From 11b5541c0f9feac4a3f7e808a4afdeee3b10c7e5 Mon Sep 17 00:00:00 2001
From: Nick Hahn <nick.hahn@posteo.de>
Date: Fri, 16 Sep 2022 23:06:07 +0200
Subject: [PATCH] Also save pad content on crawl

---
 hedgedoc-image.py | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/hedgedoc-image.py b/hedgedoc-image.py
index 753fd44..05dd570 100644
--- a/hedgedoc-image.py
+++ b/hedgedoc-image.py
@@ -8,15 +8,17 @@ from urllib.parse import urlparse
 from typing import List
 from os.path import exists
 
-PATH = "images/"
+IMG_PATH = "images/"
+PAD_PATH = "pads/"
 NEW_NETLOC = ""
 
 seen_pads = set()
 
 pads_json = []
 
-os.makedirs(PATH, exist_ok=True)
-os.makedirs(PATH + "uploads", exist_ok=True)
+os.makedirs(PAD_PATH, exist_ok=True)
+os.makedirs(IMG_PATH, exist_ok=True)
+os.makedirs(IMG_PATH + "uploads", exist_ok=True)
 
 
 class Image:
@@ -27,7 +29,7 @@ class Image:
 
     def download(self):
         r = requests.get(self.old_url)
-        p = PATH + urlparse(self.old_url).path
+        p = IMG_PATH + urlparse(self.old_url).path
         with open(p, 'wb') as f:
             f.write(r.content)
             print(f"Downloaded image {self.old_url} to {p}")
@@ -70,6 +72,8 @@ class PadPage:
         r = requests.get(self.old_url + "/download")
         if r.status_code == 200:
             self.content = r.text
+            with open(PAD_PATH + urlparse(self.old_url).path + ".md", "w") as f:
+                f.write(self.content)
             num = self._find_images()
             print(f"Found {num} images")
         else: