fix: 부스 UI 변경 대응

booth_checker/__main__.py

@@ -8,6 +8,7 @@
 import uuid
 import logging
 import threading
+from collections import defaultdict
 from datetime import datetime, timedelta
 from time import sleep
 from concurrent.futures import ThreadPoolExecutor
@@ -255,6 +256,80 @@ def generate_changelog_and_summary(item_data, download_url_list, version_json):
     return changelog_html_path, s3_object_url, summary_result, diff_found, None
 
 
+def _normalize_fbx_entries(fbx_records):
+    entries = []
+    for path_str, file_hash in fbx_records.items():
+        entries.append({'basename': os.path.basename(path_str), 'hash': file_hash})
+    return entries
+
+
+def _calculate_fbx_diff_by_name_hash(previous_fbx, current_fbx):
+    previous_entries = _normalize_fbx_entries(previous_fbx)
+    current_entries = _normalize_fbx_entries(current_fbx)
+
+    previous_by_key = defaultdict(list)
+    current_by_key = defaultdict(list)
+    for entry in previous_entries:
+        previous_by_key[(entry['basename'], entry['hash'])].append(entry)
+    for entry in current_entries:
+        current_by_key[(entry['basename'], entry['hash'])].append(entry)
+
+    remaining_previous = []
+    for key, entries in previous_by_key.items():
+        current_matches = current_by_key.get(key, [])
+        match_count = min(len(entries), len(current_matches))
+        if match_count < len(entries):
+            remaining_previous.extend(entries[match_count:])
+        if match_count < len(current_matches):
+            current_by_key[key] = current_matches[match_count:]
+        else:
+            current_by_key[key] = []
+
+    remaining_current = []
+    for entries in current_by_key.values():
+        remaining_current.extend(entries)
+
+    previous_by_name = defaultdict(list)
+    current_by_name = defaultdict(list)
+    for entry in remaining_previous:
+        previous_by_name[entry['basename']].append(entry)
+    for entry in remaining_current:
+        current_by_name[entry['basename']].append(entry)
+
+    added = []
+    changed = []
+    deleted = []
+
+    for name in sorted(set(previous_by_name) | set(current_by_name)):
+        previous_list = sorted(previous_by_name.get(name, []), key=lambda e: e['hash'])
+        current_list = sorted(current_by_name.get(name, []), key=lambda e: e['hash'])
+        if previous_list and current_list:
+            change_count = min(len(previous_list), len(current_list))
+            changed.extend(current_list[:change_count])
+            added.extend(current_list[change_count:])
+            deleted.extend(previous_list[change_count:])
+        elif current_list:
+            added.extend(current_list)
+        elif previous_list:
+            deleted.extend(previous_list)
+
+    return added, changed, deleted
+
+
+def _format_fbx_display_names(entries, used_name_counts):
+    names = []
+    for entry in sorted(entries, key=lambda e: (e['basename'], e['hash'])):
+        base = entry['basename']
+        index = used_name_counts.get(base, 0)
+        if index == 0:
+            display_name = base
+        else:
+            display_name = f'{base}({index})'
+        used_name_counts[base] = index + 1
+        names.append(display_name)
+    return names
+
+
 def generate_fbx_changelog_and_summary(item_data, download_url_list, version_json):
     """Generates changelog information for FBX-only tracking."""
     previous_fbx = version_json.get('fbx-files', {}) or {}
@@ -269,44 +344,19 @@ def generate_fbx_changelog_and_summary(item_data, download_url_list, version_jso
             logger.error(f'An error occurred while parsing {filename}: {e}')
             logger.debug(traceback.format_exc())
 
-    previous_hashes = {file_hash for file_hash in previous_fbx.values()}
-    current_hashes = {file_hash for file_hash in current_fbx.values()}
-
-    added = []
-    changed = []
-    deleted = []
-
-    previous_remaining = dict(previous_fbx)
-    current_remaining = dict(current_fbx)
-
-    for name in set(previous_fbx.keys()) & set(current_fbx.keys()):
-        old_hash = previous_fbx[name]
-        new_hash = current_fbx[name]
-        if old_hash != new_hash:
-            changed.append(name)
-        previous_remaining.pop(name, None)
-        current_remaining.pop(name, None)
-
-    for name, new_hash in current_remaining.items():
-        if new_hash in previous_hashes:
-            continue
-        added.append(name)
-
-    for name, old_hash in previous_remaining.items():
-        if old_hash in current_hashes:
-            continue
-        deleted.append(name)
+    added_entries, changed_entries, deleted_entries = _calculate_fbx_diff_by_name_hash(previous_fbx, current_fbx)
 
-    if not added and not changed and not deleted:
+    if not added_entries and not changed_entries and not deleted_entries:
         logger.info('No FBX hash differences detected; skipping changelog generation.')
         return None, None, None, False, current_fbx
 
     path_list = []
-    for name in sorted(added):
+    used_name_counts = {}
+    for name in _format_fbx_display_names(added_entries, used_name_counts):
         path_list.append({'line_str': name, 'status': 1})
-    for name in sorted(changed):
+    for name in _format_fbx_display_names(changed_entries, used_name_counts):
         path_list.append({'line_str': name, 'status': 3})
-    for name in sorted(deleted):
+    for name in _format_fbx_display_names(deleted_entries, used_name_counts):
         path_list.append({'line_str': name, 'status': 2})
 
     tree = build_tree(path_list)
@@ -874,15 +924,6 @@ def strftime_now():
     while True:
         logger.info("BoothChecker cycle started")
 
-        # BOOTH Heartbeat check once per cycle
-        try:
-            logger.info('Checking BOOTH heartbeat')
-            requests.get("https://booth.pm", timeout=10)
-        except requests.RequestException as e:
-            logger.error(f'BOOTH heartbeat failed: {e}. Skipping this cycle.')
-            sleep(refresh_interval)
-            continue
-
         # Recreate temporary folders
         recreate_folder("./download")
         recreate_folder("./process")

booth_checker/booth.py

@@ -9,14 +9,17 @@ def _extract_download_info(div, link_selector, filename_selector):
     if not download_link or not filename_div:
         return None
 
-    href = download_link.get("data-href")
-    filename = filename_div.get_text()
+    href = download_link.get("data-href") or download_link.get("href")
+    filename = filename_div.get_text(strip=True)
 
-    if not href:
+    if not href or not filename:
         return None
 
-    href = re.sub(r'[^0-9]', '', href)
-    return [href, filename]
+    match = re.search(r'/downloadables/(\d+)', href)
+    if not match:
+        return None
+
+    return [match.group(1), filename]
 
 def _crawling_base(url, cookie, selectors, shortlist, thumblist, product_only_filter=None):
     response = requests.get(url=url, cookies=cookie)
@@ -72,9 +75,19 @@ def crawling(order_num, product_only, cookie, shortlist=None, thumblist=None):
         'product_info_selector': 'a',
         'product_info_index': 1,
         'thumb_selector': 'img',
-        'download_item_selector': 'div.legacy-list-item__center, div[data-test="downloadable"]',
-        'download_link_selector': 'a.nav-reverse, div.js-download-button',
-        'filename_selector': 'div.flex-\\[1\\] b'
+        'download_item_selector': (
+            'div.legacy-list-item__center, '
+            'div.mt-16.desktop\\:flex.desktop\\:justify-between.desktop\\:items-center'
+        ),
+        'download_link_selector': (
+            'div.js-download-button[data-test="downloadable"][data-href*="/downloadables/"], '
+            'a.nav-reverse[href*="/downloadables/"]'
+        ),
+        'filename_selector': (
+            'div.min-w-0.u-text-wrap b, '
+            'div.min-w-0.break-words.whitespace-pre-line, '
+            'div.flex-\\[1\\] b'
+        )
     }
     return _crawling_base(url, cookie, selectors, shortlist, thumblist, product_only_filter=product_only)
 
@@ -85,9 +98,9 @@ def crawling_gift(order_num, cookie, shortlist=None, thumblist=None):
         'product_div_class': 'rounded-16 bg-white p-40 mobile:px-16 mobile:pt-24 mobile:pb-40 mobile:rounded-none',
         'product_info_selector': 'div.mt-24.text-left a',
         'thumb_selector': 'img',
-        'download_item_selector': 'div.w-full.text-left, div[data-test="downloadable"]',
-        'download_link_selector': 'a.no-underline.flex.items-center.flex.gap-4, div.js-download-button',
-        'filename_selector': "div[class='min-w-0 break-words whitespace-pre-line']"
+        'download_item_selector': 'div.mt-16.desktop\\:flex.desktop\\:justify-between.desktop\\:items-center',
+        'download_link_selector': 'div.js-download-button[data-test="downloadable"][data-href*="/downloadables/"]',
+        'filename_selector': 'div.min-w-0.break-words.whitespace-pre-line, div.min-w-0.u-text-wrap b'
     }
     return _crawling_base(url, cookie, selectors, shortlist, thumblist)
 

booth_discord/booth.py

@@ -4,13 +4,16 @@
 from selenium.webdriver.chrome.options import Options
 from selenium.webdriver.support.ui import WebDriverWait
 from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
 from bs4 import BeautifulSoup
 
 class BoothCrawler():
     def __init__(self, selenium_url):
         self.selenium_url = selenium_url
 
     def get_booth_order_info(self, item_number, cookie):
+        wait_timeout_seconds = 30
+
         chrome_options = Options()
         chrome_options.add_argument("--headless")
         chrome_options.add_argument("--disable-gpu")
@@ -26,32 +29,41 @@ def get_booth_order_info(self, item_number, cookie):
         driver.refresh()
 
         try:
-            WebDriverWait(driver, 10).until(
-                EC.presence_of_element_located((By.CLASS_NAME, "flex.desktop\\:flex-row.mobile\\:flex-col"))
+            WebDriverWait(driver, wait_timeout_seconds).until(
+                EC.presence_of_element_located(
+                    (
+                        By.CSS_SELECTOR,
+                        "#js-item-order a[href*='/orders/'], #js-item-gift a[href*='/gifts/']"
+                    )
+                )
             )
 
             html = driver.page_source
             soup = BeautifulSoup(html, "html.parser")
-
-            product_div = soup.find("div", class_="flex desktop:flex-row mobile:flex-col")
-            if not product_div:
-                raise Exception("상품이 존재하지 않거나, 구매하지 않은 상품입니다.")
-
-            order_page = product_div.find("a").get("href")
-            order_parse = self.parse_url(order_page)
+
+            # Prefer direct purchase order when both order/gift sections are present.
+            order_link = soup.select_one("#js-item-order a[href*='/orders/']")
+            if order_link is None:
+                order_link = soup.select_one("#js-item-gift a[href*='/gifts/']")
+            if order_link is None:
+                raise Exception("주문/기프트 링크를 찾지 못했습니다. 쿠키 만료 또는 미구매 상품일 수 있습니다.")
+
+            order_parse = self.parse_url(order_link.get("href", ""))
             return order_parse
-
+        except TimeoutException as exc:
+            raise Exception(
+                f"페이지 로딩이 지연되어 주문 정보를 찾지 못했습니다. ({wait_timeout_seconds}초 대기)"
+            ) from exc
         finally:
             driver.quit()
 
     def parse_url(self, url):
-        # 정규식 정의
-        pattern = r"https://(?:accounts\.)?booth\.pm/(orders|gifts)/([\w-]+)"
-        match = re.match(pattern, url)
+        pattern = r"(?:https://(?:accounts\.)?booth\.pm)?/(orders|gifts)/([\w-]+)"
+        match = re.search(pattern, url)
 
         if match:
             gift_flag = match.group(1) == "gifts"  # gifts이면 True, orders이면 False
             order_number = match.group(2)
             return gift_flag, order_number
         else:
-            raise ValueError("URL 형식이 잘못되었습니다.")
+            raise ValueError("URL 형식이 잘못되었습니다.")

docker-compose.yml

@@ -22,6 +22,7 @@ services:
       - ./changelog:/root/boothchecker/changelog
       - ./config.json:/root/boothchecker/config.json
     depends_on:
+      - porstgres
       - chrome
     restart: unless-stopped
     logging: