Free news for the masses - Bypass stupid paywalls easily with your own horribly written Python script!

ODT.py

from flask import Flask, request, Response, render_template_string
import requests
from playwright.sync_api import sync_playwright
from bs4 import BeautifulSoup
from urllib.parse import urljoin, urlparse

app = Flask(__name__)

ALLOWED_DOMAINS = [ "odt.co.nz", "nzherald.co.nz", "thepress.co.nz"]

@app.route('/proxy')
def proxy():
    url = request.args.get('url')
    if not url:
        return "Missing URL parameter", 400

    # Validate domain
    parsed_url = urlparse(url)
    if parsed_url.scheme not in ('http', 'https'):
        return "Invalid URL scheme", 400

    if parsed_url.hostname not in ALLOWED_DOMAINS and not any(parsed_url.hostname.endswith("." + d) for d in ALLOWED_DOMAINS):
        return "URL domain not allowed", 403


#@#zephr-html-paywall
    try:
        res = requests.get(url, timeout=10)
        res.raise_for_status()

        soup = BeautifulSoup(res.text, 'html.parser')
        
        #The Press
        if parsed_url.hostname == "www.thepress.co.nz":
            with sync_playwright() as p:
                browser = p.chromium.launch(headless=True, args=["--no-sandbox"])
                context = browser.new_context(user_agent=("Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
                                "AppleWebKit/537.36 (KHTML, like Gecko) "
                                "Chrome/122.0.0.0 Safari/537.36"),
                    locale="en-NZ"
                )
                page = context.new_page()
                page.set_default_timeout(20000)
                page.goto(url, wait_until="domcontentloaded")
                page.wait_for_selector("article, [itemprop='articleBody'], #root h1")
                rendered_html = page.content()
                context.close()
                browser.close()
                soup = BeautifulSoup(rendered_html, "html.parser")
                head = soup.head or soup.new_tag("head")
                if not soup.head:
                    if soup.html:
                        soup.html.insert(0, head)
                    else:
                        soup.insert(0, head)

                if not head.find("base"):
                    base = soup.new_tag("base", href=f"{parsed_url.scheme}://{parsed_url.netloc}")
                    head.insert(0, base)

                for tag in soup.find_all(True):
                    for attr in ("href", "src", "action"):
                        if attr in tag.attrs:
                            val = tag[attr]
                            if isinstance(val, str) and not val.startswith(("javascript:", "data:", "mailto:", "tel:")):
                                tag[attr] = urljoin(f"{parsed_url.scheme}://{parsed_url.netloc}", val)

                    if "srcset" in tag.attrs:
                        new_candidates = []
                        for candidate in str(tag["srcset"]).split(","):
                            parts = candidate.strip().split()
                            if not parts:
                                continue
                            url_part = parts[0]
                            rest = parts[1:]
                            if not url_part.startswith(("data:", "javascript:", "mailto:", "tel:")):
                                url_part = urljoin(f"{parsed_url.scheme}://{parsed_url.netloc}", url_part)
                            new_candidates.append(" ".join([url_part] + rest))
                        tag["srcset"] = ", ".join(new_candidates)

                return Response(str(soup), content_type="text/html")

        
        #Otago Daily Times
        if parsed_url.hostname == "www.odt.co.nz":
          for script in soup.find_all("script"):
            script.decompose()
        
          for div in soup.select('div.field-item.even'):
              if div.get('property') == 'content:encoded':
                  del div['property']

        #NZ Herald
        if parsed_url.hostname == "www.nzherald.co.nz":
          [s.decompose() for s in soup.find_all("script") if any(k in (s.get("src") or "").lower() for k in ["tailwind", "queryly.v4", "client", "appear", "image", "gpt", "react"])]

          div = soup.select_one("div.article-paywall-hide")
          if div:
              for tag in div.find_all(True): 
                  if 'class' in tag.attrs:
                    del tag.attrs['class']
                  if 'style' in tag.attrs:
                    del tag.attrs['style']
                  if 'data-test-ui'  in tag.attrs:
                    del tag.attrs['data-test-ui']
                    
          del div.attrs['class']
          
          soup = BeautifulSoup(str(soup).replace("&", "&"), "html.parser")

        
        #Fix all Relative URLs.
        base_url = f"{parsed_url.scheme}://{parsed_url.netloc}"

        for tag in soup.find_all(True):
          for attr in ("href", "src", "action", "img"):
            if attr in tag.attrs:
              original = tag[attr]
              tag[attr] = urljoin(base_url, original)
   
        clean_html = str(soup)

        return Response(clean_html, content_type='text/html')

    except Exception as e:
        return f"Error fetching or processing URL: {e}", 500

@app.route('/')
def index():
    return render_template_string('''
<!DOCTYPE html>
<html lang="en">
<head>
  <meta charset="UTF-8" />
  <meta name="viewport" content="width=device-width, initial-scale=1" />
  <title>ODT Free</title>
  <!-- Bootstrap CSS CDN -->
  <link
    href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/css/bootstrap.min.css"
    rel="stylesheet"
  />
</head>
<body class="bg-light">
  <div class="container py-5">
    <h1 class="mb-4 text-center">ODT Free</h1>
    <form id="urlForm" class="mx-auto" style="max-width: 480px;" action="/proxy" method="get">
      <div class="mb-3">
        <p>Otago Daily Times has full support, the web-page <i>should</i> appear mostly normal, minus the pay wall, NZ Herlad has partial support, currently images for articles will not display.</p>
                <label for="urlInput" class="form-label">Enter a premium link from <a href="https://odt.co.nz" target="_blank">odt.co.nz</a>, <a href="https://nzherald.co.nz" target="_blank">nzherald.co.nz</a>, or <a href="https://thepress.co.nz" target="_blank">thepress.co.nz</a></label>
        <input
          type="url"
          class="form-control"
          id="urlInput"
          name="url"
          placeholder="https://www.odt.co.nz/news/dunedin/far-running-company-they-were-awful"
          required
        />
      </div>
      <button type="submit" class="btn btn-primary w-100">Submit</button>
    </form>
  </div>

  <!-- Bootstrap JS Bundle with Popper (optional) -->
  <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/js/bootstrap.bundle.min.js"></script>
</body>
</html>
    ''')

if __name__ == '__main__':
    app.run(debug=False)

This was vibe coded.
I don't do Python, I don't do paying for stuff either.

It was written originally to bypass the paywall on ODT, then expanded to Herald (Yeah, I still hold a grudge), and most recently The Press.

You need the following installed

beautifulsoup4==4.14.3
blinker==1.9.0
bs4==0.0.2
certifi==2026.1.4
charset-normalizer==3.4.4
click==8.3.1
Flask==3.1.2
greenlet==3.3.2
idna==3.11
itsdangerous==2.2.0
Jinja2==3.1.6
MarkupSafe==3.0.3
playwright==1.58.0
pyee==13.0.1
requests==2.32.5
soupsieve==2.8.3
typing_extensions==4.15.0
urllib3==2.6.3
Werkzeug==3.1.5

Or at the least, ensure feature sets are the same.

Then, throw your link into the box, and it will handle the rest so long as they don't update their selectors JS / CSS trickery.(https://knowyourmeme.com/memes/cheeto-lock) is what I would use here to explain why they've done a bad bad thing.