distrowatch_architectures_count.py

# pip install requests beautifulsoup4 progress tabulate
import requests
from bs4 import BeautifulSoup
from progress.bar import Bar
from tabulate import tabulate

# Define the DistroWatch search URL that lists all active Linux distributions for servers
dws = (
    "https://distrowatch.com/search.php?"
    "ostype=Linux&" # OS Type: Linux
    "category=Server&" # Distribution Category: Server
    "status=Active&" # Status: Active
    "origin=All&"
    "basedon=All&"
    "notbasedon=None&"
    "desktop=All&"
    "architecture=All&"
    "package=All&"
    "rolling=All&"
    "isosize=All&"
    "netinstall=All&"
    "language=All&"
    "defaultinit=All"
)

# Send a GET request to the URL
dws_r = requests.get(dws)

# Parse the response text with BeautifulSoup
dws_r_soup = BeautifulSoup(dws_r.text, "lxml")

# Select all Linux distribution names from the parsed HTML
distro_atags = dws_r_soup.css.select("td > b > a")[1:]

# Define a function to create a distribution's URL on DistroWatch
def base_url(d):
    return f"https://distrowatch.com/table.php?distribution={d}"

# Initialize a dictionary to store the counts of different architectures
ARCHS = {}

# Process each Linux distribution
for distro_atag in Bar('Processing').iter(distro_atags):
    # Create the distribution's URL
    url = base_url(distro_atag["href"])
    # Send a GET request to the URL
    r = requests.get(url)
    # Parse the response text with BeautifulSoup
    soup = BeautifulSoup(r.text, "lxml")
    # Select the architecture list from the parsed HTML
    arch_li = soup.css.select("td.TablesTitle > ul > li")[3]
    arch_atags = arch_li.css.select('a')
    # Process each architecture
    for arch_atag in arch_atags:
        # Get the architecture name
        arch_name = arch_atag.text
        # Increment the count of this architecture in ARCHS
        ARCHS[arch_name] = ARCHS.get(arch_name, 0) + 1

# Print the architectures and their counts, sorted by count in descending order
print(
    tabulate(
        sorted(
            ARCHS.items(),
            key=lambda i: i[1],
            reverse=True
        ),
        headers=['Architecture', 'Count'],
        tablefmt="heavy_grid"
    )
)