更新了一下渲染模块
This commit is contained in:
parent
141e2b6cd1
commit
30e8f402d9
@ -41,6 +41,39 @@ def convert_json_to_txt_content(json_path):
|
||||
print(f" - 错误: 处理 JSON 时出错: {e}")
|
||||
return None, f"处理 JSON 时出错: {e}"
|
||||
|
||||
def load_topic_data(source_dir, run_id):
|
||||
"""
|
||||
加载选题数据
|
||||
|
||||
Args:
|
||||
source_dir: 源目录路径
|
||||
run_id: 运行ID
|
||||
|
||||
Returns:
|
||||
dict: 以topic_index为键的选题数据字典
|
||||
"""
|
||||
topic_file_path = os.path.join(source_dir, f"tweet_topic_{run_id}.json")
|
||||
topic_data = {}
|
||||
|
||||
if os.path.exists(topic_file_path):
|
||||
try:
|
||||
with open(topic_file_path, 'r', encoding='utf-8') as f:
|
||||
topics = json.load(f)
|
||||
|
||||
# 将选题数据转换为以index为键的字典
|
||||
for topic in topics:
|
||||
index = topic.get("index")
|
||||
if index:
|
||||
topic_data[index] = topic
|
||||
|
||||
print(f"成功加载选题数据，共{len(topic_data)}条")
|
||||
except Exception as e:
|
||||
print(f"加载选题数据时出错: {e}")
|
||||
else:
|
||||
print(f"警告: 未找到选题文件: {topic_file_path}")
|
||||
|
||||
return topic_data
|
||||
|
||||
def process_result_directory(source_dir, output_dir, run_id=None):
|
||||
"""
|
||||
处理指定的结果目录，提取内容并渲染到输出目录。
|
||||
@ -62,28 +95,44 @@ def process_result_directory(source_dir, output_dir, run_id=None):
|
||||
if not run_id:
|
||||
run_id = os.path.basename(source_dir)
|
||||
|
||||
# 创建CSV清单
|
||||
# 加载选题数据
|
||||
topic_data = load_topic_data(source_dir, run_id)
|
||||
|
||||
# 创建CSV清单，添加选题相关字段
|
||||
csv_path = os.path.join(output_dir, f"manifest_{run_id}.csv")
|
||||
csv_data = [
|
||||
[
|
||||
"EntryID",
|
||||
"TopicIndex",
|
||||
"VariantIndex",
|
||||
"Date",
|
||||
"Logic",
|
||||
"Object",
|
||||
"Product",
|
||||
"ProductLogic",
|
||||
"Style",
|
||||
"StyleLogic",
|
||||
"TargetAudience",
|
||||
"TargetAudienceLogic",
|
||||
"SourcePath",
|
||||
"ArticleJsonPath",
|
||||
"OutputTxtPath",
|
||||
"PosterPath",
|
||||
"AdditionalImagesCount",
|
||||
"Status",
|
||||
"Details"
|
||||
"Details",
|
||||
"JudgeStatus"
|
||||
]
|
||||
]
|
||||
|
||||
# 查找所有i_j目录
|
||||
entry_pattern = re.compile(r"^\d+_\d+$")
|
||||
entry_pattern = re.compile(r"^(\d+)_(\d+)$")
|
||||
entries = []
|
||||
|
||||
for item in os.listdir(source_dir):
|
||||
item_path = os.path.join(source_dir, item)
|
||||
if os.path.isdir(item_path) and entry_pattern.match(item):
|
||||
match = entry_pattern.match(item)
|
||||
if os.path.isdir(item_path) and match:
|
||||
entries.append(item)
|
||||
|
||||
if not entries:
|
||||
@ -99,16 +148,36 @@ def process_result_directory(source_dir, output_dir, run_id=None):
|
||||
|
||||
print(f"\n处理条目: {entry}")
|
||||
|
||||
# 解析topic_index和variant_index
|
||||
match = entry_pattern.match(entry)
|
||||
topic_index = match.group(1)
|
||||
variant_index = match.group(2)
|
||||
|
||||
# 获取该话题的选题信息
|
||||
topic_info = topic_data.get(topic_index, {})
|
||||
|
||||
# 创建记录
|
||||
record = {
|
||||
"EntryID": entry,
|
||||
"TopicIndex": topic_index,
|
||||
"VariantIndex": variant_index,
|
||||
"Date": topic_info.get("date", ""),
|
||||
"Logic": topic_info.get("logic", ""),
|
||||
"Object": topic_info.get("object", ""),
|
||||
"Product": topic_info.get("product", ""),
|
||||
"ProductLogic": topic_info.get("product_logic", ""),
|
||||
"Style": topic_info.get("style", ""),
|
||||
"StyleLogic": topic_info.get("style_logic", ""),
|
||||
"TargetAudience": topic_info.get("target_audience", ""),
|
||||
"TargetAudienceLogic": topic_info.get("target_audience_logic", ""),
|
||||
"SourcePath": entry_path,
|
||||
"ArticleJsonPath": "",
|
||||
"OutputTxtPath": "",
|
||||
"PosterPath": "",
|
||||
"AdditionalImagesCount": 0,
|
||||
"Status": "Processing",
|
||||
"Details": ""
|
||||
"Details": "",
|
||||
"JudgeStatus": ""
|
||||
}
|
||||
|
||||
# 创建输出条目目录
|
||||
@ -128,6 +197,18 @@ def process_result_directory(source_dir, output_dir, run_id=None):
|
||||
record["OutputTxtPath"] = txt_path
|
||||
|
||||
if os.path.exists(json_path):
|
||||
# 读取article.json
|
||||
try:
|
||||
with open(json_path, 'r', encoding='utf-8') as f_json:
|
||||
article_data = json.load(f_json)
|
||||
# 提取judge_success状态
|
||||
if "judge_success" in article_data:
|
||||
record["JudgeStatus"] = str(article_data["judge_success"])
|
||||
elif "judged" in article_data:
|
||||
record["JudgeStatus"] = "已审核" if article_data["judged"] else "未审核"
|
||||
except Exception as e:
|
||||
print(f" - 错误: 读取article.json失败: {e}")
|
||||
|
||||
txt_content, error = convert_json_to_txt_content(json_path)
|
||||
if error:
|
||||
record["Status"] = "Partial"
|
||||
@ -218,20 +299,26 @@ def process_result_directory(source_dir, output_dir, run_id=None):
|
||||
|
||||
def main():
|
||||
# parser = argparse.ArgumentParser(description="从TravelContentCreator结果目录提取内容并渲染到指定目录")
|
||||
# parser.add_argument("--source", type=str, required=True, help="源目录路径")
|
||||
# parser.add_argument("--output", type=str, required=True, help="输出目录路径")
|
||||
# parser.add_argument("--source", type=str, help="源目录路径")
|
||||
# parser.add_argument("--output", type=str, help="输出目录路径")
|
||||
# parser.add_argument("--run-id", type=str, help="自定义运行ID")
|
||||
|
||||
# args = parser.parse_args()
|
||||
source = ""
|
||||
output = ""
|
||||
run_id = datetime.now().strftime("%Y%m%d_%H%M%S")
|
||||
|
||||
# # 默认值设置
|
||||
# source = args.source if args.source else "/root/autodl-tmp/TravelContentCreator/result/2025-05-11_00-26-30"
|
||||
# output = args.output if args.output else "/root/autodl-tmp/TravelContentCreator/output/2025-05-11_00-26-30"
|
||||
# run_id = args.run_id if args.run_id else os.path.basename(source)
|
||||
|
||||
source = "/root/autodl-tmp/TravelContentCreator/result/2025-05-12_09-33-12"
|
||||
output = "/root/autodl-tmp/TravelContentCreator/output/2025-05-12_09-33-12"
|
||||
run_id = os.path.basename(source)
|
||||
|
||||
print("-" * 60)
|
||||
print(f"开始提取和渲染流程")
|
||||
print(f"源目录: {source}")
|
||||
print(f"输出目录: {output}")
|
||||
if run_id:
|
||||
print(f"运行ID: {run_id}")
|
||||
print(f"运行ID: {run_id}")
|
||||
print("-" * 60)
|
||||
|
||||
process_result_directory(source, output, run_id)
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user