Merge branch 'main' into feat/status-page-and-bypass-fallbacks

Dockerfile

@@ -1,5 +1,12 @@
+# syntax=docker/dockerfile:1
 FROM python:3.13.7-alpine
 
+ARG UID=1000
+ARG GID=1000
+
+RUN addgroup -g $GID thirteener
+RUN adduser -D -g '' -u $UID -G thirteener thirteener
+
 # Generic labels
 LABEL maintainer="Arian Mollik Wasi <arianmollik323@gmail.com>"
 LABEL version="0.3.4"
@@ -18,9 +25,13 @@ LABEL org.opencontainers.image.description="My own custom 12ft.io replacement"
 LABEL org.opencontainers.image.documentation="https://github.com/wasi-master/13ft/blob/main/README.md"
 LABEL org.opencontainers.image.licenses=MIT
 
+RUN python -m pip install --upgrade pip
+
+USER thirteener
 COPY . .
-RUN pip install -r requirements.txt
+RUN --mount=type=cache,mode=0755,target=/home/thirteener/.cache/pip \
+  pip install -U -r requirements.txt
+
 WORKDIR /app
 EXPOSE 5000
-ENTRYPOINT [ "python" ]
+CMD [ "python", "-m", "gunicorn", "portable:app" ]
-CMD [ "portable.py" ] 

README.md

@@ -15,6 +15,7 @@ It pretends to be GoogleBot (Google's web crawler) and gets the same content tha
 ### Using Docker
 
 Requirements:
+
 - docker
 - Docker Compose (available as `docker compose`)
 
@@ -47,7 +48,13 @@ Then run `portable.py`, click [this link](https://realpython.com/run-python-scri
 python portable.py
 ```
 
-Then open the link shown in the terminal in the browser and you'll be able to use this
+Or you can also run via gunicorn as follows:
+
+```sh
+python -m gunicorn 'portable:app'
+```
+
+Then open the link shown in the terminal in the browser and you'll be able to use this script
 
 ### Installation using venv and running under specific bind address / port
 
@@ -58,16 +65,18 @@ python -m pip install -r requirements.txt
 FLASK_APP=app/portable.py flask run --host=127.0.0.1 --port=9982
 ```
 
-
 ## Using as a Bookmarklet in Chrome:
 
 You can create a bookmarklet that performs the URL transformation by writing a small JavaScript snippet. Below is the JavaScript code for your bookmarklet:
+
 ```javascript
-javascript:(function(){window.location.href='https://13ft.wasimaster.me/'+encodeURIComponent(window.location.href);})();
+javascript: (function () {window.location.href="https://13ft.wasimaster.me/" + encodeURIComponent(window.location.href);})();
 ```
+
 You can replace https://13ft.wasimaster.me with your own 13ft instance if desired.
 
 Steps:
+
 1. Open Bookmarks Manager:
 
 2. Click on the three dots (menu) in the top-right corner of Chrome.
@@ -75,9 +84,7 @@ Go to Bookmarks > Bookmark manager, or simply press Ctrl+Shift+O on Windows/Linu
    Create a New Bookmark:
 
 3. In the Bookmark Manager, click the three-dot menu in the top-right corner of the window and select Add new bookmark.
-Enter Bookmark Details:
+   Enter Bookmark Details: - Name: Enter a name for your bookmarklet, such as "13ft-ize". This name will show as a bookmark title in the bookmarks bar - URL: Paste the JavaScript code provided above into the URL field.
-    - Name: Enter a name for your bookmarklet, such as "13ft-ize". This name will show as a bookmark title in the bookmarks bar
-    - URL: Paste the JavaScript code provided above into the URL field.
 4. Click Save.
 
 Using the Bookmarklet:

app/gunicorn.conf.py

@@ -0,0 +1,4 @@
+from os import environ
+
+# https://docs.gunicorn.org/en/stable/settings.html#settings
+bind = f"0.0.0.0:{environ.get('PORT', 5000)}"

app/index.html

@@ -1,177 +0,0 @@
-<!DOCTYPE html>
-<html lang="en">
-
-<head>
-    <meta charset="UTF-8">
-    <meta name="viewport" content="width=device-width, initial-scale=1.0">
-    <meta http-equiv="X-UA-Compatible" content="IE=edge">
-    <title>13ft Ladder</title>
-    <link href="https://fonts.googleapis.com/css2?family=Open+Sans&display=swap" rel="stylesheet" async>
-    <style>
-        body {
-            font-family: 'Open Sans', sans-serif;
-            background-color: #FFF;
-            margin: 0;
-            padding: 0;
-            display: flex;
-            justify-content: center;
-            align-items: center;
-            height: 90vh;
-            transition: background-color 0.3s, color 0.3s;
-        }
-
-        h1 {
-            font-size: 1.5rem;
-            margin-bottom: 20px;
-            text-align: center;
-            color: #333;
-        }
-
-        label {
-            display: block;
-            margin-bottom: 10px;
-            font-weight: bold;
-        }
-
-        input[type=text] {
-            padding: 10px;
-            margin-bottom: 10px;
-            border: 1px solid #ccc;
-            border-radius: 5px;
-            width: 100%;
-            font-size: 1rem;
-            box-sizing: border-box;
-        }
-
-        input[type="submit"] {
-            padding: 16px;
-            background-color: #a327f0;
-            color: #fff;
-            border: none;
-            border-radius: 5px;
-            width: 100%;
-            text-transform: uppercase;
-            font-size: 1rem;
-            font-weight: 600;
-            cursor: pointer;
-            transition: background-color 0.3s ease;
-        }
-
-        input[type="submit"]:hover {
-            background-color: #821fc0;
-        }
-
-        /* Toggle switch styles */
-        .dark-mode-toggle {
-            position: absolute;
-            top: 10px;
-            right: 10px;
-        }
-
-        .dark-mode-toggle input {
-            display: none;
-        }
-
-        .dark-mode-toggle label {
-            cursor: pointer;
-            text-indent: -9999px;
-            width: 52px;
-            height: 27px;
-            background: grey;
-            display: block;
-            border-radius: 100px;
-            position: relative;
-        }
-
-        .dark-mode-toggle label:after {
-            content: '';
-            position: absolute;
-            top: 2px;
-            left: 2px;
-            width: 23px;
-            height: 23px;
-            background: #fff;
-            border-radius: 90px;
-            transition: 0.3s;
-        }
-
-        .dark-mode-toggle input:checked+label {
-            background: #7359f8;
-        }
-
-        .dark-mode-toggle input:checked+label:after {
-            left: calc(100% - 2px);
-            transform: translateX(-100%);
-        }
-
-        /* Responsive adjustments */
-        @media only screen and (max-width: 600px) {
-            form {
-                padding: 10px;
-            }
-
-            h1 {
-                font-size: 1.2rem;
-            }
-        }
-
-        /* Dark mode styles */
-        body.dark-mode {
-            background-color: #191a21;
-            color: #FFF;
-        }
-
-        body.dark-mode h1 {
-            color: #FFF;
-        }
-
-        body.dark-mode input[type=text] {
-            background-color: #555;
-            border: 1px solid #777;
-            color: #FFF;
-        }
-
-        body.dark-mode input[type="submit"] {
-            background-color: #7359f8;
-        }
-
-        body.dark-mode input[type="submit"]:hover {
-            background-color: #5c47c6;
-        }
-    </style>
-</head>
-
-<body>
-    <div class="dark-mode-toggle">
-        <input type="checkbox" id="dark-mode-toggle">
-        <label for="dark-mode-toggle" title="Toggle Dark Mode"></label>
-    </div>
-    <form action="/article" method="post">
-        <h1>Enter Website Link</h1>
-        <label for="link">Link of the website you want to remove paywall for:</label>
-        <input type="text" id="link" name="link" required autofocus>
-        <input type="submit" value="Submit">
-    </form>
-
-    <script>
-        const toggleSwitch = document.getElementById('dark-mode-toggle');
-        const currentTheme = localStorage.getItem('theme') || (window.matchMedia("(prefers-color-scheme: dark)").matches ? "dark" : "light");
-
-        if (currentTheme === "dark") {
-            document.body.classList.add("dark-mode");
-            toggleSwitch.checked = true;
-        }
-
-        toggleSwitch.addEventListener('change', function () {
-            if (this.checked) {
-                document.body.classList.add("dark-mode");
-                localStorage.setItem('theme', 'dark');
-            } else {
-                document.body.classList.remove("dark-mode");
-                localStorage.setItem('theme', 'light');
-            }
-        });
-    </script>
-</body>
-
-</html>

app/index.py

@@ -1,82 +0,0 @@
-import flask
-import requests
-from flask import request
-from bs4 import BeautifulSoup
-from urllib.parse import urlparse, urljoin
-
-app = flask.Flask(__name__)
-googlebot_headers = {
-    "User-Agent": "Mozilla/5.0 (Linux; Android 6.0.1; Nexus 5X Build/MMB29P) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.6533.119 Mobile Safari/537.36 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)"
-}
-
-def add_base_tag(html_content, original_url):
-    soup = BeautifulSoup(html_content, 'html.parser')
-    parsed_url = urlparse(original_url)
-    base_url = f"{parsed_url.scheme}://{parsed_url.netloc}/"
-    
-    # Handle paths that are not root, e.g., "https://x.com/some/path/w.html"
-    if parsed_url.path and not parsed_url.path.endswith('/'):
-        base_url = urljoin(base_url, parsed_url.path.rsplit('/', 1)[0] + '/')
-    base_tag = soup.find('base')
-    
-    print(base_url)
-    if not base_tag:
-        new_base_tag = soup.new_tag('base', href=base_url)
-        if soup.head:
-            soup.head.insert(0, new_base_tag)
-        else:
-            head_tag = soup.new_tag('head')
-            head_tag.insert(0, new_base_tag)
-            soup.insert(0, head_tag)
-    
-    return str(soup)
-
-def bypass_paywall(url):
-    """
-    Bypass paywall for a given url
-    """
-    if url.startswith("http"):
-        response = requests.get(url, headers=googlebot_headers)
-        response.encoding = response.apparent_encoding
-        return add_base_tag(response.text, response.url)
-
-    try:
-        return bypass_paywall("https://" + url)
-    except requests.exceptions.RequestException as e:
-        return bypass_paywall("http://" + url)
-
-
-@app.route("/")
-def main_page():
-    return flask.send_from_directory(".", "index.html")
-
-
-@app.route("/article", methods=["POST"])
-def show_article():
-    link = flask.request.form["link"]
-    try:
-        return bypass_paywall(link)
-    except requests.exceptions.RequestException as e:
-        return str(e), 400
-    except Exception as exc:
-        raise exc
-
-
-@app.route("/", defaults={"path": ""})
-@app.route("/<path:path>", methods=["GET"])
-def get_article(path):
-    full_url = request.url
-    parts = full_url.split("/", 4)
-    if len(parts) >= 5:
-        actual_url = "https://" + parts[4].lstrip("/")
-        try:
-            return bypass_paywall(actual_url)
-        except requests.exceptions.RequestException as e:
-            return str(e), 400
-        except e:
-            raise e
-    else:
-        return "Invalid URL", 400
-
-
-app.run(debug=False)

app/portable.py

@@ -1,3 +1,6 @@
+import os
+from urllib.parse import urljoin, urlparse
+
 import flask
 import re
 import requests
@@ -408,20 +411,21 @@ html = """
 
 
 def add_base_tag(html_content, original_url):
-    soup = BeautifulSoup(html_content, 'html.parser')
+    soup = BeautifulSoup(html_content, "html.parser")
     parsed_url = urlparse(original_url)
     base_url = f"{parsed_url.scheme}://{parsed_url.netloc}/"
 
-    if parsed_url.path and not parsed_url.path.endswith('/'):
-        base_url = urljoin(base_url, parsed_url.path.rsplit('/', 1)[0] + '/')
-    base_tag = soup.find('base')
 
+    # Handle paths that are not root, e.g., "https://x.com/some/path/w.html"
+    if parsed_url.path and not parsed_url.path.endswith("/"):
+        base_url = urljoin(base_url, parsed_url.path.rsplit("/", 1)[0] + "/")
+    base_tag = soup.find("base")
     if not base_tag:
-        new_base_tag = soup.new_tag('base', href=base_url)
+        new_base_tag = soup.new_tag("base", href=base_url)
         if soup.head:
             soup.head.insert(0, new_base_tag)
         else:
-            head_tag = soup.new_tag('head')
+            head_tag = soup.new_tag("head")
             head_tag.insert(0, new_base_tag)
             soup.insert(0, head_tag)
 
@@ -711,8 +715,8 @@ def show_article():
         return bypass_paywall(link)
     except requests.exceptions.RequestException as e:
         return str(e), 400
-    except Exception as exc:
+    except Exception as e:
-        raise exc
+        raise e
 
 
 @app.route("/", defaults={"path": ""})
@@ -732,4 +736,5 @@ def get_article(path):
         return "Invalid URL", 400
 
 
-app.run(host="0.0.0.0", port=5000, debug=False)
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=os.getenv("PORT") or 5000, debug=False)

app/requirements.txt

@@ -1,3 +1,4 @@
-flask
-requests
 bs4
+flask
+gunicorn
+requests

docker-compose.dev.yaml

@@ -0,0 +1,9 @@
+services:
+  13ft:
+    container_name: 13ft
+    hostname: 13ft
+    build:
+      context: .
+    restart: unless-stopped
+    ports:
+      - "5000:5000"

requirements.txt

@@ -1,3 +1,4 @@
-flask
-requests
 bs4
+flask
+gunicorn
+requests