resume-parse/tools/irafa.py

# -*- coding: utf-8 -*-
# @Author: privacy
# @Date:   2022-07-07 13:12:17
# @Last Modified by:   privacy
# @Last Modified time: 2022-07-14 09:39:42

# 内部人才市场简历模板
from pprint import pprint
import re
import docx
from docx import Document
from docx.shared import Inches


path = "d:\\desktop\\内部人才市场简历模板.docx"

keywords = ["姓名", "性别", "出生日期", "民族", "籍贯", "健康状况", "政治面貌", "参加工作时间", "外语水平", "专业技术资格（取得时间）", "计算机水平", "熟悉专业有何专长", "工作单位", "现任职务", "任职时间", "联系电话", "对报名岗位认识及工作设想", "意向地区", "意向岗位", "意向单位", "意向专业", "职业证书", "资格等级", "取得日期", "学校/培训机构", "专业", "起始时间", "毕业时间", "姓名", "职业", "与本人关系"]

def parse_line(line):
    result = []
    key = None
    for cell in line:
        if cell and ''.join(cell.split()) in keywords:
            key = ''.join(cell.split())
        elif cell and key:
            schema = {key:cell}
            result.append(schema)
            key = None
    return result


def parse_layout(path):
    result = []
    doc = Document(path)

    lo = {}
    tables = doc.tables
    for _table in tables[:]:
        for i, row in enumerate(_table.rows[:]):
            row_content = []
            for cell in row.cells[:]:
                c = cell.text
                row_content.append(c)
            lo[len(lo.keys())] = row_content
    
    kwln = -1
    kwline = None
    for key in lo.keys():
        # pdb.set_trace()
        for val in lo[key]:# 通过全关键词，判断此行是否为关键词行
            if val and ''.join(val.split()) not in keywords:# 有非关键字元素，非关键词行，判断是否为关键词行元素
                # pdb.set_trace()
                for c in lo[key]:
                    # pdb.set_trace()
                    if c and ''.join(c.split()) in keywords:# 非关键词行元素
                        result.extend(parse_line(lo[key]))
                        break
                else:# 关键词行元素
                    schema = dict()
                    for key, val in zip(kwline, lo[key]):
                        if key:
                            schema[key] = val
                    if "学校/培训机构" in schema.keys():
                        schema["学习经历"] = "学习经历"
                    elif "与本人关系" in schema.keys():
                        schema["家庭成员"] = "家庭成员"
                    elif "意向地区" in schema.keys():
                        schema["职业发展管理"] = "职业发展管理"
                    elif "职业证书" in schema.keys():
                        schema["职业资格证书"] = "职业资格证书"
                    result.append(schema)
                    break
                break
        else:
            # print("此行为关键词行")
            kwline = [''.join(cell.split()) for cell in lo[key]]
            kwln = len(lo[key])

    job = {"工作经历":"工作经历"}
    flag = None
    for p in doc.paragraphs:
        text = p.text.replace("：", ":")
        if ":" in text:
            text = re.sub(r'(\w+)\W{0,2}:', r'\n\1:', text)
            for line in text.split("\n"):
                if line.strip():
                    i = line.split(":")
                    if job.get(i[0].strip()):
                        result.append(job)
                        job = {"工作经历":"工作经历"}
                    job[i[0].strip()] = i[1].strip()
                    flag = i[0].strip()
        elif flag == "工作描述":
            job["工作描述"] += '\n' + text.strip()
    else:
        result.append(job)
    return result


# 格式化数据
def formatter(datalist):
    result = dict()

    for d in datalist:
        if len(d) == 1:
            for key in d.keys():
                result[key] = d[key]
        else:
            for k in list(d.keys()):
                if k == "".join(d[k].split()):
                    d.pop(k)
                    if result.get(k):
                        result[k].append(d)
                    else:
                        result[k] = [d]

    normal = {
        "姓名":"name",
        "性别":"gender",
        "邮箱地址":"email",
        "政治面貌":"politics",
        "联系电话":"mobile",
        "籍贯":"birthplace",
        "出生日期":"birth_time",
        "现任职务":"current_job",
        "所在城市":"living_city",
        "参加工作时间":"work_begin_time",
        "意向岗位":"intent_job",
        "熟悉专业有何专长":"skills",
    }
    edunormal = {
        "学校":"school_name",
        "专业":"major",
        "学历":"degree",
        "是否全日制":"degree_type",
    }
    for key in normal.keys():
        if result.get(key):
            result[normal[key]] = result[key]
            result.pop(key)

    edunormal = {
        "学校/培训机构":"school_name",
        "专业":"major",
        "起始时间":"start_time",
        "毕业时间":"end_time"
    }
    for idx in range(len(result['学习经历'])):
        for key in edunormal.keys():
            if result['学习经历'][idx].get(key):
                result['学习经历'][idx][edunormal[key]] = result['学习经历'][idx][key]
                result['学习经历'][idx].pop(key)
    return result

if __name__ == "__main__":
    pprint(formatter(parse_layout(path)))