使用python处理一万份word表格简历操作

import zipfile
import re
def get_document(filepath):
  z = zipfile.ZipFile(filepath, "r")
  text = z.read("word/document.xml").decode("UTF-8")
  text = re.sub(r"<.*?>", "", text)#去除xml里的所有标记符
  ###如果多份简历在同一个word文件里###
  #table_list = text.split("XX简历")[1:]#依据简历标题切分每一份简历信息
  #return table_list
  return text

import re
def get_field_value(text):
  value_list = []
  m = re.findall(r"姓 名(.*?)性  别", table)
  value_list.append(m)
  m = re.findall(r"性  别(.*?)学  历", table)
  value_list.append(m)
  m = re.findall(r"民 族(.*?)健康状况", table)
  value_list.append(m)  
  '''
  此处省略其他字段匹配
  '''
  return value_list

str1 = ""
for value in value_list:
  str1 = str1 + str(value[0]) + "\t"#每个字段值用制表符\t分隔
str1 = str1 + "\n"
with open("result.txt", "a+") as f:#将内容以追加形式写入到result.txt中
  f.write(str1)

import re
import zipfile
import os
def get_document(filepath):
  z = zipfile.ZipFile(filepath, "r")
  text = z.read("word/document.xml").decode("UTF-8")
  text = re.sub(r"<.*?>", "", text)#去除xml里的所有标记符
  ###如果多份简历在同一个word文件里###
  table_list = text.split("XX简历")[1:]#依据简历标题切分每一份简历信息
  return table_list
def get_field_value(text):
  value_list = []
  m = re.findall(r"姓 名(.*?)性  别", table)
  value_list.append(m)
  m = re.findall(r"性  别(.*?)学  历", table)
  value_list.append(m)
  m = re.findall(r"民 族(.*?)健康状况", table)
  value_list.append(m)  
  '''
  此处省略其他字段匹配
  '''
  return value_list
cv_list = []
for i in os.listdir(os.getcwd()):
  a = os.path.splitext(os.getcwd() + "\\" + i)#获取当前目录下所有文件的文件名
  if a[1] == '.docx':#如果文件后缀
    print(os.getcwd()+"\\"+i)
    cv_list = cv_list + get_document(os.getcwd() + "\\" + i)#每份简历信息为一个列表元素
for i in cv_list:
  value_list = get_field_value(i)
  str1 = ""
  for value in value_list:
    str1 = str1 + str(value[0]) + "\t"
  str1 = str1 + "\n"
  with open("result.txt", "a+") as f:
    f.write(str1)

aa =[ [1,2,3,4,5],[6,7,8,9],[]…]

import os
import requests
import json
import datetime
from docx import Document
from docx.shared import Inches, Pt, Cm
from docx.oxml.ns import qn
from docx.enum.text import WD_PARAGRAPH_ALIGNMENT
def create_insert_word_table(datas, stday, etday, s):
  """创建word表格以及插入数据"""
  doc = Document()
  doc.styles['Normal'].font.name = 'Calibri' # 是用来设置当文字是西文时的字体，
  doc.styles['Normal']._element.rPr.rFonts.set(qn('w:eastAsia'), u'宋体') # 是用来设置当文字是中文时的字体
  # doc.styles['Normal'].font.size = Pt(14) # 设置所有文字字体大小为14
  distance = Inches(0.5)
  sec = doc.sections[0] # sections对应文档中的“节”
  sec.left_margin = distance # 以下依次设置左、右、上、下页面边距
  sec.right_margin = distance
  sec.top_margin = distance
  sec.bottom_margin = distance
  sec.page_width = Inches(11.7) # 设置页面宽度
  # sec.page_height = Inches(9) # 设置页面高度
  # doc.add_heading() # 设置标题，但是不符合我的条件，只能试用下方p.add_run('我是文字')
  p = doc.add_paragraph() # 添加段落
  p.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER # 设置中央对齐
  run = p.add_run('我是文字')
  run.font.size = Pt(22)
  doc.add_paragraph() # 添加空段落
  # 添加表格
  table = doc.add_table(rows=1, cols=10, style='Table Grid')
  table.style.name = 'Table Grid'
  table.style.font.size = Pt(14)
  table.rows[0].height = Cm(20)
  title = table.rows[0].cells
  title[0].text = '姓名'
  title[1].text = '1'
  title[2].text = '2'
  title[3].text = '3'
  title[4].text = '4'
  title[5].text = '5'
  title[6].text = '6 '
  title[7].text = '7'
  title[8].text = '8'
  title[9].text = '9'
  for i in range(len(datas)):
    cels = table.add_row().cells
    for j in range(len(datas[i])):
      # cels[j].text = str(datas[i][j])
      p = cels[j].paragraphs[0]
      p.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER # 设置中央对齐
      p.add_run(str(datas[i][j]))
      ph_format = p.paragraph_format
      # ph_format.space_before = Pt(10) # 设置段前间距
      # ph_format.space_after = Pt(12) # 设置段后间距
      ph_format.line_spacing = Pt(40) # 设置行间距
  doc.save('./files/项目总结.docx')