From 5aa8ba95864187d226e8d5ae4be2be0660a9a6d3 Mon Sep 17 00:00:00 2001
From: PeterM18 <69867559+PeterM18@users.noreply.github.com>
Date: Fri, 1 Jul 2022 15:33:43 -0500
Subject: [PATCH 1/2] Published from Watson Studio.
---
testNB.ipynb | 32 ++++++++++++++++++++++++++++++++
1 file changed, 32 insertions(+)
create mode 100644 testNB.ipynb
diff --git a/testNB.ipynb b/testNB.ipynb
new file mode 100644
index 0000000..8080270
--- /dev/null
+++ b/testNB.ipynb
@@ -0,0 +1,32 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "collapsed": true
+ },
+ "source": "# testNB Peterm"
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3.9",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.9.12"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}
\ No newline at end of file
From 7f314cbf0e86908294f06460cef79c9fdb43f689 Mon Sep 17 00:00:00 2001
From: PeterM18 <69867559+PeterM18@users.noreply.github.com>
Date: Thu, 28 Jul 2022 15:06:42 -0500
Subject: [PATCH 2/2] webscrapingLab
webscrapingLab Python Notebook
---
webscrapingLab.ipynb | 1196 ++++++++++++++++++++++++++++++++++++++++++
1 file changed, 1196 insertions(+)
create mode 100644 webscrapingLab.ipynb
diff --git a/webscrapingLab.ipynb b/webscrapingLab.ipynb
new file mode 100644
index 0000000..dbb6ff7
--- /dev/null
+++ b/webscrapingLab.ipynb
@@ -0,0 +1,1196 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "\n",
+ " \n",
+ " ![\"Skills](\"https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/assets/logos/SN_web_lightmode.png\")
\n",
+ " \n",
+ "
\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# **Space X Falcon 9 First Stage Landing Prediction**\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Web scraping Falcon 9 and Falcon Heavy Launches Records from Wikipedia\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Estimated time needed: **40** minutes\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "In this lab, you will be performing web scraping to collect Falcon 9 historical launch records from a Wikipedia page titled `List of Falcon 9 and Falcon Heavy launches`\n",
+ "\n",
+ "[https://en.wikipedia.org/wiki/List_of_Falcon\\_9\\_and_Falcon_Heavy_launches](https://en.wikipedia.org/wiki/List_of_Falcon\\_9\\_and_Falcon_Heavy_launches?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDS0321ENSkillsNetwork26802033-2022-01-01)\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Falcon 9 first stage will land successfully\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Several examples of an unsuccessful landing are shown here:\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "More specifically, the launch records are stored in a HTML table shown below:\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Objectives\n",
+ "\n",
+ "Web scrap Falcon 9 launch records with `BeautifulSoup`:\n",
+ "\n",
+ "* Extract a Falcon 9 launch records HTML table from Wikipedia\n",
+ "* Parse the table and convert it into a Pandas data frame\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "First let's import required packages for this lab\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Collecting beautifulsoup4\n",
+ " Downloading beautifulsoup4-4.11.1-py3-none-any.whl (128 kB)\n",
+ "\u001b[2K \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m128.2/128.2 KB\u001b[0m \u001b[31m889.6 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m kB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m:01\u001b[0m\n",
+ "\u001b[?25hCollecting soupsieve>1.2\n",
+ " Downloading soupsieve-2.3.2.post1-py3-none-any.whl (37 kB)\n",
+ "Installing collected packages: soupsieve, beautifulsoup4\n",
+ "Successfully installed beautifulsoup4-4.11.1 soupsieve-2.3.2.post1\n",
+ "Requirement already satisfied: requests in /home/pm/Software/miniconda3/lib/python3.9/site-packages (2.27.1)\n",
+ "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /home/pm/Software/miniconda3/lib/python3.9/site-packages (from requests) (1.26.9)\n",
+ "Requirement already satisfied: idna<4,>=2.5 in /home/pm/Software/miniconda3/lib/python3.9/site-packages (from requests) (3.3)\n",
+ "Requirement already satisfied: certifi>=2017.4.17 in /home/pm/Software/miniconda3/lib/python3.9/site-packages (from requests) (2022.6.15)\n",
+ "Requirement already satisfied: charset-normalizer~=2.0.0 in /home/pm/Software/miniconda3/lib/python3.9/site-packages (from requests) (2.0.12)\n"
+ ]
+ }
+ ],
+ "source": [
+ "!pip3 install beautifulsoup4\n",
+ "!pip3 install requests"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import sys\n",
+ "\n",
+ "import requests\n",
+ "from bs4 import BeautifulSoup\n",
+ "import re\n",
+ "import unicodedata\n",
+ "import pandas as pd"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "and we will provide some helper functions for you to process web scraped HTML table\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def date_time(table_cells):\n",
+ " \"\"\"\n",
+ " This function returns the data and time from the HTML table cell\n",
+ " Input: the element of a table data cell extracts extra row\n",
+ " \"\"\"\n",
+ " return [data_time.strip() for data_time in list(table_cells.strings)][0:2]\n",
+ "\n",
+ "def booster_version(table_cells):\n",
+ " \"\"\"\n",
+ " This function returns the booster version from the HTML table cell \n",
+ " Input: the element of a table data cell extracts extra row\n",
+ " \"\"\"\n",
+ " out=''.join([booster_version for i,booster_version in enumerate( table_cells.strings) if i%2==0][0:-1])\n",
+ " return out\n",
+ "\n",
+ "def landing_status(table_cells):\n",
+ " \"\"\"\n",
+ " This function returns the landing status from the HTML table cell \n",
+ " Input: the element of a table data cell extracts extra row\n",
+ " \"\"\"\n",
+ " out=[i for i in table_cells.strings][0]\n",
+ " return out\n",
+ "\n",
+ "\n",
+ "def get_mass(table_cells):\n",
+ " mass=unicodedata.normalize(\"NFKD\", table_cells.text).strip()\n",
+ " if mass:\n",
+ " mass.find(\"kg\")\n",
+ " new_mass=mass[0:mass.find(\"kg\")+2]\n",
+ " else:\n",
+ " new_mass=0\n",
+ " return new_mass\n",
+ "\n",
+ "\n",
+ "def extract_column_from_header(row):\n",
+ " \"\"\"\n",
+ " This function returns the landing status from the HTML table cell \n",
+ " Input: the element of a table data cell extracts extra row\n",
+ " \"\"\"\n",
+ " if (row.br):\n",
+ " row.br.extract()\n",
+ " if row.a:\n",
+ " row.a.extract()\n",
+ " if row.sup:\n",
+ " row.sup.extract()\n",
+ " \n",
+ " colunm_name = ' '.join(row.contents)\n",
+ " \n",
+ " # Filter the digit and empty names\n",
+ " if not(colunm_name.strip().isdigit()):\n",
+ " colunm_name = colunm_name.strip()\n",
+ " return colunm_name \n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "To keep the lab tasks consistent, you will be asked to scrape the data from a snapshot of the `List of Falcon 9 and Falcon Heavy launches` Wikipage updated on\n",
+ "`9th June 2021`\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "static_url = \"https://en.wikipedia.org/w/index.php?title=List_of_Falcon_9_and_Falcon_Heavy_launches&oldid=1027686922\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Next, request the HTML page from the above URL and get a `response` object\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### TASK 1: Request the Falcon9 Launch Wiki page from its URL\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "First, let's perform an HTTP GET method to request the Falcon9 Launch HTML page, as an HTTP response.\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# use requests.get() method with the provided static_url\n",
+ "# assign the response to a object\n",
+ "reqObj = requests.get(static_url)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "'\\n\\n\\n\\nList of Falcon 9 and Falcon Heavy launches - Wikipedia\\n