add new codes, parsed by Claude AI

.gitignore

@@ -0,0 +1,4 @@
+mergeCodes.py
+__pycache__/
+*.pyc
+*.pyo

merge_shiftcodes.py

@@ -0,0 +1,133 @@
+#!/usr/bin/env python3
+"""
+Merge shift codes from GitHub repositories and web scrapers.
+"""
+
+import json
+import requests
+from datetime import datetime, timezone
+from collections import OrderedDict
+
+from scrapers import mentalmars, gamedevtools, xsmashx88x
+
+REPOS = [
+    "https://raw.githubusercontent.com/Majawat/autoshift-codes/main/shiftcodes.json",
+    "https://raw.githubusercontent.com/ugoogalizer/autoshift-codes/main/shiftcodes.json",
+    "https://raw.githubusercontent.com/DankestMemeLord/autoshift-codes/main/shiftcodes.json",
+    "https://raw.githubusercontent.com/zarmstrong/autoshift-codes/main/shiftcodes.json",
+]
+
+SCRAPERS = [
+    mentalmars,
+    gamedevtools,
+    xsmashx88x,
+]
+
+
+def fetch_json(url):
+    print(f"Fetching {url}...")
+    try:
+        response = requests.get(url, timeout=30)
+        response.raise_for_status()
+        return response.json()
+    except Exception as e:
+        print(f"  Error fetching {url}: {e}")
+        return None
+
+
+def merge_codes(all_data):
+    """Merge codes from multiple sources, keeping the entry with the most recent archived date."""
+    merged = OrderedDict()
+
+    for data in all_data:
+        if not data or not isinstance(data, list) or len(data) == 0:
+            continue
+
+        # Handles [{meta, codes}] (repo JSON) or a flat list of code dicts (scrapers)
+        if isinstance(data[0], dict) and "codes" in data[0]:
+            codes = data[0].get("codes", [])
+        else:
+            codes = data
+
+        for entry in codes:
+            if not isinstance(entry, dict):
+                continue
+            code = entry.get("code")
+            if not code:
+                continue
+
+            if code in merged:
+                if entry.get("archived", "") > merged[code].get("archived", ""):
+                    merged[code] = entry
+            else:
+                merged[code] = entry
+
+    return list(merged.values())
+
+
+def main():
+    print("Starting shift codes merge...\n")
+
+    all_data = []
+
+    # --- GitHub repos ---
+    repo_count = 0
+    for url in REPOS:
+        data = fetch_json(url)
+        if data:
+            all_data.append(data)
+            repo_count += 1
+    print(f"\nFetched {repo_count}/{len(REPOS)} repositories")
+
+    # --- Web scrapers ---
+    print()
+    scraper_total = 0
+    for scraper in SCRAPERS:
+        try:
+            codes = scraper.scrape()
+            if codes:
+                all_data.append(codes)
+                scraper_total += len(codes)
+        except Exception as e:
+            print(f"  [ERROR] {scraper.__name__} failed: {e}")
+
+    print(f"\nScraped {scraper_total} codes from web sources")
+
+    if not all_data:
+        print("\nError: No data from any source!")
+        return
+
+    # --- Merge & sort ---
+    merged = merge_codes(all_data)
+    print(f"Total unique codes after merge: {len(merged)}")
+
+    # Sort A→Z by game, then newest-first within each game
+    merged.sort(key=lambda x: (x.get("game", ""), x.get("archived", "")), reverse=False)
+    merged.sort(key=lambda x: x.get("game", ""))
+
+    output = [
+        {
+            "meta": {
+                "version": "0.1",
+                "description": "GitHub Alternate Source for Shift Codes",
+                "attribution": "Data sourced from mentalmars.com, gamedevtools.net, xsmashx88x.github.io, and GitHub forks",
+                "permalink": "https://raw.githubusercontent.com/Majawat/autoshift-codes/main/shiftcodes.json",
+                "generated": {
+                    "human": datetime.now(timezone.utc).isoformat()
+                },
+                "newcodecount": len(merged)
+            },
+            "codes": merged
+        }
+    ]
+
+    output_file = "shiftcodes.json"
+    print(f"\nWriting to {output_file}...")
+    with open(output_file, "w", encoding="utf-8") as f:
+        json.dump(output, f, indent=2, ensure_ascii=False)
+
+    print(f"[SUCCESS] {len(merged)} unique codes written to {output_file}")
+
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,2 @@
+requests
+beautifulsoup4

scrapers/gamedevtools.py

@@ -0,0 +1,79 @@
+import re
+import requests
+from bs4 import BeautifulSoup
+from datetime import datetime, timezone
+
+from .utils import CODE_PATTERN, format_expires
+
+PAGES = [
+    ("Borderlands 4", "https://gamedevtools.net/shift-codes-borderlands-4"),
+]
+
+_HEADERS = {"User-Agent": "Mozilla/5.0 (compatible; autoshift-scraper/1.0)"}
+
+# en-dash or hyphen between code and description
+_SEP = re.compile(r"\s*[–\-]+\s*")
+
+
+def _scrape_page(game, url):
+    try:
+        resp = requests.get(url, timeout=30, headers=_HEADERS)
+        resp.raise_for_status()
+    except Exception as e:
+        print(f"  [gamedevtools] Error fetching {url}: {e}")
+        return []
+
+    soup = BeautifulSoup(resp.text, "html.parser")
+    codes = []
+
+    for li in soup.find_all("li"):
+        strong = li.find("strong")
+        if not strong:
+            continue
+
+        code = strong.get_text(strip=True)
+        if not CODE_PATTERN.match(code):
+            continue
+
+        full_text = li.get_text(" ", strip=True)
+        rest = _SEP.split(full_text[len(code):].strip(), maxsplit=1)
+        description = rest[-1].strip() if rest else ""
+
+        # Split "REWARD, expires DATE"
+        expires_str = ""
+        if re.search(r",\s*expires\s+", description, re.IGNORECASE):
+            parts = re.split(r",\s*expires\s+", description, maxsplit=1, flags=re.IGNORECASE)
+            reward      = parts[0].strip()
+            expires_str = parts[1].strip()
+        else:
+            reward = description
+
+        codes.append({
+            "code":     code,
+            "type":     "shift",
+            "game":     game,
+            "platform": "universal",
+            "reward":   reward,
+            "archived": datetime.now(timezone.utc).isoformat(),
+            "expires":  format_expires(expires_str),
+            "expired":  False,
+            "link":     url,
+        })
+
+    return codes
+
+
+def scrape():
+    print("Scraping gamedevtools.net...")
+    codes = []
+    for game, url in PAGES:
+        page_codes = _scrape_page(game, url)
+        print(f"  {game}: {len(page_codes)} codes")
+        codes.extend(page_codes)
+    print(f"  Total from gamedevtools: {len(codes)}")
+    return codes
+
+
+if __name__ == "__main__":
+    for entry in scrape():
+        print(entry)

scrapers/mentalmars.py

@@ -0,0 +1,98 @@
+import requests
+from bs4 import BeautifulSoup
+from datetime import datetime, timezone
+
+from .utils import CODE_PATTERN, parse_date, format_expires
+
+PAGES = [
+    ("Borderlands 4",           "https://mentalmars.com/game-news/borderlands-4-shift-codes/"),
+    ("Borderlands 3",           "https://mentalmars.com/game-news/borderlands-3-golden-keys/"),
+    ("Tiny Tina's Wonderlands", "https://mentalmars.com/game-news/tiny-tinas-wonderlands-shift-codes/"),
+    ("Borderlands 2",           "https://mentalmars.com/game-news/borderlands-2-golden-keys/"),
+]
+
+_HEADERS = {"User-Agent": "Mozilla/5.0 (compatible; autoshift-scraper/1.0)"}
+
+
+def _scrape_page(game, url):
+    try:
+        resp = requests.get(url, timeout=30, headers=_HEADERS)
+        resp.raise_for_status()
+    except Exception as e:
+        print(f"  [mentalmars] Error fetching {url}: {e}")
+        return []
+
+    soup = BeautifulSoup(resp.text, "html.parser")
+    codes = []
+
+    for table in soup.find_all("table"):
+        thead = table.find("thead")
+        if not thead:
+            continue
+        headers = [th.get_text(strip=True).lower() for th in thead.find_all("th")]
+
+        # Require a column whose header contains "code"
+        code_col = next((i for i, h in enumerate(headers) if "code" in h), None)
+        if code_col is None:
+            continue
+
+        reward_col  = next((i for i, h in enumerate(headers) if "reward" in h), 0)
+        added_col   = next((i for i, h in enumerate(headers) if "added" in h), 1)
+        expires_col = next((i for i, h in enumerate(headers) if "expir" in h), 3)
+
+        tbody = table.find("tbody")
+        if not tbody:
+            continue
+
+        for row in tbody.find_all("tr"):
+            cells = row.find_all("td")
+            if len(cells) <= code_col:
+                continue
+
+            code_cell = cells[code_col]
+            code_tag  = code_cell.find("code")
+            if not code_tag:
+                continue
+
+            code = code_tag.get_text(strip=True)
+            if not CODE_PATTERN.match(code):
+                continue
+
+            expired = bool(code_cell.find("s"))
+
+            reward      = cells[reward_col].get_text(" ", strip=True)  if len(cells) > reward_col  else ""
+            added_str   = cells[added_col].get_text(strip=True)        if len(cells) > added_col   else ""
+            expires_str = cells[expires_col].get_text(strip=True)      if len(cells) > expires_col else ""
+
+            added_dt = parse_date(added_str)
+            archived = (added_dt or datetime.now(timezone.utc)).isoformat()
+
+            codes.append({
+                "code":     code,
+                "type":     "shift",
+                "game":     game,
+                "platform": "universal",
+                "reward":   reward,
+                "archived": archived,
+                "expires":  format_expires(expires_str),
+                "expired":  expired,
+                "link":     url,
+            })
+
+    return codes
+
+
+def scrape():
+    print("Scraping mentalmars.com...")
+    codes = []
+    for game, url in PAGES:
+        page_codes = _scrape_page(game, url)
+        print(f"  {game}: {len(page_codes)} codes")
+        codes.extend(page_codes)
+    print(f"  Total from mentalmars: {len(codes)}")
+    return codes
+
+
+if __name__ == "__main__":
+    for entry in scrape():
+        print(entry)

scrapers/utils.py

@@ -0,0 +1,33 @@
+import re
+from datetime import datetime, timezone
+
+CODE_PATTERN = re.compile(r'^[A-Z0-9]{5}-[A-Z0-9]{5}-[A-Z0-9]{5}-[A-Z0-9]{5}-[A-Z0-9]{5}$')
+
+_DATE_FORMATS = [
+    "%b %d, %Y",   # May 1, 2026
+    "%B %d, %Y",   # May 01, 2026
+    "%d %B %Y",    # 1 May 2026
+    "%d %b %Y",    # 1 May 2026 (abbrev)
+    "%Y-%m-%d",    # 2026-05-01
+    "%m/%d/%Y",    # 4/6/2026
+]
+
+def parse_date(s):
+    if not s:
+        return None
+    s = s.strip()
+    for fmt in _DATE_FORMATS:
+        try:
+            return datetime.strptime(s, fmt).replace(tzinfo=timezone.utc)
+        except ValueError:
+            continue
+    return None
+
+def format_expires(s):
+    """Normalise an expiry string to YYYY-MM-DD, 'Never', or 'Unknown'."""
+    dt = parse_date(s)
+    if dt:
+        return dt.strftime("%Y-%m-%d")
+    if s and s.strip().lower() in ("never", "ued", "unlimited", "n/a"):
+        return "Never"
+    return "Unknown"