From 7c770166a75b2930292e0c80ac466c21299ac7d3 Mon Sep 17 00:00:00 2001
From: Nick Hahn <nick.hahn@posteo.de>
Date: Thu, 15 Sep 2022 19:31:00 +0200
Subject: [PATCH] Add ability to specify multiple metapads

---
 README.md         |  4 ++--
 hedgedoc-image.py | 26 +++++++++++++-------------
 2 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/README.md b/README.md
index 7215df9..64ccbb3 100644
--- a/README.md
+++ b/README.md
@@ -36,12 +36,12 @@ pip install -r requirements.txt
 
 Start the extractor
 ```
-python hedgedoc-image.py meta_pad new_netloc
+python hedgedoc-image.py --replace new_netloc meta_pad1 meta_pad2 ...
 ```
 
 For example:
 ```
-python hedgedoc-image.py https://md.margau.net/dbk-meta pad.hacknang.de
+python hedgedoc-image.py --replace pad.hacknang.de https://md.margau.net/dbk-meta
 ```
 
 ### Produced files
diff --git a/hedgedoc-image.py b/hedgedoc-image.py
index dcb5d90..753fd44 100644
--- a/hedgedoc-image.py
+++ b/hedgedoc-image.py
@@ -2,7 +2,6 @@ import requests
 import json
 import re
 import argparse
-
 import os
 
 from urllib.parse import urlparse
@@ -12,7 +11,7 @@ from os.path import exists
 PATH = "images/"
 NEW_NETLOC = ""
 
-seen_pads = []
+seen_pads = set()
 
 pads_json = []
 
@@ -67,7 +66,7 @@ class PadPage:
 
     def download_and_process_content(self):
         print(f"Downloading pad at {self.old_url}")
-        seen_pads.append(self.old_url)
+        seen_pads.add(self.old_url)
         r = requests.get(self.old_url + "/download")
         if r.status_code == 200:
             self.content = r.text
@@ -109,9 +108,9 @@ class PadPage:
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="Recursivly downloads all images from a hedgedoc pad")
-    parser.add_argument("pad_url", metavar="N", type=str, nargs=1,
-                        help="url of the pad to start searching")
-    parser.add_argument("new_pad_url", metavar="N", type=str, nargs=1,
+    parser.add_argument("pad_url", metavar="N", type=str, nargs="+",
+                        help="urls of the pad to start searching")
+    parser.add_argument("--replace", dest="new_pad_url", metavar="B", type=str, nargs=1,
                         help="url of the new pad for generating the json")
 
     args = parser.parse_args()
@@ -123,19 +122,20 @@ if __name__ == "__main__":
             old_file = json.load(f)
 
         for entry in old_file:
-            seen_pads.append(entry["old_url"])
+            seen_pads.add(entry["old_url"])
 
         pads_json.extend(old_file)
         print(f"Seen Pads: {seen_pads}")
 
 
     NEW_NETLOC = args.new_pad_url[0]
-    pad = PadPage(args.pad_url[0])
-    pad.download_and_process_content()
-    pad.download_images()
-    pad.gather_linked_pads()
-    pads_json.append(pad.to_dict())
-    pad.recursive()
+    for pad_url in args.pad_url:
+        pad = PadPage(pad_url)
+        pad.download_and_process_content()
+        pad.download_images()
+        pad.gather_linked_pads()
+        pads_json.append(pad.to_dict())
+        pad.recursive()
 
     print(f"We have seen {len(seen_pads)} which were {seen_pads}")