Reducing image count

2026-07-17 19:47:51 -04:00
parent e64193639e
commit 8690334a80
1203 changed files with 2 additions and 291 deletions
@@ -66,25 +66,6 @@ foreach (var file in mdFiles)
    cards.Add(card);
 }
 // Copy PNGs to wwwroot/cards
 var cardsDir = Path.Combine(webWwwRoot, "cards");
 Directory.CreateDirectory(cardsDir);
 var pngFiles = Directory.GetFiles(docsDir, "*.png", SearchOption.AllDirectories);
 var pngMap = pngFiles
    .GroupBy(Path.GetFileName)
    .ToDictionary(g => g.Key!, g => g.First(), StringComparer.OrdinalIgnoreCase);
 foreach (var card in cards)
 {
    if (card.ImageFile == null) continue;
    if (pngMap.TryGetValue(card.ImageFile, out var src))
    {
        var dst = Path.Combine(cardsDir, card.ImageFile);
        File.Copy(src, dst, true);
    }
 }
 // Generate C# source file
 Directory.CreateDirectory(Path.GetDirectoryName(generatedFile)!);
 using var writer = new StreamWriter(generatedFile, false, Encoding.UTF8);
@@ -1,138 +0,0 @@
 import os
 import re
 import requests
 import time
 from concurrent.futures import ThreadPoolExecutor
 # Configuration
 DOCS_DIR = r"..\chrono.docs"
 CLOUD_CARDS_DIR = r"Cloud\wwwroot\cards"
 STANDALONE_CARDS_DIR = r"Standalone\wwwroot\cards"
 USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36"
 def get_card_names():
    card_names = []
    # Search for all .md files in chrono.docs
    for root, dirs, files in os.walk(DOCS_DIR):
        for file in files:
            if file.endswith(".md"):
                # Remove .md extension
                card_names.append(file[:-3])
    return card_names
 def slugify(card_name):
    # Manual overrides for slugs that don't follow the standard pattern
    overrides = {
        "APEX Starcruise": "apex-starcruiser",
        "Consummate Conspirator": "consomme-conspirator",
        "Librarian's Assistant": "librarian-assistant",
        "Violet Inquisitioner": "violet-inquisitor",
        "Breakdown": "break-down",
        "Da'Kad, Heretic Crusher": "da-kad-heretic-crusher",
        "Shae'Fan, Remembered": "shae-fan-remembered",
        "Possessed Prawn": "possessed-prawn-card",
        "P.O.G.O": "p-o-g-o",
        "A'kon, Starry Diviner": "a-kon-starry-diviner",
        "B.O.O.F.": "b-o-o-f",
        "Raiz, Pacifist's Conclusion": "raiz-pacifists-conclusion",
        "Spirit's Lament": "spirits-lament",
        "Overmind's Guilt": "overminds-guilt",
        "Entropy's End": "entropys-end",
        "Vor’kon, Eternal Source": "vor-kon-eternal-source",
        "Ta'kan the Tattle": "ta-kan-the-tattle",
    }
    # Fix potential encoding issues in card_name (e.g. smart quotes)
    # If the script is run in an environment where the filenames were read as mangled
    # we want to ensure we use the correct name for the filename and slug lookup.
    # Note: 'â€™' is the UTF-8 bytes for '’' interpreted as Windows-1252
    if isinstance(card_name, str):
        card_name = card_name.replace("â€™", "'").replace("’", "'")
    if card_name in overrides:
        return overrides[card_name]
    # Convert to lowercase, replace spaces/special chars with hyphens
    slug = card_name.lower()
    slug = re.sub(r'[^a-z0-9]+', '-', slug)
    slug = slug.strip('-')
    return slug
 def download_full_art(card_name):
    # Fix potential encoding issues in card_name (e.g. smart quotes)
    if isinstance(card_name, str):
        card_name = card_name.replace("â€™", "'").replace("’", "'")
    slug = slugify(card_name)
    url = f"https://www.playchrono.com/card/{slug}"
    print(f"Processing {card_name} ({url})...")
    try:
        response = requests.get(url, headers={"User-Agent": USER_AGENT}, timeout=10)
        if response.status_code != 200:
            print(f"  [ERROR] Failed to fetch page for {card_name}: {response.status_code}")
            return
        # Look for all data-lightbox-src and data-lightbox-alt pairs
        # We want the ones that end with "Full Art" and match our card name
        pattern = r'data-lightbox-src="([^"]+)"\s+data-lightbox-alt="([^"]+)"'
        matches = re.findall(pattern, response.text)
        full_art_url = None
        for src, alt in matches:
            if "Full Art" in alt and (card_name.lower() in alt.lower()):
                full_art_url = src
                break
        # Fallback to the first "Full Art" if no exact match (sometimes names might slightly differ)
        if not full_art_url:
            for src, alt in matches:
                if "Full Art" in alt:
                    full_art_url = src
                    break
        # Absolute fallback to any data-lightbox-src with the pattern if still nothing
        if not full_art_url:
            match = re.search(r'data-lightbox-src="(https://cdn\.playchrono\.com/latest/en_us/img/cards/set/1/[^"]+\.png)"', response.text)
            if match:
                full_art_url = match.group(1)
        if not full_art_url:
            print(f"  [INFO] No full art found for {card_name}")
            return
        print(f"  [FOUND] {full_art_url} for {card_name}")
        # Download image
        img_response = requests.get(full_art_url, headers={"User-Agent": USER_AGENT}, timeout=10)
        if img_response.status_code == 200:
            filename = f"fa{card_name}.png"
            # Save to Cloud
            os.makedirs(CLOUD_CARDS_DIR, exist_ok=True)
            with open(os.path.join(CLOUD_CARDS_DIR, filename), "wb") as f:
                f.write(img_response.content)
            # Save to Standalone
            os.makedirs(STANDALONE_CARDS_DIR, exist_ok=True)
            with open(os.path.join(STANDALONE_CARDS_DIR, filename), "wb") as f:
                f.write(img_response.content)
            print(f"  [SUCCESS] Saved {filename}")
        else:
            print(f"  [ERROR] Failed to download image for {card_name}: {img_response.status_code}")
    except Exception as e:
        print(f"  [ERROR] Exception for {card_name}: {e}")
 def main():
    card_names = get_card_names()
    print(f"Found {len(card_names)} cards to process.")
    # Use ThreadPoolExecutor for faster downloads
    with ThreadPoolExecutor(max_workers=5) as executor:
        executor.map(download_full_art, card_names)
 if __name__ == "__main__":
    main()
@@ -1,133 +0,0 @@
 """
 One-time script: Download card images from playchrono.com and add imageLink frontmatter.
 Usage:
    python process_cards.py
 Requires a saved HTML copy of https://www.playchrono.com/collections/cards
 with the embedded JSON.parse('...') card data.
 """
 import re
 import json
 import os
 import urllib.request
 import sys
 # Adjust these paths for your environment
 html_file = r"../playchrono_cards_page.html"
 docs_dir = r"../../chrono.docs"
 if not os.path.exists(html_file):
    # Fallback: search for saved tool output
    possible = [f for f in os.listdir(r"C:\Users\jonmc\.local\share\opencode\tool-output")
                if f.startswith("tool_") and os.path.isfile(os.path.join(r"C:\Users\jonmc\.local\share\opencode\tool-output", f))]
    if possible:
        html_file = os.path.join(r"C:\Users\jonmc\.local\share\opencode\tool-output", possible[-1])
 with open(html_file, 'r', encoding='utf-8') as f:
    html = f.read()
 start_marker = "JSON.parse('"
 idx = html.find(start_marker)
 if idx < 0:
    print("ERROR: Could not find JSON.parse in HTML")
    sys.exit(1)
 start = idx + len(start_marker)
 quote_end = html.find("')", start)
 if quote_end < 0:
    print("ERROR: Could not find closing '")
    sys.exit(1)
 raw_json_str = html[start:quote_end]
 json_str = raw_json_str.encode('utf-8').decode('unicode_escape')
 json_str = json_str.replace('\\/', '/')
 try:
    cards = json.loads(json_str)
 except json.JSONDecodeError as e:
    print(f"ERROR parsing JSON: {e}")
    sys.exit(1)
 print(f"Found {len(cards)} cards")
 name_to_image = {}
 for card in cards:
    name = card.get('name', '')
    image_url = card.get('image_url', '')
    if name and image_url:
        name_to_image[name.lower()] = image_url
    counterpart = card.get('counterpart')
    if counterpart and isinstance(counterpart, dict):
        cname = counterpart.get('name', '')
        cimage = counterpart.get('image_url', '')
        if cname and cimage:
            name_to_image[cname.lower()] = cimage
 print(f"Built mapping for {len(name_to_image)} card names")
 md_files = [f for f in os.listdir(docs_dir) if f.endswith('.md')]
 print(f"Found {len(md_files)} markdown files")
 processed = 0
 downloaded = 0
 matched = 0
 for md_file in sorted(md_files):
    filepath = os.path.join(docs_dir, md_file)
    card_name = md_file[:-3]
    card_name_lower = card_name.lower()
    if card_name_lower not in name_to_image:
        continue
    matched += 1
    image_url = name_to_image[card_name_lower]
    png_filename = f"{card_name}.png"
    png_filepath = os.path.join(docs_dir, png_filename)
    if not os.path.exists(png_filepath):
        try:
            print(f"  DL: {png_filename}")
            req = urllib.request.Request(image_url, headers={
                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36'
            })
            with urllib.request.urlopen(req) as response:
                with open(png_filepath, 'wb') as out:
                    out.write(response.read())
            downloaded += 1
        except Exception as e:
            print(f"  ERR: {png_filename} - {e}")
            continue
    with open(filepath, 'r', encoding='utf-8') as f:
        content = f.read()
    has_image_link = 'imageLink:' in content
    img_ref = f"![[{png_filename}]]"
    has_img_ref = img_ref in content
    if has_image_link and has_img_ref:
        continue
    modified = content
    if not has_image_link:
        modified = modified.rstrip()
        if modified.endswith('---'):
            modified = modified[:-3] + f'imageLink: "[[{png_filename}]]"\n---'
        else:
            modified = modified + f'\nimageLink: "[[{png_filename}]]"\n'
    if not has_img_ref:
        modified = modified.rstrip() + f'\n\n\n{img_ref}\n'
    with open(filepath, 'w', encoding='utf-8') as f:
        f.write(modified)
    processed += 1
 print(f"\nDone! Matched: {matched}, Downloaded: {downloaded}, Updated markdown: {processed}")
 print(f"Skipped (no card match): {len(md_files) - matched}")
--- a/Show More
+++ b/Show More