Python 3 Web Scraping HTML Tables to CSV File Using BeautifulSoup4 Library

Welcome folks today in this blog post we will be scraping the html tables from the webpage and saving it as csv file in python using the beautifulsoup4 library. All the full source code of the application is shown below.

Get Started

In order to get started you need to install the below library using the pip command as shown below

pip install bs4

And after that you need to make an app.py file and copy paste the following code

app.py

import requests
from bs4 import BeautifulSoup
import csv

# Make a GET request to the URL that contains the table
url = "https://wpdatatables.com/documentation/column-features/url-link-columns/"
response = requests.get(url)

# Parse the HTML content of the page
soup = BeautifulSoup(response.text, "html.parser")

# Find the table in the HTML content
table = soup.find("table")

# Write the table data to a CSV file
with open("table.csv", "w", newline="") as csvfile:
    writer = csv.writer(csvfile)

    # Write the header row
    header = [th.text.strip() for th in table.find("thead").find_all("th")]
    writer.writerow(header)

    # Write the data rows
    for row in table.find("tbody").find_all("tr"):
        data = [td.text.strip() for td in row.find_all("td")]
        writer.writerow(data)

import requests

from bs4 import BeautifulSoup

import csv

# Make a GET request to the URL that contains the table

url = "https://wpdatatables.com/documentation/column-features/url-link-columns/"

response = requests.get(url)

# Parse the HTML content of the page

soup = BeautifulSoup(response.text, "html.parser")

# Find the table in the HTML content

table = soup.find("table")

# Write the table data to a CSV file

with open("table.csv", "w", newline="") as csvfile:

writer = csv.writer(csvfile)

# Write the header row

header = [th.text.strip() for th in table.find("thead").find_all("th")]

writer.writerow(header)

# Write the data rows

for row in table.find("tbody").find_all("tr"):

data = [td.text.strip() for td in row.find_all("td")]

writer.writerow(data)

As you can see we are importing the bs4 library at the top and then we have provided the online url of the webpage where some html table is there so now it will scrape the whole webpage and scan it and find all the table tags and convert that data into the csv file and save it using the bs4 library.