |           },
1105 |           "metadata": {
1106 |             "tags": []
1107 |           },
1108 |           "execution_count": 32
1109 |         }
1110 |       ]
1111 |     },
1112 |     {
1113 |       "cell_type": "code",
1114 |       "metadata": {
1115 |         "id": "-C7uHXfFSxbN",
1116 |         "colab": {
1117 |           "base_uri": "https://localhost:8080/",
1118 |           "height": 204
1119 |         },
1120 |         "outputId": "b53182cc-4377-4aa5-ffd2-0c2fac64d4f0"
1121 |       },
1122 |       "source": [
1123 |         "kw_list = [\"BTS\", \"Stray Kids\", \"Day 6\"]\n",
1124 |         "pytrends.build_payload(kw_list)\n",
1125 |         "kpop_regions_df = pytrends.interest_by_region(resolution='COUNTRY', inc_low_vol=True)\n",
1126 |         "\n",
1127 |         "kpop_regions_df.head(10)"
1128 |       ],
1129 |       "execution_count": null,
1130 |       "outputs": [
1131 |         {
1132 |           "output_type": "execute_result",
1133 |           "data": {
1134 |             "text/html": [
1135 |               "<div>\n",
1136 |               "<style scoped>\n",
1137 |               "    .dataframe tbody tr th:only-of-type {\n",
1138 |               "        vertical-align: middle;\n",
1139 |               "    }\n",
1140 |               "\n",
1141 |               "    .dataframe tbody tr th {\n",
1142 |               "        vertical-align: top;\n",
1143 |               "    }\n",
1144 |               "\n",
1145 |               "    .dataframe thead th {\n",
1146 |               "        text-align: right;\n",
1147 |               "    }\n",
1148 |               "</style>\n",
1149 |               "<table border=\"1\" class=\"dataframe\">\n",
1150 |               "  <thead>\n",
1151 |               "    <tr style=\"text-align: right;\">\n",
1152 |               "      <th></th>\n",
1153 |               "      <th>BTS</th>\n",
1154 |               "      <th>Stray Kids</th>\n",
1155 |               "      <th>Day 6</th>\n",
1156 |               "    </tr>\n",
1157 |               "    <tr>\n",
1158 |               "      <th>geoName</th>\n",
1159 |               "      <th></th>\n",
1160 |               "      <th></th>\n",
1161 |               "      <th></th>\n",
1162 |               "    </tr>\n",
1163 |               "  </thead>\n",
1164 |               "  <tbody>\n",
1165 |               "    <tr>\n",
1166 |               "      <th>England</th>\n",
1167 |               "      <td>82</td>\n",
1168 |               "      <td>3</td>\n",
1169 |               "      <td>15</td>\n",
1170 |               "    </tr>\n",
1171 |               "    <tr>\n",
1172 |               "      <th>Northern Ireland</th>\n",
1173 |               "      <td>80</td>\n",
1174 |               "      <td>3</td>\n",
1175 |               "      <td>17</td>\n",
1176 |               "    </tr>\n",
1177 |               "    <tr>\n",
1178 |               "      <th>Scotland</th>\n",
1179 |               "      <td>81</td>\n",
1180 |               "      <td>3</td>\n",
1181 |               "      <td>16</td>\n",
1182 |               "    </tr>\n",
1183 |               "    <tr>\n",
1184 |               "      <th>Wales</th>\n",
1185 |               "      <td>79</td>\n",
1186 |               "      <td>3</td>\n",
1187 |               "      <td>18</td>\n",
1188 |               "    </tr>\n",
1189 |               "  </tbody>\n",
1190 |               "</table>\n",
1191 |               "</div>"
1192 |             ],
1193 |             "text/plain": [
1194 |               "                  BTS  Stray Kids  Day 6\n",
1195 |               "geoName                                 \n",
1196 |               "England            82           3     15\n",
1197 |               "Northern Ireland   80           3     17\n",
1198 |               "Scotland           81           3     16\n",
1199 |               "Wales              79           3     18"
1200 |             ]
1201 |           },
1202 |           "metadata": {
1203 |             "tags": []
1204 |           },
1205 |           "execution_count": 33
1206 |         }
1207 |       ]
1208 |     }
1209 |   ]
1210 | }


--------------------------------------------------------------------------------