简历批量导入人才库

api/api_v1/endpoints/forms.py

@@ -2704,8 +2704,8 @@ async def find_column_update(
         current_user: schemas.UserDB = Depends(deps.get_current_user)
 ) -> schemas.Msg:
     """ 修改一条查询字段对照表数据 """
-    data = await crud.api_find_column.update_columns(db, update_data, where={'column_type': column_type})
+    await crud.api_find_column.update_columns(db, update_data, where={'column_type': column_type})
-    return schemas.Msg(code=200, msg='ok', data=data)
+    return schemas.Msg(code=200, msg='ok', data='')
 
 
 # 报表查询字段对照列表
@@ -2773,6 +2773,7 @@ async def currency_interview_form(
     }
     return schemas.Msg(code=200, msg='ok', data=res_data)
 
+
 # 通用入职人员分析报表
 @router.post("/currency_worker_form")
 async def currency_worker_form(
@@ -2822,6 +2823,7 @@ async def currency_worker_form(
     }
     return schemas.Msg(code=200, msg='ok', data=res_data)
 
+
 # 读取邮箱简历方法
 def email_user(dir_name, mail_dict):
     file_list = []  # 简历文件

api/api_v1/endpoints/interview.py

@@ -30,7 +30,7 @@ from db import get_database
 from db.ckdb import get_ck_db, CKDrive
 from datetime import timedelta
 from models.interview_zsgc import InterviewDo
-from utils import get_time, qujian_time, Download_xlsx, send_str_mail, doc2pdf
+from utils import get_time, qujian_time, Download_xlsx, send_str_mail, doc2pdf, png2pdf
 
 router = APIRouter()
 
@@ -709,6 +709,258 @@ async def file_to_hw(
         return schemas.Msg(code=400, msg='上传华为云失败或者解析失败', data=None)
 
 
+# 批量导入简历
+@router.post("/files_to_hw")
+async def files_to_hw(
+        request: Request,
+        file_path: str,
+        db: CKDrive = Depends(get_ck_db),
+        current_user: schemas.UserDB = Depends(deps.get_current_user)
+) -> schemas.Msg:
+    """ 批量导入简历 """
+    insert_list = []  # 插入数据
+    error_files = []  # 解析错误简历文件
+    error_to_fw_files = []  # 上传失败简历文件
+    # 简历初始文档
+    data_mode = {
+        "interview_name": "",
+        "interview_type": 1,
+        "interview_sign": 0,
+        "hope_money": "",
+        "feedback": 0,
+        "interview_round": 0,
+        "event_time": datetime.now(),
+        "name": "",
+        "phone": "",
+        "job_name": "",
+        "hr_name": "",
+        "work_exp": 0,
+        "interview_stage": -1,
+        "owner_name": 2,
+        "education": 1,
+        "work_undergo": [],
+        "project_undergo": [],
+        "work_list": [],
+        "school": "",
+        "at_school": "",
+        "specialty": "",
+        "specialty_do": [],
+        "mmended_state": 0,
+        "mail": "",
+        "account": "",
+        "id_card": "",
+        "gender": "",
+        "age": 0,
+        "gam": "",
+        "interview_state": 1,
+        "counts": 1,
+        "nation": "汉",
+        "review": "",
+        "upgrade": [],
+        "come_time": "",
+        "now_money": "",
+        "men_state": 1,
+        "teacher_state": 1,
+        "teacher_back": 1,
+        "offer_state": 1,
+        "offer_exam_state": 1,
+        "notice_state": 1,
+        "pass_why": 0,
+        "pass_text": "",
+        "now_address": "",
+        "language": [],
+        "remembrance": [],
+        "file_url": '',
+        "hr_manner": 2,
+    }
+    for file in os.listdir(file_path):
+        try:
+            fn = file_path + '/' + file
+            end_str = file.split('.')[-1].lower()  # 文件类型
+            # 文件类型支持
+            if end_str not in ['pdf', 'doc', 'docx', 'png', 'jpg', 'jpeg', 'word']:
+                continue
+            if end_str in ['doc', 'docx', 'word']:  # doc,docx, word转pdf
+                fn, fil = doc2pdf(fn, file_path, file)
+                file = fil
+            if end_str in ['png', 'jpg', 'jpeg']:  # 图片转pdf
+                fn, fil = png2pdf(file_path, file)
+                file = fil
+            data_mode1 = deepcopy(data_mode)
+            uid = get_uid()
+            data_mode1['uid'] = uid
+            # 存数据
+            chk_txt = getText_pdf(file_path + '/' + file)
+            data = fmt_txt(chk_txt)
+            education = data['education']
+            # 学历int转化
+            education_int = {
+                '大专': 1,
+                '本科': 2,
+                '研究生': 3,
+                '博士': 4,
+                '硕士': 5,
+            }
+            if education and isinstance(education, str):
+                data['education'] = education_int.get(education, 1)
+            age = data['age']
+            if not age:
+                data['age'] = 20
+            # 年龄int转化
+            if age and isinstance(age, str):
+                true_age = re.search(r"\d+\.?\d*", age)
+                if len(true_age.group()) > 2:
+                    data['age'] = 20
+                else:
+                    data['age'] = int(true_age.group())
+            work_exp = data['work_exp']
+            if not work_exp:
+                data['work_exp'] = 0
+            # 工作经验float转化
+            if work_exp and isinstance(work_exp, str):
+                true_work_exp = re.search(r"\d+\.?\d*", work_exp)
+                if len(true_work_exp.group()) > 3:
+                    data['work_exp'] = 0
+                else:
+                    data['work_exp'] = float(true_work_exp.group())
+
+            data_mode1.update(data)
+            # 转json字符串
+            if 'remembrance_list' in data_mode1:
+                remembrance = data_mode1.pop('remembrance_list')
+                data_mode1['remembrance'] = remembrance
+            if 'language_list' in data_mode1:
+                language = data_mode1.pop('language_list')
+                data_mode1['language'] = language
+            if 'project_undergo' in data_mode1:
+                if data_mode1.get('project_undergo', []):
+                    data_mode1['project_undergo'] = [json.dumps(i) for i in data_mode1['project_undergo']]
+                else:
+                    data_mode1['project_undergo'] = []
+            if 'work_list' in data_mode1:
+                if data_mode1.get('work_list', []):
+                    data_mode1['work_list'] = [json.dumps(i) for i in data_mode1['work_list']]
+                else:
+                    data_mode1['work_list'] = []
+            if 'language' in data_mode1:
+                if data_mode1.get('language', []):
+                    data_mode1['language'] = [json.dumps(i) for i in data_mode1['language']]
+                else:
+                    data_mode1['language'] = []
+            if 'remembrance' in data_mode1:
+                if data_mode1.get('remembrance', []):
+                    data_mode1['remembrance'] = [json.dumps(i) for i in data_mode1['remembrance']]
+                else:
+                    data_mode1['remembrance'] = []
+
+            # 字符串转datetime
+            if data_mode1.get('in_time', ''):
+                chk_in_time = data_mode1['in_time'].replace('-', '/').replace('.', '/')
+                if len(chk_in_time.split('/')) == 2:
+                    data_mode1['in_time'] = str(datetime.strptime(chk_in_time, "%Y/%m").date())
+                if len(chk_in_time.split('/')) == 3:
+                    data_mode1['in_time'] = str(datetime.strptime(chk_in_time, "%Y/%m/%d").date())
+
+            if data_mode1.get('out_time', ''):
+                chk_out_time = data_mode1['out_time'].replace('-', '/').replace('.', '/')
+                if len(chk_out_time.split('/')) == 2:
+                    data_mode1['out_time'] = str(datetime.strptime(chk_out_time, "%Y/%m").date())
+                if len(chk_out_time.split('/')) == 3:
+                    data_mode1['out_time'] = str(datetime.strptime(chk_out_time, "%Y/%m/%d").date())
+
+            if data_mode1.get('birthday', ''):
+                chk_birthday = data_mode1['birthday'].replace('-', '/').replace('.', '/')
+                if len(chk_birthday.split('/')) == 2:
+                    data_mode1['birthday'] = str(datetime.strptime(chk_birthday, "%Y/%m").date())
+                if len(chk_birthday.split('/')) == 3:
+                    data_mode1['birthday'] = str(datetime.strptime(chk_birthday, "%Y/%m/%d").date())
+
+            if data_mode1.get('star_time', ''):
+                chk_star_time = data_mode1['star_time'].replace('-', '/').replace('.', '/')
+                if len(chk_star_time.split('/')) == 2:
+                    data_mode1['star_time'] = str(datetime.strptime(chk_star_time, "%Y/%m").date())
+                if len(chk_star_time.split('/')) == 3:
+                    data_mode1['star_time'] = str(datetime.strptime(chk_star_time, "%Y/%m/%d").date())
+
+            if data_mode1.get('end_time', ''):
+                chk_end_time = data_mode1['end_time'].replace('-', '/').replace('.', '/')
+                if len(chk_end_time.split('/')) == 2:
+                    data_mode1['end_time'] = str(datetime.strptime(chk_end_time, "%Y/%m").date())
+                if len(chk_end_time.split('/')) == 3:
+                    data_mode1['end_time'] = str(datetime.strptime(chk_end_time, "%Y/%m/%d").date())
+
+            if data_mode1.get('graduate_time', ''):
+                chk_graduate = data_mode1['graduate_time'].replace('-', '/').replace('.', '/')
+                if len(chk_graduate.split('/')) == 2:
+                    data_mode1['graduate_time'] = str(datetime.strptime(chk_graduate, "%Y/%m").date())
+                if len(chk_graduate.split('/')) == 3:
+                    data_mode1['graduate_time'] = str(datetime.strptime(chk_graduate, "%Y/%m/%d").date())
+
+            # 简历查重,姓名,手机号,性别name,phone,gender
+            find_name = data['name']
+            find_phone = data['phone']
+            find_gender = data['gender']
+            where = {}
+            if find_name:
+                where.update({
+                    'name': find_name
+                })
+            if find_phone:
+                where.update({
+                    'phone': find_phone
+                })
+            if find_gender:
+                where.update({
+                    'gender': find_gender
+                })
+            whereStr = ''
+            for key, value in where.items():
+                if isinstance(value, str):
+                    if not value.strip():
+                        continue
+                    if whereStr:
+                        whereStr += 'and ' + str(key) + ' = ' + "'" + value + "'" + ' '
+                    else:
+                        whereStr += str(key) + ' = ' + "'" + value + "'" + ' '
+                    continue
+                if whereStr:
+                    whereStr += 'and ' + str(key) + ' = ' + str(value) + ' '
+                else:
+                    whereStr += str(key) + ' = ' + str(value) + ' '
+            whereStr = whereStr.strip()
+            sql = f"select uid from HR.resumes where {whereStr}"
+            is_in_data = await db.execute(sql)
+            exist = 0
+            if is_in_data:
+                exist = 1
+                uid = list(is_in_data.values())[0]['uid']
+            # os.rename(path_data + '/' + filename, path_data + '/' + find_phone + '.pdf')
+            res = obsClient.putFile('legu-cdn-source', 'hrms/' + uid + '.pdf', fn)
+            if res.status < 300:
+                # 地址
+                url = res.body.objectUrl
+                data_mode1['file_url'] = url
+                data['file_url'] = url
+                if exist:
+                    continue
+                insert_list.append(data_mode1)
+            else:
+                error_to_fw_files.append(file)
+                continue
+        except:
+            error_files.append(file)
+            continue
+    sql = f"insert into HR.resumes(interview_name, interview_type, interview_sign, hope_money, feedback," \
+          f" interview_round, event_time, uid, name, phone, job_name, hr_name, work_exp, interview_stage, owner_name," \
+          f" education, work_undergo, project_undergo, work_list, school, at_school, specialty, specialty_do, " \
+          f"mmended_state, mail, account, id_card, gender, age, gam, interview_state, counts, nation, come_time," \
+          f" review, upgrade, now_money, men_state, teacher_state, teacher_back, offer_state, offer_exam_state," \
+          f" notice_state, pass_why, pass_text, now_address,language,remembrance, file_url, hr_manner) values"
+
+    await db.execute_dict(sql, insert_list)
+    return schemas.Msg(code=0, msg='ok', data='')
+
+
 # 导入面试数据
 @router.post("/interview_file_insert")
 async def interview_file_insert(
@@ -1095,7 +1347,7 @@ async def resume_affix(
             # 地址
             url = res.body.objectUrl
             resData = {'file_url': url, 'filename': 'hrms/accessory/' + filename}
-            res=json.dumps(resData)
+            res = json.dumps(resData)
             # sql = f"""
             # ALTER table HR.resumes update resume_affix_id = {url} WHERE uid = '{data_in.uid}'
             # """
@@ -2118,8 +2370,8 @@ async def add_interviewee(
     # 同步发送邮件通知被安排了面试
     find_sql = f"""select job_names,name from HR.resumes where uid = '{data_in.uid}' limit 1"""
     df = await ckdb.query_dataframe(find_sql)
-    interview_names='，'.join(name_list)
+    interview_names = '，'.join(name_list)
-    hr_names='，'.join(hr_list)
+    hr_names = '，'.join(hr_list)
     send = f"""【面试通知】\n面试岗位：{df['job_names'][0]}\n面试时间：{data_in.star_time}\n面试者：{df['name'][0]}\nHR：{hr_names}\n面试官：{interview_names}"""
     hr_user = data_in.hr_user
     hr_user.extend(data_in.user_id)
@@ -2147,18 +2399,18 @@ async def add_interviewee(
                                                    'type': 'interview'  # 记录的类型
                                                    })
     #  创建空白的面试反馈到mdb数据库
-    survey={}
+    survey = {}
-    for us in [name,hr]:
+    for us in [name, hr]:
         for i in us:
-            survey[i['user_id']]={
+            survey[i['user_id']] = {
                 "name": i['nickname'],
                 "voice": 0,
                 "thought": 0,
                 "diathesis": 0,
                 "evaluate": "",
                 "teacher_back": 0,
-                'type':False}
+                'type': False}
-    await crud.feedback.ins_feedback(db,schemas.Feedback(uid=data_in.uid,survey=survey))
+    await crud.feedback.ins_feedback(db, schemas.Feedback(uid=data_in.uid, survey=survey))
 
     return schemas.Msg(code=200, msg='ok', data='')
 
@@ -2312,9 +2564,6 @@ async def interview_find(
     return schemas.Msg(code=200, msg='ok', data=res_data)
 
 
-
-
-
 @router.post("/interview")
 async def interview(
         request: Request,
@@ -2428,6 +2677,7 @@ async def interviews(
 
     return schemas.Msg(code=200, msg='ok', data=datas)
 
+
 @router.post("/interview_teacher")
 async def interview_teacher(
         request: Request,
@@ -2455,13 +2705,13 @@ async def interview_teacher(
 ) -> schemas.Msg:
     """ 修改面试反馈 """
     data = await crud.feedback.one_feedback(db, {'uid': data_in.uid})
-    for k,v in data['survey'].items():
+    for k, v in data['survey'].items():
         if k == list(data_in.survey.keys())[0]:
-            data['survey'][k]=data_in.survey[k]
+            data['survey'][k] = data_in.survey[k]
-            data['survey'][k]['type']=True
+            data['survey'][k]['type'] = True
 
-    await crud.feedback.up_feedback(db, schemas.Feedback(uid=data_in.uid,survey=data['survey']))
+    await crud.feedback.up_feedback(db, schemas.Feedback(uid=data_in.uid, survey=data['survey']))
-    a=1
+    a = 1
     # user_list=list(data_in.survey.keys())
     # sql = f"""select hr_id,interview_id from HR.resumes  WHERE uid = '{data_in.uid}' limit 1"""
     # res=await ckdb.query_dataframe(sql)
@@ -2484,7 +2734,7 @@ async def interview_teacher(
         current_user: schemas.UserDB = Depends(deps.get_current_user)
 ) -> schemas.Msg:
     """ 获取面试反馈 """
-    data=await crud.feedback.one_feedback(db,{'uid':data_in.uid})
+    data = await crud.feedback.one_feedback(db, {'uid': data_in.uid})
     return schemas.Msg(code=200, msg='ok', data=data)
 
 
@@ -2503,4 +2753,3 @@ async def hint(
         res.append(i)
     data = sorted(res, key=operator.itemgetter('times'))
     return schemas.Msg(code=200, msg='ok', data=data)
-

utils/func.py

@@ -1,6 +1,6 @@
 #!/usr/bin/python
 # coding:utf-8
-
+import os
 import random
 import time
 import datetime
@@ -9,14 +9,13 @@ import pandas as pd
 import smtplib
 from email.mime.text import MIMEText
 from email.utils import formataddr
-
+from fitz import fitz
 from datetime import timedelta
 from datetime import datetime as p1
 import calendar
 from core.config import Settings
 
 
-
 def get_uid():
     return hex(int(time.time() * 10 ** 7) + random.randint(0, 10000))[2:]
 
@@ -349,13 +348,33 @@ def doc2pdf(fn, path_data, filename):
     # :param filename:陈超峰.docx
     # :return: 'C:\Users\86173\Desktop\陈超峰.pdf'
     # """
-    new_filename=filename.split('.')[0]
+    new_filename = filename.split('.')[0]
     word = client.Dispatch("Word.Application")  # 打开word应用程序
     doc = word.Documents.Open(fn)  # 打开word文件
     doc.SaveAs("{}/{}.pdf".format(path_data, new_filename), 17)  # 另存为后缀为".pdf"的文件，其中参数17表示为pdf
     doc.Close()  # 关闭原来word文件
     word.Quit()
-    return path_data + '/' + new_filename + '.pdf',new_filename + '.pdf'
+    return path_data + '/' + new_filename + '.pdf', new_filename + '.pdf'
+
+
+# 图片转pdf
+def png2pdf(dir_path, filename):
+    """
+    :param dir_path: 图片所在目录路径
+    :param filename: 图片文件名
+    :return: 转化成的dpf的绝对路径
+    """
+    img_path = dir_path + '/' + filename
+    img_type = filename.split('.')[-1]
+    new_filename = os.path.basename(img_path).replace(img_type, 'pdf')
+    doc = fitz.open()
+    img_doc = fitz.open(img_path)
+    pdf_bytes = img_doc.convert_to_pdf()
+    img_pdf = fitz.open('pdf', pdf_bytes)
+    doc.insert_pdf(img_pdf)
+    res_path = dir_path + '/' + new_filename
+    doc.save(res_path)
+    return res_path, new_filename
 
 
 if __name__ == '__main__':