From 2232f289f09af34076d116794a25934bccf692ff Mon Sep 17 00:00:00 2001
From: FrederikBaerentsen <frederik+gitea@baerentsen.net>
Date: Mon, 20 Jan 2025 22:41:22 +0100
Subject: [PATCH] Initial upload of working copy

---
 instDownloader.py | 116 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 116 insertions(+)
 create mode 100644 instDownloader.py

diff --git a/instDownloader.py b/instDownloader.py
new file mode 100644
index 0000000..044d265
--- /dev/null
+++ b/instDownloader.py
@@ -0,0 +1,116 @@
+import requests
+from bs4 import BeautifulSoup
+
+def get_instruction_links(set_id):
+    # Construct the URL
+    url = f"https://rebrickable.com/instructions/{set_id}"
+    
+    # Load the page
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
+}
+    response = requests.get(url, headers=headers)
+    if response.status_code != 200:
+        print(f"Failed to load page. Status code: {response.status_code}")
+        return []
+    
+    # Parse the HTML content
+    soup = BeautifulSoup(response.content, 'html.parser')
+    
+    # Collect all <img> tags with "LEGO Building Instructions" in the alt attribute
+    found_tags = []
+    links = []
+    for a_tag in soup.find_all('a', href=True):
+        img_tag = a_tag.find('img', alt=True)
+        if img_tag and "LEGO Building Instructions" in img_tag['alt']:
+            found_tags.append((img_tag['alt'], a_tag['href']))  # Save alt and href
+    
+    # Filter links containing "V29"
+    v29_links = []
+    for alt_text, href in found_tags:
+        if "V29" in alt_text or "V 29" in alt_text:
+            # Check for x/y format or assign sequential numbers if missing
+            if '/' in alt_text:
+                parts = alt_text.split('/')[0]
+                try:
+                    numbers = [int(num) for num in parts.replace("-", " ").split() if num.isdigit()]
+                    if len(numbers) == 2:
+                        x, y = numbers
+                        if x <= 10 and y <= 10:  # Only consider valid x/y pairs
+                            v29_links.append((x, y, href))
+                except ValueError:
+                    print(f"Failed to parse x/y in alt text: {alt_text}")
+            else:
+                # Assign sequential numbers if no x/y format is found
+                v29_links.append((len(v29_links) + 1, None, href))
+    
+    # Sort the V29 links by x value (if available)
+    v29_links.sort(key=lambda link: link[0])
+    
+    # If no V29 links found, return all found tags
+    if not v29_links:
+        print("No instructions with 'V29' found. Found the following tags:")
+        for alt_text, href in found_tags:
+            print(f"ALT: {alt_text}, HREF: {href}")
+        return found_tags  # Return all links for downloading
+    
+    return v29_links
+
+
+def normalize_alt(alt_text):
+    # Normalize the alt text to a file-friendly name
+    normalized = alt_text.replace("/", "-").replace(",", "").replace(" ", "-").replace(".", "")
+    return normalized
+
+
+def download_instructions(set_id, links, is_v29=True):
+    for index, link in enumerate(links):
+        if is_v29:
+            # V29 links have three elements: (x, y, href)
+            href = link[2]  # Extract href from the tuple
+            if len(links) == 1:
+                # Single link, use the set ID only
+                file_name = f"{set_id}.pdf"
+            else:
+                # Multiple links, use the x value
+                file_name = f"{set_id}+{index + 1}.pdf"
+        else:
+            # Non-V29 links have two elements: (alt_text, href)
+            alt_text, href = link
+            normalized_name = normalize_alt(alt_text)
+            file_name = f"{set_id}-{normalized_name}.pdf"
+        
+        download_url = f"https://rebrickable.com{href}"  # Full URL
+        print(f"Downloading: {download_url} -> {file_name}")
+        
+        # Fetch the file
+        response = requests.get(download_url, stream=True)
+        if response.status_code == 200:
+            with open(file_name, 'wb') as file:
+                for chunk in response.iter_content(chunk_size=1024):
+                    file.write(chunk)
+            print(f"Saved: {file_name}")
+        else:
+            print(f"Failed to download {download_url}. Status code: {response.status_code}")
+
+# Example usage
+if __name__ == "__main__":
+    import argparse
+    
+    # Set up argument parser
+    parser = argparse.ArgumentParser(description="Download LEGO building instructions for a given set ID.")
+    parser.add_argument("set_id", type=str, help="The LEGO set ID (e.g., 10313-1)")
+    args = parser.parse_args()
+    
+    set_id = args.set_id
+    instruction_links = get_instruction_links(set_id)
+    
+    if instruction_links:
+        if isinstance(instruction_links[0], tuple) and len(instruction_links[0]) == 3:  # V29 links
+            print(f"Found {len(instruction_links)} V29 instruction links.")
+            download_instructions(set_id, instruction_links)
+        else:  # Non-V29 links
+            print(f"Found {len(instruction_links)} non-V29 instruction links.")
+            download_instructions(set_id, instruction_links, is_v29=False)
+    else:
+        print("No instruction links found.")