File size: 1,564 Bytes
61fd574
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import asyncio
import io
import logging

try:
    import pdfplumber
    PDFPLUMBER_AVAILABLE = True
except ImportError:
    PDFPLUMBER_AVAILABLE = False

logger = logging.getLogger(__name__)

MOCK_RESULT = {
    "name": "张三",
    "school": "华南理工大学",
    "major": "计算机科学与技术",
    "grade": "研二",
    "skills": ["Python", "Java", "SQL", "PyTorch", "Flask"],
    "projects": [
        "基于协同过滤的推荐系统",
        "在线商城后端开发",
    ],
    "summary": "技术栈集中在Python/Java后端开发,有推荐系统和Web开发项目经验",
}


async def parse_resume_pdf(file_bytes: bytes) -> dict:
    if not PDFPLUMBER_AVAILABLE:
        return dict(MOCK_RESULT)

    try:
        with pdfplumber.open(io.BytesIO(file_bytes)) as pdf:
            text_parts = []
            for page in pdf.pages:
                page_text = page.extract_text()
                if page_text:
                    text_parts.append(page_text)
            full_text = "\n".join(text_parts)

        if not full_text.strip():
            return dict(MOCK_RESULT)

        from app.agents.resume_parser import ResumeParser
        parser = ResumeParser()
        result = await parser.parse_resume(full_text)
        if isinstance(result, dict) and "error" not in result:
            return result
        logger.warning("Resume parser returned error: %s", result.get("error"))
        return dict(MOCK_RESULT)

    except Exception as e:
        logger.error("Resume parsing failed: %s", e)
        return dict(MOCK_RESULT)