diff --git a/poster_gen_config.json b/poster_gen_config.json index ff564f6..fcf4f03 100644 --- a/poster_gen_config.json +++ b/poster_gen_config.json @@ -1,7 +1,7 @@ { "date": "4月29日,4月30日, 4月28日, 5月1日", - "num": 10, - "variants": 5, + "num": 5, + "variants": 1, "topic_temperature": 0.2, "topic_top_p": 0.3, "topic_presence_penalty": 1.5, @@ -42,13 +42,13 @@ { "type": "Object", "file_path": [ - "./resource/Object/笔架山居森林度假酒店.txt" + "./resource/Object/美的鹭湖鹭栖台酒店.txt" ] }, { "type": "Description", "file_path": [ - "./resource/Object/笔架山居森林度假酒店.txt" + "./resource/Object/美的鹭湖鹭栖台酒店.txt" ] }, { diff --git a/utils/__pycache__/content_generator.cpython-312.pyc b/utils/__pycache__/content_generator.cpython-312.pyc index bab567e..3803942 100644 Binary files a/utils/__pycache__/content_generator.cpython-312.pyc and b/utils/__pycache__/content_generator.cpython-312.pyc differ diff --git a/utils/__pycache__/tweet_generator.cpython-312.pyc b/utils/__pycache__/tweet_generator.cpython-312.pyc index 885d944..977cbbf 100644 Binary files a/utils/__pycache__/tweet_generator.cpython-312.pyc and b/utils/__pycache__/tweet_generator.cpython-312.pyc differ diff --git a/utils/tweet_generator.py b/utils/tweet_generator.py index 4471985..4c0692b 100644 --- a/utils/tweet_generator.py +++ b/utils/tweet_generator.py @@ -10,6 +10,7 @@ from datetime import datetime import sys import traceback import logging # Add logging +import re # sys.path.append('/root/autodl-tmp') # No longer needed if running as a module or if path is set correctly # 从本地模块导入 # from TravelContentCreator.core.ai_agent import AI_Agent # Remove project name prefix @@ -548,13 +549,88 @@ def generate_posters_for_topic(topic_item: dict, # Construct and check INPUT image paths input_img_dir_path = os.path.join(image_base_dir, object_name) if not os.path.exists(input_img_dir_path) or not os.path.isdir(input_img_dir_path): - logging.warning(f"Warning: Modify Image directory not found or not a directory: '{input_img_dir_path}'. Skipping posters for this topic.") - return False + # 模糊匹配：如果找不到完全匹配的目录，尝试查找包含关键词的目录 + logging.info(f"尝试对图片目录进行模糊匹配: {object_name}") + found_dir = None + + # 1. 尝试获取image_base_dir下的所有目录 + try: + all_dirs = [d for d in os.listdir(image_base_dir) + if os.path.isdir(os.path.join(image_base_dir, d))] + logging.info(f"找到 {len(all_dirs)} 个图片目录可用于模糊匹配") + + # 2. 提取对象名称中的关键词 + # 例如："美的鹭湖鹭栖台酒店+盈香心动乐园" -> ["美的", "鹭湖", "酒店", "乐园"] + # 首先通过常见分隔符分割（+、空格、_、-等） + parts = re.split(r'[+\s_\-]', object_name) + keywords = [] + for part in parts: + # 只保留长度大于1的有意义关键词 + if len(part) > 1: + keywords.append(part) + + # 尝试匹配更短的语义单元（例如中文的2-3个字的词语） + # 对于中文名称，可以尝试提取2-3个字的短语 + for i in range(len(object_name) - 1): + keyword = object_name[i:i+2] # 提取2个字符 + if len(keyword) == 2 and all('\u4e00' <= c <= '\u9fff' for c in keyword): + keywords.append(keyword) + + # 3. 对每个目录进行评分 + dir_scores = {} + for directory in all_dirs: + score = 0 + dir_lower = directory.lower() + # 为每个匹配的关键词增加分数 + for keyword in keywords: + if keyword.lower() in dir_lower: + score += 1 + + # 如果得分大于0（至少匹配一个关键词），记录该目录 + if score > 0: + dir_scores[directory] = score + + # 4. 选择得分最高的目录 + if dir_scores: + best_match = max(dir_scores.items(), key=lambda x: x[1]) + found_dir = best_match[0] + logging.info(f"模糊匹配成功！匹配目录: {found_dir}，匹配分数: {best_match[1]}") + + # 更新图片目录路径 + input_img_dir_path = os.path.join(image_base_dir, found_dir) + logging.info(f"使用模糊匹配的图片目录: {input_img_dir_path}") + else: + logging.warning(f"模糊匹配未找到任何包含关键词的目录") + except Exception as e: + logging.warning(f"模糊匹配过程中出错: {e}") + + # 如果仍然无法找到有效目录，则返回错误 + if not found_dir or not os.path.exists(input_img_dir_path) or not os.path.isdir(input_img_dir_path): + logging.warning(f"Warning: 即使通过模糊匹配也无法找到图片目录: '{input_img_dir_path}'. Skipping posters for this topic.") + return False # Locate Description File using resource_dir_config parameter info_directory = [] description_file_path = None found_description = False + + # 准备关键词列表用于模糊匹配 + # 与上面图片目录匹配类似，提取对象名称的关键词 + parts = re.split(r'[+\s_\-]', object_name) + keywords = [] + for part in parts: + if len(part) > 1: + keywords.append(part) + + # 尝试提取中文短语作为关键词 + for i in range(len(object_name) - 1): + keyword = object_name[i:i+2] + if len(keyword) == 2 and all('\u4e00' <= c <= '\u9fff' for c in keyword): + keywords.append(keyword) + + logging.info(f"用于描述文件模糊匹配的关键词: {keywords}") + + # 尝试精确匹配 for dir_info in resource_dir_config: if dir_info.get("type") == "Description": for file_path in dir_info.get("file_path", []): @@ -562,15 +638,45 @@ def generate_posters_for_topic(topic_item: dict, description_file_path = file_path if os.path.exists(description_file_path): info_directory = [description_file_path] - logging.info(f"Found and using description file from config: {description_file_path}") + logging.info(f"找到并使用精确匹配的描述文件: {description_file_path}") found_description = True else: - logging.warning(f"Warning: Description file specified in config not found: {description_file_path}") + logging.warning(f"Warning: 配置中指定的描述文件未找到: {description_file_path}") break if found_description: - break + break + + # 如果精确匹配失败，尝试模糊匹配 if not found_description: - logging.info(f"Warning: No matching description file found for object '{object_name}' in config resource_dir (type='Description').") + logging.info(f"未找到'{object_name}'的精确匹配描述文件，尝试模糊匹配...") + best_score = 0 + best_file = None + + for dir_info in resource_dir_config: + if dir_info.get("type") == "Description": + for file_path in dir_info.get("file_path", []): + file_name = os.path.basename(file_path) + score = 0 + + # 计算关键词匹配分数 + for keyword in keywords: + if keyword.lower() in file_name.lower(): + score += 1 + + # 如果当前文件得分更高，更新最佳匹配 + if score > best_score and os.path.exists(file_path): + best_score = score + best_file = file_path + + # 如果找到了最佳匹配文件 + if best_file: + description_file_path = best_file + info_directory = [description_file_path] + logging.info(f"模糊匹配找到描述文件: {description_file_path}，匹配分数: {best_score}") + found_description = True + + if not found_description: + logging.warning(f"未找到对象'{object_name}'的匹配描述文件。") # Generate Text Configurations for All Variants try: