导入遵化网站完善
This commit is contained in:
parent
286cbe907b
commit
8d3719206f
@ -1,9 +1,10 @@
|
||||
from datetime import datetime, timedelta
|
||||
|
||||
from django.core.management.base import BaseCommand
|
||||
from pandas._libs.tslibs.timestamps import Timestamp
|
||||
import pandas as pd
|
||||
from resumes.models import ResumeBasic
|
||||
import re
|
||||
import traceback
|
||||
|
||||
|
||||
class Command(BaseCommand):
|
||||
@ -20,24 +21,24 @@ class Command(BaseCommand):
|
||||
default_source = options['source']
|
||||
df = pd.read_excel(filepath)
|
||||
|
||||
# 中文列名映射（依据新版表格）
|
||||
rename_map = {
|
||||
'简历ID': 'resume_id', '姓名': 'name', '性别': 'gender', '年龄': 'age',
|
||||
'姓名': 'name', '性别': 'gender', '年龄': 'age',
|
||||
'手机': 'phone', '婚姻状况': 'marital_status', '身高': 'height', '体重': 'weight',
|
||||
'学历': 'education', '毕业学校': 'school', '专业': 'major', '工作经验': 'work_years',
|
||||
'现居住地': 'current_location', '期望职位': 'expected_position', '期望月薪': 'expected_salary',
|
||||
'工作地点': 'job_location', '到岗时间': 'available_time', '更新时间': 'update_time'
|
||||
'学历': 'education', '毕业学校': 'school', '工作经验': 'work_years',
|
||||
'现居住地': 'current_location', '工作地点': 'job_location', '到岗时间': 'available_time',
|
||||
'更新时间': 'update_time', '最高学历': 'education', '婚姻状态': 'marital_status',
|
||||
'民族': 'ethnicity', '工作职能': 'job_function', '意向岗位': 'intended_position',
|
||||
'从事行业': 'industry', '期望薪资': 'expected_salary', '工作性质': 'job_property',
|
||||
'求职状态': 'job_status',
|
||||
}
|
||||
df.rename(columns={k: v for k, v in rename_map.items() if k in df.columns}, inplace=True)
|
||||
|
||||
# 默认字段填充
|
||||
df['source_id'] = default_source
|
||||
df['crawl_keywords'] = default_keyword
|
||||
|
||||
# 时间格式清洗
|
||||
def parse_update_time(val):
|
||||
if pd.isna(val):
|
||||
return None
|
||||
return datetime(2019, 12, 12)
|
||||
val = str(val)
|
||||
now = datetime.now()
|
||||
if "刚刚" in val:
|
||||
@ -49,52 +50,90 @@ class Command(BaseCommand):
|
||||
days = int(re.search(r'\d+', val).group())
|
||||
return now - timedelta(days=days)
|
||||
try:
|
||||
return pd.to_datetime(val)
|
||||
dt = pd.to_datetime(val)
|
||||
return dt.to_pydatetime()
|
||||
except Exception:
|
||||
return None
|
||||
return datetime(2019, 12, 12)
|
||||
|
||||
if 'update_time' in df.columns:
|
||||
df['update_time'] = df['update_time'].apply(parse_update_time)
|
||||
|
||||
# 清洗身高/体重（复合字段提取）
|
||||
def extract_height_weight(text):
|
||||
text = str(text) if text and not pd.isna(text) else ''
|
||||
h = re.search(r'(\d{2,3})\s*cm', text)
|
||||
w = re.search(r'(\d{2,3})\s*kg', text)
|
||||
return {
|
||||
'height': int(h.group(1)) if h else None,
|
||||
'weight': int(w.group(1)) if w else None
|
||||
def val(v, field=None):
|
||||
if v is None or pd.isna(v):
|
||||
if field == 'update_time':
|
||||
return datetime(2019, 12, 12)
|
||||
return None
|
||||
if field == 'update_time':
|
||||
if isinstance(v, Timestamp):
|
||||
return v.to_pydatetime()
|
||||
if isinstance(v, str):
|
||||
try:
|
||||
return pd.to_datetime(v).to_pydatetime()
|
||||
except Exception:
|
||||
return datetime(2019, 12, 12)
|
||||
if isinstance(v, datetime):
|
||||
return v
|
||||
return datetime(2019, 12, 12)
|
||||
if isinstance(v, Timestamp):
|
||||
return v.to_pydatetime()
|
||||
return v
|
||||
|
||||
success_count = 0
|
||||
fail_count = 0
|
||||
errors = []
|
||||
|
||||
for i, row in df.iterrows():
|
||||
try:
|
||||
resume_id = val(row.get('resume_id'))
|
||||
defaults = {
|
||||
'name': val(row.get('name')),
|
||||
'gender': val(row.get('gender')),
|
||||
'age': val(row.get('age')),
|
||||
'phone': val(row.get('phone')),
|
||||
'marital_status': val(row.get('marital_status')),
|
||||
'height': val(row.get('height')),
|
||||
'weight': val(row.get('weight')),
|
||||
'education': val(row.get('education')),
|
||||
'school': val(row.get('school')),
|
||||
'work_years': val(row.get('work_years')),
|
||||
'current_location': val(row.get('current_location')),
|
||||
'job_location': val(row.get('job_location')),
|
||||
'available_time': val(row.get('available_time')),
|
||||
'update_time': val(row['update_time'], field='update_time'),
|
||||
'ethnicity': val(row.get('ethnicity')),
|
||||
'job_function': val(row.get('job_function')),
|
||||
'intended_position': val(row.get('intended_position')),
|
||||
'industry': val(row.get('industry')),
|
||||
'expected_salary': val(row.get('expected_salary')),
|
||||
'job_property': val(row.get('job_property')),
|
||||
'job_status': val(row.get('job_status')),
|
||||
'source_id': val(row.get('source_id')),
|
||||
'crawl_keywords': val(row.get('crawl_keywords')),
|
||||
}
|
||||
|
||||
for idx, row in df.iterrows():
|
||||
text = ' '.join([str(v) for k, v in row.items() if k not in ['height', 'weight']])
|
||||
parsed = extract_height_weight(text)
|
||||
for key in ['height', 'weight']:
|
||||
val = row.get(key)
|
||||
# 安全方式：get_or_create + 逐字段 set
|
||||
obj, _ = ResumeBasic.objects.get_or_create(resume_id=resume_id)
|
||||
|
||||
for k, v in defaults.items():
|
||||
try:
|
||||
if pd.isna(val) or str(val).strip().lower() in ['nan', 'none', 'null', '']:
|
||||
df.at[idx, key] = parsed[key]
|
||||
except:
|
||||
df.at[idx, key] = parsed[key]
|
||||
setattr(obj, k, v)
|
||||
except Exception as field_error:
|
||||
print(f"[字段设置错误] {k} = {v!r} ({type(v)}) → {field_error}")
|
||||
raise
|
||||
|
||||
if 'age' in df.columns:
|
||||
df['age'] = df['age'].apply(lambda x: int(re.search(r'\d+', str(x)).group()) if pd.notna(x) and re.search(r'\d+', str(x)) else None)
|
||||
obj.save()
|
||||
success_count += 1
|
||||
|
||||
valid_fields = [f.name for f in ResumeBasic._meta.fields]
|
||||
df = df[[col for col in df.columns if col in valid_fields]]
|
||||
except Exception as e:
|
||||
fail_count += 1
|
||||
errors.append((i + 2, str(e)))
|
||||
print(f"\n❌ 第 {i + 2} 行出错：{e}")
|
||||
print(f"resume_id: {repr(resume_id)} ({type(resume_id).__name__})")
|
||||
for k, v in defaults.items():
|
||||
print(f"{k:<20} | {repr(v):<30} | {type(v).__name__}")
|
||||
traceback.print_exc()
|
||||
|
||||
# 清除所有 NaN -> None
|
||||
for col in df.columns:
|
||||
df[col] = df[col].apply(lambda x: None if pd.isna(x) or str(x).strip().lower() in ['nan', 'none', 'null', ''] else x)
|
||||
|
||||
records = df.to_dict(orient='records')
|
||||
existing_ids = set(ResumeBasic.objects.filter(
|
||||
resume_id__in=[r["resume_id"] for r in records if "resume_id" in r]
|
||||
).values_list("resume_id", flat=True))
|
||||
|
||||
new_records = [r for r in records if r.get("resume_id") not in existing_ids]
|
||||
|
||||
ResumeBasic.objects.bulk_create([ResumeBasic(**r) for r in new_records])
|
||||
self.stdout.write(self.style.SUCCESS(
|
||||
f"✅ 成功导入 {len(new_records)} 条简历记录（关键词：{default_keyword}，来源：{default_source}）"
|
||||
))
|
||||
self.stdout.write(self.style.SUCCESS(f"导入完成！总数：{len(df)}，成功：{success_count}，失败：{fail_count}"))
|
||||
if errors:
|
||||
self.stdout.write(self.style.WARNING("失败记录如下："))
|
||||
for line_no, msg in errors:
|
||||
self.stdout.write(f" 第 {line_no} 行出错：{msg}")
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user