How Playwright Helps You Land a Data Analyst Job Faster

# pip install playwright && playwright install chromium
# Use only on portals you are authorised to automate.
import os
from datetime import date
from playwright.sync_api import sync_playwright

PORTAL = os.environ["PORTAL_URL"]
USER = os.environ["PORTAL_USER"]
PASSWORD = os.environ["PORTAL_PASSWORD"]

with sync_playwright() as p:
    browser = p.chromium.launch()
    page = browser.new_page()
    page.goto(PORTAL)
    page.get_by_label("Email").fill(USER)
    page.get_by_label("Password").fill(PASSWORD)
    page.get_by_role("button", name="Sign in").click()
    page.get_by_role("link", name="Reports").click()
    with page.expect_download() as info:
        page.get_by_role("button", name="Export CSV").click()
    info.value.save_as(f"exports/sales_{date.today():%Y-%m-%d}.csv")
    browser.close()

from pathlib import Path
import pandas as pd

# Pick the newest export and clean it
files = sorted(Path("exports").glob("sales_*.csv"))
if not files:
    raise SystemExit("no exports found yet")
latest = files[-1]
df = pd.read_csv(latest)
df.columns = [c.strip().lower().replace(" ", "_") for c in df.columns]
print(latest.name, df.shape)
print(df.head())

# Runs against a local HTML page, so no external site is touched.
import pandas as pd
from playwright.sync_api import sync_playwright

HTML = """
<table id='rates'>
  <tr><th>City</th><th>Rate</th></tr>
  <tr><td>Noida</td><td>4.2</td></tr>
  <tr><td>Delhi</td><td>3.9</td></tr>
</table>
"""

with sync_playwright() as p:
    browser = p.chromium.launch()
    page = browser.new_page()
    page.set_content(HTML)
    rows = page.locator("#rates tr").all()
    data = [r.locator("th, td").all_inner_texts() for r in rows]
    browser.close()

df = pd.DataFrame(data[1:], columns=data[0])
df["Rate"] = pd.to_numeric(df["Rate"])
print(df)

Before collecting web data:

[ ] Is there an official API or download? Use it first.
[ ] Do the site's terms allow automated access?
[ ] Does robots.txt disallow the pages?
[ ] Am I collecting personal data? If so, stop and check the law and policy.
[ ] Is my script slow and polite (one page at a time, pauses)?
[ ] Have I recorded the source URL and date?

# Opens a local sample dashboard; point DASH_URL at your own when authorised.
import os
from playwright.sync_api import sync_playwright, expect

SAMPLE = "<h1>Sales</h1><div id='total'>₹ 12,40,000</div><div id='error' hidden>Error</div>"

with sync_playwright() as p:
    browser = p.chromium.launch()
    page = browser.new_page()
    url = os.environ.get("DASH_URL")
    page.goto(url) if url else page.set_content(SAMPLE)
    expect(page.locator("#total")).not_to_have_text("")
    expect(page.locator("#error")).to_be_hidden()
    page.screenshot(path="dashboard_check.png", full_page=True)
    print("dashboard OK:", page.locator("#total").inner_text())
    browser.close()

# Linux/macOS cron: run every weekday at 8:30
# 30 8 * * 1-5  cd /path/to/project && .venv/bin/python dashboard_check.py >> check.log 2>&1

# Windows: use Task Scheduler to run
#   python dashboard_check.py
# at 8:30 on weekdays.

# Keep credentials in environment variables, never in the script.

Project: Automated daily report pipeline

- Playwright script downloads a CSV from a demo portal you build locally
- pandas cleans it and builds a summary
- Summary exported to Excel with dated file names
- Dashboard check with screenshot
- Credentials from environment variables
- Scheduled with cron or Task Scheduler
- README covering permissions and responsible use

Week 1  Playwright basics: goto, locators, click, fill
Week 2  Downloads and waits; save files reliably
Week 3  Connect to pandas cleaning and Excel output
Week 4  Dashboard check, scheduling, README

Situation: daily sales export took manual clicks each morning
Task: automate download and summary (practice project)
Action:
  - Playwright script for login and export
  - pandas cleaning and Excel summary
  - dashboard check with screenshot
  - credentials in environment variables
Result: report ready automatically; I can explain each step and its limits