1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
|
from typing import Dict, List
import re
class ResumeService:
"""简历服务"""
def __init__(self, ocr_service, nlp_service, db):
self.ocr = ocr_service
self.nlp = nlp_service
self.db = db
def parse_resume(self, file_path: str) -> Dict:
"""解析简历"""
text = self._extract_text(file_path)
basic_info = self._parse_basic_info(text)
education = self._parse_education(text)
experience = self._parse_experience(text)
skills = self._extract_skills(text)
resume_data = {
**basic_info,
'education': education,
'experience': experience,
'skills': skills,
'raw_text': text
}
self.db.save_resume(resume_data)
return resume_data
def _extract_text(self, file_path: str) -> str:
"""从文件提取文本"""
if file_path.endswith('.pdf'):
return self.ocr.extract_from_pdf(file_path)
elif file_path.endswith(('.doc', '.docx')):
return self.ocr.extract_from_word(file_path)
else:
return self.ocr.recognize(file_path)
def _parse_basic_info(self, text: str) -> Dict:
"""解析基本信息"""
info = {}
name_match = re.search(r'^([\u4e00-\u9fa5]{2,4})', text)
info['name'] = name_match.group(1) if name_match else None
phone_match = re.search(r'1[3-9]\d{9}', text)
info['phone'] = phone_match.group() if phone_match else None
email_match = re.search(r'[\w.-]+@[\w.-]+\.\w+', text)
info['email'] = email_match.group() if email_match else None
if '男' in text[:100]:
info['gender'] = '男'
elif '女' in text[:100]:
info['gender'] = '女'
else:
info['gender'] = None
age_match = re.search(r'(\d{4})年.*出生|出生.*(\d{4})', text)
if age_match:
birth_year = int(age_match.group(1) or age_match.group(2))
info['age'] = 2024 - birth_year
else:
info['age'] = None
return info
def _parse_education(self, text: str) -> List[Dict]:
"""解析教育经历"""
education = []
edu_pattern = r'(\d{4}[./]\d{1,2}[-~至](?:\d{4}[./]\d{1,2}|至今))\s*([\u4e00-\u9fa5]+大学|[\u4e00-\u9fa5]+学院).*?([\u4e00-\u9fa5]+)(?:专业|系)'
for match in re.finditer(edu_pattern, text, re.DOTALL):
education.append({
'period': match.group(1),
'school': match.group(2),
'major': match.group(3)
})
return education
def _parse_experience(self, text: str) -> List[Dict]:
"""解析工作经历"""
experience = []
exp_pattern = r'(\d{4}[./]\d{1,2}[-~至](?:\d{4}[./]\d{1,2}|至今))\s*([\u4e00-\u9fa5]+公司|[^\n]+).*?([\u4e00-\u9fa5]+)'
for match in re.finditer(exp_pattern, text, re.DOTALL):
experience.append({
'period': match.group(1),
'company': match.group(2),
'position': match.group(3)
})
return experience
def _extract_skills(self, text: str) -> List[str]:
"""提取技能"""
skill_keywords = [
'Python', 'Java', 'JavaScript', 'C++', 'Go', 'Rust',
'MySQL', 'PostgreSQL', 'MongoDB', 'Redis',
'Linux', 'Docker', 'Kubernetes', 'AWS', 'Azure',
'机器学习', '深度学习', '数据分析', '人工智能',
'项目管理', '团队协作', '敏捷开发'
]
found_skills = []
for skill in skill_keywords:
if skill.lower() in text.lower():
found_skills.append(skill)
return found_skills
def search_resumes(self, keywords: List[str], min_score: int = 60) -> List[Dict]:
"""搜索简历"""
all_resumes = self.db.get_all_resumes()
results = []
for resume in all_resumes:
score = self._calculate_match_score(resume, keywords)
if score >= min_score:
resume['matching_score'] = score
results.append(resume)
results.sort(key=lambda x: x['matching_score'], reverse=True)
return results
def _calculate_match_score(self, resume: Dict, keywords: List[str]) -> int:
"""计算匹配分数"""
score = 0
text = resume.get('raw_text', '')
for keyword in keywords:
if keyword.lower() in text.lower():
score += 20
return min(score, 100)
|
微信进群
