From 2f6d487676e1829085548fca4bb2d837e6ad9148 Mon Sep 17 00:00:00 2001
From: Leon Haag-Fank <leon@haagfank.de>
Date: Fri, 1 Dec 2023 14:42:14 +0100
Subject: [PATCH] Initial commit

---
 README.md | 29 +++++++++++++++++++
 pep5-dl   | 85 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 114 insertions(+)
 create mode 100644 README.md
 create mode 100755 pep5-dl

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..2b3d713
--- /dev/null
+++ b/README.md
@@ -0,0 +1,29 @@
+# pep5-dl
+An unofficial script to download the slides of the 2023 PEP5 lecture.
+
+## Disclaimer
+This script uses your login credentials.
+If the script is run multiple times without terminating properly (before logout procedure) the Übungsgruppensystem might block you for some hours.
+Use at your own risk.
+
+## Installation
+Requires `playwright` (with `chromium` driver) and `PyPDF4`:
+```sh
+pip install playwright PyPDF4
+playwright install chromium
+```
+Then you just need to download the [`pep5-dl`](https://git.haagfank.de/LnLcFlx/pep5-dl/raw/branch/master/pep5-dl) file from this repository.
+
+### (Without `PyPDF4`)
+If you are on Linux and have `pdfunite` installed, you can alternatively supply `--merger=pdfunite` and do not need `PyPDF4`.
+
+Alternatively you can supply `--merger=none --keep --tmpdir=<DIR>` and simply download the individual PDFs to `<DIR>`.
+
+## Usage
+If you simply want to download all current slides into one file `slides.pdf` in the current directory, run
+```sh
+python pep5-dl '<USERNAME>' '<PASSWORD>'
+```
+where your have to replace `<USERNAME>` and `<PASSWORD>` with your credentials.
+
+For help and more options run `pep5-dl --help`.
diff --git a/pep5-dl b/pep5-dl
new file mode 100755
index 0000000..ec0d233
--- /dev/null
+++ b/pep5-dl
@@ -0,0 +1,85 @@
+#!/usr/bin/env python
+
+import os
+import glob
+import tempfile
+import argparse
+from playwright.sync_api import sync_playwright
+
+BASE = 'https://uebungen.physik.uni-heidelberg.de'
+LOGIN = BASE+'/uebungen/login.php'
+MATERIAL = BASE+'/c/image/d/vorlesung/20232/1735/material/'
+
+DEFAULT = os.path.join(os.getcwd(), 'slides.pdf')
+
+
+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=DEFAULT, help='Output path')
+    parser.add_argument('-f', '--force', action='store_true', help='Redownload file even if already present in TMPDIR')
+    parser.add_argument('-k', '--keep', action='store_true', help='Keep temporary files in TMPDIR')
+    parser.add_argument('-t', '--tmpdir', type=str, default=tempfile.gettempdir(), help='Temporary directory')
+    parser.add_argument('-m', '--merger', type=str, default='pypdf', choices=['pypdf', 'pdfunite', 'none'], help='Method used for merging PDFs')
+    args = parser.parse_args()
+    if args.user is None or args.pwd is None:
+        parser.error('You need to supply a username and password')
+        exit(1)
+
+    with sync_playwright() as p:
+        browser = p.chromium.launch()
+        page = browser.new_page()
+        page.goto(LOGIN)
+        page.locator("input[name='username']").fill(args.user)
+        page.locator("input[name='submit']").click()
+        page.locator("input[name='loginpass']").fill(args.pwd)
+        try:
+            page.locator("input[name='submit']").click()
+            if page.url == LOGIN:
+                print('could not login')
+            else:
+                i = 1
+                while True:
+                    name = 'PEP5_{:02d}.pdf'.format(i)
+                    if not os.path.isfile(name) or args.all:
+                        pdf = page.context.request.get(MATERIAL+name)
+                        if pdf.headers['content-type'] == 'application/pdf':
+                            print('Downloading {}...'.format(name))
+                            with open(os.path.join(args.tmpdir, name), 'wb') as f:
+                                f.write(pdf.body())
+                        else:
+                            break
+                    else:
+                        print('{} already downloaded'.format(name))
+                    i += 1
+        except Exception as e:
+            page.goto(BASE+'/uebungen/logout.php')
+            print(e)
+        finally:
+            page.goto(BASE+'/uebungen/logout.php')
+        browser.close()
+
+    glexpr = os.path.join(args.tmpdir, 'PEP5_*')
+    gl = glob.glob(glexpr)
+
+    if args.out is not None and args.out != '':
+        if args.merger == 'pypdf':
+            from PyPDF4 import PdfMerger
+            merger = PdfMerger()
+            for pdf in gl:
+                merger.append(pdf)
+            merger.write(args.out)
+            merger.close()
+        elif args.merger == 'pdfunite':
+            from subprocess import Popen
+            p = Popen('pdfunite {} {}'.format(glexpr, args.out), shell=True)
+            p.communicate()
+
+    if not args.keep and args.merger != 'none':
+        for f in gl:
+            os.remove(f)
+
+
+if __name__ == "__main__":
+    main()