[pandas] web scraping

pip install lxml html5lib beautifulsoup4

import pandas as pd

url = 'https://en.wikipedia.org/wiki/History_of_Python'
dfs = pd.read_html(url)

print(len(dfs))

print(dfs[0]['Version'])
print(dfs[0]['Release date'])

# Load pandas

import pandas as pd

# Webpage url                                                                                                               
url = 'https://en.wikipedia.org/wiki/History_of_Python'

# Extract tables
dfs = pd.read_html(url)

# Get first table                                                                                                           
df = dfs[0]

# Extract columns                                                                                                           
df2 = df[['Version','Release date']]
print(df2)

# Write to excel
df2.to_excel('python.xlsx')

https://pythonbasics.org/pandas-web-scraping/

Pandas Web Scraping - Python Tutorial