IndiaFOSS Proposal Approvals Tracking

indiafoss-approvals-tracking.py

import re
from multiprocessing import Pool
from playwright.sync_api import sync_playwright
from tabulate import tabulate

def fetch_approval(workshop):
    title, url = workshop
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        context = browser.new_context()
        page = context.new_page()
        try:
            page.goto(url, timeout=10000)
            page.wait_for_load_state("domcontentloaded")
            try:
                page.wait_for_selector("div.flex.text-green-600", timeout=3000)
                approval_span = page.locator("div.flex.text-green-600 span.text-xl.font-bold").first
                approvals = approval_span.inner_text().strip()
            except:
                approvals = "?"
        except Exception as e:
            print(f"⚠️ Error for {title}: {e}")
            approvals = "?"
        finally:
            context.close()
            browser.close()
        return (title, approvals)

def run():
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        context = browser.new_context()
        page = context.new_page()

        # Step 1: Go to proposals page
        page.goto("https://fossunited.org/dashboard/cfp/all/indiafoss/2025")

        # Step 2: Apply Workshop filter
        page.get_by_role("button", name="Filter").click()
        page.locator("div").filter(has_text=re.compile(r"^Add filter$")).first.click()
        page.get_by_role("button", name="Add filter").click()
        page.get_by_text("Session Type").click()
        page.locator("#frappe-ui-3").select_option("Workshop")

        # Step 3: Wait for proposals to load
        page.wait_for_selector("a[href^='/c/indiafoss/2025/cfp/'] h4")

        # Step 4: Extract titles and URLs
        proposal_links = page.query_selector_all("a[href^='/c/indiafoss/2025/cfp/']")
        workshops = []
        for a_tag in proposal_links:
            try:
                href = a_tag.get_attribute("href")
                h4_elem = a_tag.query_selector("h4")
                title = h4_elem.inner_text().strip() if h4_elem else "Untitled"
                if href:
                    full_url = "https://fossunited.org" + href
                    workshops.append((title, full_url))
            except Exception as e:
                print("⚠️ Skipping one due to:", e)

        context.close()
        browser.close()

    # Step 5: Parallel fetch approvals
    print(f"\n🔄 Fetching {len(workshops)} workshop approvals in parallel...\n")
    with Pool(processes=5) as pool:
        results = pool.map(fetch_approval, workshops)

    # Step 6: Sort by approval count
    sorted_results = sorted(
        results,
        key=lambda x: int(x[1]) if x[1].isdigit() else 0,
        reverse=True
    )

    # Step 7: Display results
    print("\n📋 Workshop Approvals Table (Sorted by Approvals):\n")
    print(tabulate(sorted_results, headers=["Workshop Title", "Approvals"], tablefmt="github"))

if __name__ == "__main__":
    run()