From 3e25d664745ed0a99d7b691157333478679c4131 Mon Sep 17 00:00:00 2001
From: Leon Haag-Fank <leon@haagfank.de>
Date: Wed, 3 Apr 2024 15:43:39 +0200
Subject: [PATCH] Initial commit

---
 README.md | 23 +++++++++++++++
 zeit-dl   | 85 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 108 insertions(+)
 create mode 100644 README.md
 create mode 100755 zeit-dl

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..0f6f0e4
--- /dev/null
+++ b/README.md
@@ -0,0 +1,23 @@
+# zeit-dl
+An unofficial script to download PDF/EPUB/audio files from your Die ZEIT Digitalabo.
+
+## Disclaimer
+This script uses your login credentials.
+Use at your own risk.
+
+## Installation
+Requires `playwright` (with `chromium` driver):
+```sh
+pip install playwright
+playwright install chromium
+```
+Then you just need to download the [`zeit-dl`](https://git.haagfank.de/LnLcFlx/zeit-dl/raw/branch/master/zeit-dl) file from this repository.
+
+## Usage
+If you simply want to download the current issue of Die ZEIT as pdf run
+```sh
+python zeit-dl '<USERNAME>' '<PASSWORD>'
+```
+where your have to replace `<USERNAME>` and `<PASSWORD>` with your credentials.
+
+For help and more options run `zeit-dl --help`.
diff --git a/zeit-dl b/zeit-dl
new file mode 100755
index 0000000..4047d20
--- /dev/null
+++ b/zeit-dl
@@ -0,0 +1,85 @@
+#!/usr/bin/env python
+
+import os
+import re
+import argparse
+from playwright.sync_api import sync_playwright
+
+EPAPER = 'https://epaper.zeit.de'
+MEINE = 'https://meine.zeit.de'
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('user', type=str, help='Username')
+    parser.add_argument('pwd', type=str, help='Password')
+    parser.add_argument('-o', '--out', type=str, default=os.getcwd(), help='Output directory')
+    parser.add_argument('-a', '--abo', type=str, choices=['diezeit', 'zeitcampus', 'zeit-audio'], default='diezeit', help='Abo')
+    parser.add_argument('-i', '--issue', type=str, help='Ausgabe (meistens DD.MM.YYYY)')
+    parser.add_argument('-t', '--type', type=str, choices=['pdf', 'epub', 'mp3'], default='pdf', help='Dateiformat')
+    parser.add_argument('-f', '--force', action='store_true', help='Redownload file even if already present')
+    args = parser.parse_args()
+    if args.user is None or args.pwd is None:
+        parser.error('You need to supply a username and password')
+
+    with sync_playwright() as p:
+        browser = p.chromium.launch()
+        page = browser.new_page()
+        page.goto(MEINE+'/anmelden')
+        page.locator("input[id='login_email']").fill(args.user)
+        page.locator("input[id='login_pass']").fill(args.pwd)
+        try:
+            page.locator("input[type='submit']").click()
+            if page.url == MEINE+'/anmelden':
+                print('could not login')
+            else:
+                download(page, args)
+        except Exception as e:
+            page.goto(MEINE+'/abmelden')
+            print(e)
+        finally:
+            page.goto(MEINE+'/abmelden')
+            print('finally: logout')
+        browser.close()
+
+
+def download(page, args):
+    if args.abo == 'zeit-audio':
+        print('not yet implemented')
+    else:
+        if args.issue is None:
+            page.goto(EPAPER+'/abo/'+args.abo)
+            page.locator("div.epaper-highlighted > a.btn").click(force=True)
+            issue = page.url.split('/')[-1]
+        else:
+            page.goto(EPAPER+'/abo/'+args.abo+'/'+args.issue)
+            issue = args.issue
+
+        filename = '{}-{}.{}'.format(args.abo, issue, args.type)
+        filepath = os.path.join(args.out, filename)
+        if os.path.isfile(filepath):
+            print('Issue already exists:', filepath)
+            return 1
+
+        dl_btns = page.locator("div.download-buttons > a.btn").all()
+        url = None
+        for btn in dl_btns:
+            js_obj = btn.get_attribute('data-wt-click')
+            match = re.search(r"9: ?'([^']*)'", js_obj)
+            if match.group(1) == args.type:
+                print(js_obj)
+                url = EPAPER+btn.get_attribute('href')
+                continue
+        if url is None:
+            print('Could not find appropriate button for', args.type)
+            return 1
+
+        file = page.context.request.get(url)
+        if file.headers['content-type'] != 'text/html':
+            print('Downloading {}...'.format(filename))
+            with open(filepath, 'wb') as f:
+                f.write(file.body())
+
+
+if __name__ == "__main__":
+    main()