92 lines
2.8 KiB
Python
92 lines
2.8 KiB
Python
|
#!/usr/bin/env python3
|
|||
|
|
# -*- coding: utf-8 -*-
|
|||
|
|
|
|||
|
|
import json
|
|||
|
|
import re
|
|||
|
|
|
|||
|
|
def clean_markdown_content(content):
|
|||
|
|
"""清理markdown内容中的删除线和加粗符号"""
|
|||
|
|
if not content:
|
|||
|
|
return content
|
|||
|
|
|
|||
|
|
# 删除删除线及其内容 ~~text~~
|
|||
|
|
content = re.sub(r'~~[^~]+~~', '', content)
|
|||
|
|
|
|||
|
|
# 删除中文删除线及其内容 ～～text～～
|
|||
|
|
content = re.sub(r'～～[^～]+～～', '', content)
|
|||
|
|
|
|||
|
|
# 删除加粗符号但保留内容 **text** -> text
|
|||
|
|
content = re.sub(r'\*\*([^*]+)\*\*', r'\1', content)
|
|||
|
|
|
|||
|
|
# 删除加粗符号但保留内容 __text__ -> text
|
|||
|
|
content = re.sub(r'__([^_]+)__', r'\1', content)
|
|||
|
|
|
|||
|
|
# 清理多余的空格和换行
|
|||
|
|
content = re.sub(r'\n{3,}', '\n\n', content) # 多个换行变为最多两个
|
|||
|
|
content = re.sub(r' +', ' ', content) # 多个空格变为一个
|
|||
|
|
|
|||
|
|
return content.strip()
|
|||
|
|
|
|||
|
|
# 读取数据文件
|
|||
|
|
with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
|
|||
|
|
content = f.read()
|
|||
|
|
|
|||
|
|
# 提取data对象
|
|||
|
|
import ast
|
|||
|
|
data_start = content.find('const data = {')
|
|||
|
|
data_end = content.rfind('};') + 2
|
|||
|
|
data_str = content[data_start:data_end]
|
|||
|
|
|
|||
|
|
# 解析JSON部分
|
|||
|
|
json_start = data_str.find('{')
|
|||
|
|
json_str = data_str[json_start:]
|
|||
|
|
|
|||
|
|
# 手动解析positions数组，找到有modified字段的岗位
|
|||
|
|
positions_with_modified = [
|
|||
|
|
"会展策划师",
|
|||
|
|
"会展讲解员",
|
|||
|
|
"活动执行",
|
|||
|
|
"活动策划师",
|
|||
|
|
"漫展策划师",
|
|||
|
|
"会展执行助理",
|
|||
|
|
"旅游规划师",
|
|||
|
|
"旅游计调专员",
|
|||
|
|
"景区运营专员",
|
|||
|
|
"文旅运营总监助理"
|
|||
|
|
]
|
|||
|
|
|
|||
|
|
print("开始清理修改版简历内容...")
|
|||
|
|
print(f"需要清理的岗位: {positions_with_modified}")
|
|||
|
|
|
|||
|
|
# 逐个处理每个岗位
|
|||
|
|
for position_name in positions_with_modified:
|
|||
|
|
print(f"\n处理岗位: {position_name}")
|
|||
|
|
|
|||
|
|
# 查找该岗位在文件中的位置
|
|||
|
|
# 使用更精确的模式匹配
|
|||
|
|
pattern = rf'title:\s*["\']({position_name})["\'].*?content:\s*\{{.*?modified:\s*`([^`]+)`'
|
|||
|
|
|
|||
|
|
matches = list(re.finditer(pattern, content, re.DOTALL))
|
|||
|
|
|
|||
|
|
if matches:
|
|||
|
|
for match in matches:
|
|||
|
|
original_modified = match.group(2)
|
|||
|
|
cleaned_modified = clean_markdown_content(original_modified)
|
|||
|
|
|
|||
|
|
# 替换文件内容
|
|||
|
|
content = content.replace(
|
|||
|
|
f"modified: `{original_modified}`",
|
|||
|
|
f"modified: `{cleaned_modified}`"
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
print(f" ✓ 清理了修改版内容")
|
|||
|
|
print(f" 原长度: {len(original_modified)}")
|
|||
|
|
print(f" 新长度: {len(cleaned_modified)}")
|
|||
|
|
else:
|
|||
|
|
print(f" ⚠ 未找到该岗位的修改版内容")
|
|||
|
|
|
|||
|
|
# 写回文件
|
|||
|
|
with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
|
|||
|
|
f.write(content)
|
|||
|
|
|
|||
|
|
print("\n✅ 清理完成！")
|