fixed
This commit is contained in:
@@ -156,22 +156,21 @@ def read_docx_content(doc_path: Path) -> List[str]:
|
||||
is_datetime_line(lines[start_idx + 2])
|
||||
return False
|
||||
|
||||
# 确定起始偏移量
|
||||
offset = 0
|
||||
if is_six_row_group(lines, 0):
|
||||
offset = 0
|
||||
elif len(lines) >= 3:
|
||||
# 丢弃第一行，检查第二行是否是网址且第三行是否是日期/时间
|
||||
offset = 1
|
||||
|
||||
# 按确定的行数组模式处理所有行
|
||||
# 按组处理，每组独立判断 offset
|
||||
# 规则：如果第二行是网址且第三行是日期/时间，则当前 6 行为一组；否则丢弃第一行，继续判断
|
||||
result = []
|
||||
i = offset
|
||||
i = 0
|
||||
while i + 5 <= len(lines):
|
||||
combined = '\t'.join(lines[i:i+6])
|
||||
result.append(combined)
|
||||
i += 6
|
||||
# 处理剩余行
|
||||
# 检查当前位置开始是否是 6 行一组模式
|
||||
if is_six_row_group(lines, i):
|
||||
# 是 6 行一组，合并这 6 行
|
||||
combined = '\t'.join(lines[i:i+6])
|
||||
result.append(combined)
|
||||
i += 6
|
||||
else:
|
||||
# 不是 6 行一组，丢弃当前行（相当于 offset+1）
|
||||
i += 1
|
||||
# 处理剩余行（不足 6 行的）
|
||||
while i < len(lines):
|
||||
result.append(lines[i])
|
||||
i += 1
|
||||
@@ -449,76 +448,38 @@ def main():
|
||||
extract_all_zips(source_dir, "data", delete_original=args.delete_original)
|
||||
return
|
||||
|
||||
# 批量处理所有 zip 文件
|
||||
# 批量处理所有文件夹（已从 cc 目录解压好）
|
||||
if True or args.batch:
|
||||
source_dir = Path(args.base_dir) if args.base_dir else Path("cc")
|
||||
data_dir = Path("data")
|
||||
server_jsons_dir = Path("server") / "jsons"
|
||||
server_jsons_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
zip_files = list(source_dir.glob("*.zip"))
|
||||
# 获取 cc 目录下的所有子文件夹（已解压好的文件夹）
|
||||
folders = [f for f in source_dir.iterdir() if f.is_dir()]
|
||||
|
||||
if not zip_files:
|
||||
print(f"在 {source_dir} 中未发现 zip 文件")
|
||||
if not folders:
|
||||
print(f"在 {source_dir} 中未发现文件夹")
|
||||
return
|
||||
|
||||
print(f"找到 {len(zip_files)} 个压缩文件，开始批量处理...")
|
||||
print(f"找到 {len(folders)} 个文件夹，开始批量处理...")
|
||||
success_count = 0
|
||||
fail_count = 0
|
||||
|
||||
for zip_file in zip_files:
|
||||
print(f"\n【开始处理】{zip_file.name}")
|
||||
for folder in folders:
|
||||
print(f"\n【开始处理】{folder.name}")
|
||||
# 清空 data 目录
|
||||
clear_directory(data_dir)
|
||||
|
||||
|
||||
|
||||
try:
|
||||
# 先提取所有文件
|
||||
with zipfile.ZipFile(zip_file, 'r') as zip_ref:
|
||||
zip_ref.extractall(data_dir)
|
||||
IsdirectorExtracted = False
|
||||
extract_dir = data_dir / zip_file.stem
|
||||
|
||||
# 然后遍历所有成员，设置时间戳
|
||||
with zipfile.ZipFile(zip_file, 'r') as zip_ref:
|
||||
for member in zip_ref.infolist():
|
||||
# 计算解压后的实际路径
|
||||
# 解压后，文件可能在 data_dir/zip_file.stem/ 目录下
|
||||
# 或者在 data_dir/ 下（如果 zip 内部没有额外的目录层）
|
||||
base_extract_path = data_dir / zip_file.stem
|
||||
|
||||
# 如果 member.filename 以 zip_file.stem/开头，需要先去掉这个前缀
|
||||
if member.filename.startswith(zip_file.stem + '/') or member.filename.startswith(zip_file.stem + os.sep):
|
||||
relative_path = member.filename[len(zip_file.stem) + 1:]
|
||||
member_path = base_extract_path / relative_path
|
||||
else:
|
||||
# 否则直接在 base_extract_path 下查找
|
||||
member_path = data_dir / member.filename
|
||||
IsdirectorExtracted = True
|
||||
|
||||
# 如果路径存在，设置时间戳
|
||||
if member_path.exists():
|
||||
try:
|
||||
date_time = datetime(*member.date_time[:5])
|
||||
timestamp = date_time.timestamp()
|
||||
os.utime(member_path, (timestamp, timestamp))
|
||||
except Exception:
|
||||
pass
|
||||
if IsdirectorExtracted:
|
||||
extract_dir = data_dir
|
||||
|
||||
# 检查是否多了一层目录
|
||||
inner_dir = extract_dir / zip_file.stem
|
||||
if inner_dir.is_dir() and len(list(extract_dir.iterdir())) == 1:
|
||||
for item in inner_dir.iterdir():
|
||||
item.rename(extract_dir / item.name)
|
||||
inner_dir.rmdir()
|
||||
# 移动文件夹到 data 目录
|
||||
extract_dir = data_dir / folder.name
|
||||
shutil.move(str(folder), str(extract_dir))
|
||||
|
||||
# 查找 Word 文档
|
||||
word_doc = find_word_doc_recursive(extract_dir)
|
||||
if not word_doc:
|
||||
print(f"⚠️ 在 {zip_file.name} 中未找到 Word 文档")
|
||||
print(f"⚠️ 在 {folder.name} 中未找到 Word 文档")
|
||||
fail_count += 1
|
||||
continue
|
||||
|
||||
@@ -539,13 +500,12 @@ def main():
|
||||
|
||||
if not zxxk_folder.exists():
|
||||
print("❌ 文件夹不存在，请先解压文件")
|
||||
# 将失败的原始压缩包拷贝到本程序所在目录的 ee 子目录
|
||||
# 将失败的文件拷贝到本程序所在目录的 ee 子目录
|
||||
script_dir = Path(__file__).parent
|
||||
ee_dir = script_dir / "ee"
|
||||
ee_dir.mkdir(exist_ok=True)
|
||||
dest_file = ee_dir / zip_file.name
|
||||
import shutil
|
||||
shutil.copy2(zip_file, dest_file)
|
||||
dest_file = ee_dir / folder.name
|
||||
shutil.copy2(folder, dest_file)
|
||||
print(f" 已拷贝失败文件到：{dest_file}")
|
||||
fail_count += 1
|
||||
continue
|
||||
@@ -553,13 +513,12 @@ def main():
|
||||
twole_folder = base_dir / "二一教育"
|
||||
if not twole_folder.exists():
|
||||
print("❌ 文件夹不存在，请先解压文件")
|
||||
# 将失败的原始压缩包拷贝到本程序所在目录的 ee 子目录
|
||||
# 将失败的文件拷贝到本程序所在目录的 ee 子目录
|
||||
script_dir = Path(__file__).parent
|
||||
ee_dir = script_dir / "ee"
|
||||
ee_dir.mkdir(exist_ok=True)
|
||||
dest_file = ee_dir / zip_file.name
|
||||
import shutil
|
||||
shutil.copy2(zip_file, dest_file)
|
||||
dest_file = ee_dir / folder.name
|
||||
shutil.copy2(folder, dest_file)
|
||||
print(f" 已拷贝失败文件到：{dest_file}")
|
||||
fail_count += 1
|
||||
continue
|
||||
@@ -573,9 +532,9 @@ def main():
|
||||
|
||||
print(f"✓ JSON 文件已保存到：{output_file}")
|
||||
|
||||
# 删除原压缩包
|
||||
# 删除原文件夹
|
||||
if args.delete_original:
|
||||
zip_file.unlink()
|
||||
shutil.rmtree(folder)
|
||||
|
||||
success_count += 1
|
||||
|
||||
|
||||
Reference in New Issue
Block a user