数据详情
This commit is contained in:
parent
7755381cd6
commit
bad2f4acd7
@ -462,72 +462,11 @@ async def interview_file_insert(
|
||||
data['work_exp'] = float(true_work_exp.group())
|
||||
|
||||
print(data)
|
||||
# 项目切割
|
||||
# if data['project_undergo']:
|
||||
# string = data['project_undergo'][0]
|
||||
# project_u = string.split('项目名')
|
||||
# for chkstr in project_u:
|
||||
# if '：' not in chkstr:
|
||||
# continue
|
||||
# chkdict = {}
|
||||
# chklist = chkstr.split('\n\n')
|
||||
# for turestr in chklist:
|
||||
# turestr.strip()
|
||||
# if not turestr:
|
||||
# continue
|
||||
# if turestr.startswith('称'):
|
||||
# turestr1 = '项目名' + turestr
|
||||
# chklist1 = turestr1.split('\n')
|
||||
# chklist += chklist1
|
||||
# continue
|
||||
# true_d_list = turestr.split('：')
|
||||
# if len(true_d_list) == 2:
|
||||
# chk_list = deepcopy(true_d_list)
|
||||
# chkdict[chk_list[0]] = chk_list[1]
|
||||
# dp_dict = {
|
||||
# 'time': '',
|
||||
# 'name': '',
|
||||
# 'work': '',
|
||||
# 'comment': '',
|
||||
# 'duty': '',
|
||||
# }
|
||||
#
|
||||
# true_dict = deepcopy(dp_dict)
|
||||
# for key, v in chkdict.items():
|
||||
# if key == '项目名称':
|
||||
# true_dict['name'] = v
|
||||
# continue
|
||||
# if key == '开发周期':
|
||||
# true_dict['time'] = v
|
||||
# continue
|
||||
# if key == '项目描述':
|
||||
# true_dict['comment'] = v
|
||||
# continue
|
||||
# if key in ['技术要点', '功能模块']:
|
||||
# true_dict['work'] += v
|
||||
# continue
|
||||
# if key == '职务':
|
||||
# true_dict['duty'] = v
|
||||
# continue
|
||||
# # true_dict = deepcopy(chkdict)
|
||||
# true_upgrade.append(true_dict)
|
||||
|
||||
work_list = data['work_list']
|
||||
language = data['language']
|
||||
project_undergo = data['project_undergo']
|
||||
remembrance = data['remembrance']
|
||||
# true_work = []
|
||||
# language_list = []
|
||||
# remembrance_list = []
|
||||
# true_upgrade = []
|
||||
# if work_list:
|
||||
# true_work = json.loads(work_list)
|
||||
# if language:
|
||||
# language_list = json.loads(language)
|
||||
# if project_undergo:
|
||||
# true_upgrade = json.loads(project_undergo)
|
||||
# if remembrance:
|
||||
# remembrance_list = json.loads(remembrance)
|
||||
|
||||
res_data = {
|
||||
'data': data,
|
||||
|
||||
@ -360,7 +360,7 @@ def doc2pdf(fn, path_data, filename):
|
||||
|
||||
if __name__ == '__main__':
|
||||
pass
|
||||
# fn=r'C:\Users\Administrator\Desktop\面试简历\智联招聘_张双琪_Web开发工程师_中文.doc'
|
||||
# path_data=r'C:\Users\Administrator\Desktop\面试简历\\'
|
||||
# fn=r'C:\Users\Administrator\Desktop\面试简历1\智联招聘_张双琪_Web开发工程师_中文.doc'
|
||||
# path_data=r'C:\Users\Administrator\Desktop\面试简历1\\'
|
||||
# filename='智联招聘_张双琪_Web开发工程师_中文.doc'
|
||||
# doc2pdf(fn, path_data, filename)
|
||||
|
||||
@ -152,8 +152,15 @@ def fmt_txt(chk_str):
|
||||
school_str = school[0].replace('\n', '').strip()
|
||||
if ' ' in school_str and '：' not in school_str:
|
||||
school_list = school_str.split(' ')
|
||||
|
||||
else:
|
||||
school_list = [school_str]
|
||||
if '：' in school_str:
|
||||
school_list1 = school_str.split('：')
|
||||
for index, i in enumerate(school_list1):
|
||||
if i.endswith('院校'):
|
||||
school_list = [school_list1[index + 1], school_list1[index + 1]]
|
||||
else:
|
||||
school_list = [school_str]
|
||||
else:
|
||||
school = re.findall(r'.*?大学.*?\n', true_chkStr, re.M)
|
||||
if school:
|
||||
@ -291,7 +298,7 @@ def fmt_txt(chk_str):
|
||||
if project_list[0] == '':
|
||||
project_list = project_list[1:]
|
||||
# 数字开头
|
||||
if project_list[0][0].isdigit():
|
||||
if project_list[0][0].isdigit() and project_list[0][1] != '、':
|
||||
index2 = -1
|
||||
new_str_list1 = []
|
||||
for index, i in enumerate(project_list):
|
||||
@ -473,11 +480,18 @@ def fmt_txt(chk_str):
|
||||
if not p_str:
|
||||
continue
|
||||
if p_str[0].isdigit():
|
||||
dict_project['time'] = (
|
||||
p_str + project_name_time_str2[index + 1] + project_name_time_str2[
|
||||
index + 2]).replace('.', '/')
|
||||
dict_project['name'] = project_name_time_str2[index - 1]
|
||||
break
|
||||
if u'\u4e00' <= project_name_time_str2[index + 1].strip()[0] <= u'\u9fff':
|
||||
dict_project['time'] = p_str.replace('.', '/')
|
||||
dict_project['name'] = project_name_time_str2[index + 1].split(' ')[-2]
|
||||
dict_project['work'] = project_name_time_str2[index + 1].split(' ')[-1]
|
||||
break
|
||||
else:
|
||||
dict_project['time'] = (
|
||||
p_str + project_name_time_str2[index + 1] + project_name_time_str2[
|
||||
index + 2]).replace('.', '/')
|
||||
dict_project['name'] = project_name_time_str2[index - 1]
|
||||
|
||||
break
|
||||
project_chk_str2 = project_str.split(project_name_time_str)[-1]
|
||||
project_chk_str2_list = re.split('(:|：)', project_chk_str2)
|
||||
if project_chk_str2_list:
|
||||
@ -608,7 +622,7 @@ def fmt_txt(chk_str):
|
||||
work_dict['position_name'] = new_str_list1[1].split('：')[-1]
|
||||
work_duty = new_str_list1[3:]
|
||||
duty1 = new_str_list1[2].split('职责')[-1]
|
||||
duty = duty1.join((str(x) for x in work_duty))
|
||||
duty = duty1.join((x for x in work_duty))
|
||||
work_dict['duty'] = duty
|
||||
work_list.append(work_dict)
|
||||
dict_chk['work_list'] = work_list
|
||||
@ -627,22 +641,31 @@ def fmt_txt(chk_str):
|
||||
if '自我描述' in review_chk:
|
||||
review = review_chk.split('自我描述')[-1]
|
||||
dict_chk['review'] = review
|
||||
upgrade = upgrade.strip().strip('\n')
|
||||
upgrade_chk_list = upgrade.split('\n')
|
||||
upgrade_list = []
|
||||
if upgrade_chk_list:
|
||||
for index, i in enumerate(upgrade_chk_list):
|
||||
if index == 0:
|
||||
if sum([1 if u'\u4e00' <= x <= u'\u9fff' else 0 for x in i]) <= 0:
|
||||
upgrade_list.append(i + upgrade_chk_list[index + 1] + upgrade_chk_list[index + 2])
|
||||
break
|
||||
else:
|
||||
upgrade_list.append(i)
|
||||
break
|
||||
dict_chk['upgrade'] = upgrade_list
|
||||
specialty_do = []
|
||||
if '教育经历' in true_chkStr:
|
||||
upgrade = true_chkStr.split('教育经历')[-1]
|
||||
upgrade = upgrade.strip().strip('\n')
|
||||
upgrade_chk_list = upgrade.split('\n')
|
||||
upgrade_list = []
|
||||
if upgrade_chk_list:
|
||||
for index, i in enumerate(upgrade_chk_list):
|
||||
if index == 0:
|
||||
if sum([1 if u'\u4e00' <= x <= u'\u9fff' else 0 for x in i]) <= 0:
|
||||
upgrade_list.append(i + upgrade_chk_list[index + 1] + upgrade_chk_list[index + 2])
|
||||
break
|
||||
else:
|
||||
upgrade_list.append(i)
|
||||
break
|
||||
dict_chk['upgrade'] = upgrade_list
|
||||
|
||||
else:
|
||||
dict_chk['upgrade'] = []
|
||||
if '教育经历' in true_chkStr:
|
||||
upgrade = true_chkStr.split('教育经历')[-1]
|
||||
else:
|
||||
upgrade = true_chkStr
|
||||
language = []
|
||||
remembrance = []
|
||||
specialty_do = []
|
||||
if '证书' in upgrade:
|
||||
chk_upgrade_str1 = upgrade.split('证书')[-1]
|
||||
if '专业技能' in chk_upgrade_str1:
|
||||
@ -742,7 +765,7 @@ def fmt_txt(chk_str):
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
# txt = getText_pdf('D:\wokerplay\面试简历\吴操.pdf')
|
||||
# txt = getText_pdf('D:\wokerplay\面试简历1\Android高级开发工程师-方明洋-拉勾招聘.pdf')
|
||||
# 拉勾
|
||||
chk_str1 = """
|
||||
|
||||
@ -914,7 +937,6 @@ ListView和GridView视图切换的效果。 3.在分类信息中，每个分类
|
||||
教育经历
|
||||
汉口学院 本科 / 电子信息工程 2011 - 2015
|
||||
|
||||
|
||||
"""
|
||||
# 前程无忧
|
||||
chk_str2 = """
|
||||
@ -1335,4 +1357,4 @@ vms视频和grafana监控系统；
|
||||
|
||||
"""
|
||||
|
||||
fmt_txt(chk_str6)
|
||||
fmt_txt(chk_str1)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user