powerexploit · powerexploit · Sep 29, 2020 · Sep 26, 2020
diff --git a/Web-Scraping/Hacktoberfest_Events/README.md b/Web-Scraping/Hacktoberfest_Events/README.md
@@ -0,0 +1,17 @@
+## Hacktoberfest Events
+
+### This script scrapes all the events from the Hacktoberfest events website and stores them in a csv file.
+
+### How to use this script?
+
+1. Make sure all the requirements for the script are present in your system by running:
+
+    pip install -r requirements.txt
+
+2. Run the following command:
+
+    python hacktoberfest_events.py
+
+### Author
+
+[Aditya Jetely](https://github.com/AdityaJ7)
diff --git a/Web-Scraping/Hacktoberfest_Events/hacktoberfest_events.py b/Web-Scraping/Hacktoberfest_Events/hacktoberfest_events.py
@@ -0,0 +1,44 @@
+import requests
+from bs4 import BeautifulSoup as bs
+import pandas as pd
+
+
+def scrape_tablerows():
+    """This function scrapes the tablerows related to our target elements.
+       Our target element here are the events of hactoberfest.
+
+    Returns:
+        tablerows[list]: A list of tablerows of our taget elements.
+    """
+    hacktoberfest_events_url = "https://hacktoberfest.digitalocean.com/events"
+    response = requests.get(hacktoberfest_events_url)
+    soup = bs(response.content, 'html.parser')
+    mydivs = soup.findAll("tbody", {"class": "list"})
+    tablerows = mydivs[0].findAll("tr")
+    return tablerows
+
+
+def hacktoberfest_events(tablerows):
+    """This function takes the list of tablerows as input and performs
+       scraping of required elements as well as stores the scraped data
+       into a csv file.
+
+    Args:
+        tablerows (list): Lis of tablerows of the target elements.
+    """
+    events = {}
+    for i, tablerow in enumerate(tablerows):
+        location = tablerow.find("td", {"class": "location"}).text
+        link = tablerow.find("a")['href']
+        name = tablerow.find("td", {"class": "event_name"}).text.strip()
+        date = tablerow.find("td", {"class": "date is-hidden"}).text.strip()
+        events[i] = [name, date, location, link]
+    df1 = pd.DataFrame.from_dict(events, orient='index')
+    df1.columns = ['Name', 'Date', 'Location', 'Link']
+    df1.to_csv('hacktoberfest_events.csv')
+
+
+if __name__ == "__main__":
+    tablerows = scrape_tablerows()
+    hacktoberfest_events(tablerows)
+    print("The events have been stored successfully")
diff --git a/Web-Scraping/Hacktoberfest_Events/requirements.txt b/Web-Scraping/Hacktoberfest_Events/requirements.txt
@@ -0,0 +1,8 @@
+beautifulsoup4==4.9.1
+certifi==2020.6.20
+chardet==3.0.4
+idna==2.10
+requests==2.24.0
+soupsieve==2.0.1
+urllib3==1.25.10
+pandas==1.1.2