使用python處理一萬份word表格簡歷操作

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里的所有標(biāo)記符
  ###如果多份簡歷在同一個word文件里###
  #table_list = text.split("XX簡歷")[1:]#依據(jù)簡歷標(biāo)題切分每一份簡歷信息
  #return table_list
  return text

import re
def get_field_value(text):
  value_list = []
  m = re.findall(r"姓 名(.*?)性  別", table)
  value_list.append(m)
  m = re.findall(r"性  別(.*?)學(xué)  歷", table)
  value_list.append(m)
  m = re.findall(r"民 族(.*?)健康狀況", table)
  value_list.append(m)  
  '''
  此處省略其他字段匹配
  '''
  return value_list

str1 = ""
for value in value_list:
  str1 = str1 + str(value[0]) + "\t"#每個字段值用制表符\t分隔
str1 = str1 + "\n"
with open("result.txt", "a+") as f:#將內(nèi)容以追加形式寫入到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里的所有標(biāo)記符
  ###如果多份簡歷在同一個word文件里###
  table_list = text.split("XX簡歷")[1:]#依據(jù)簡歷標(biāo)題切分每一份簡歷信息
  return table_list
def get_field_value(text):
  value_list = []
  m = re.findall(r"姓 名(.*?)性  別", table)
  value_list.append(m)
  m = re.findall(r"性  別(.*?)學(xué)  歷", table)
  value_list.append(m)
  m = re.findall(r"民 族(.*?)健康狀況", table)
  value_list.append(m)  
  '''
  此處省略其他字段匹配
  '''
  return value_list
cv_list = []
for i in os.listdir(os.getcwd()):
  a = os.path.splitext(os.getcwd() + "\\" + i)#獲取當(dāng)前目錄下所有文件的文件名
  if a[1] == '.docx':#如果文件后綴
    print(os.getcwd()+"\\"+i)
    cv_list = cv_list + get_document(os.getcwd() + "\\" + i)#每份簡歷信息為一個列表元素
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):
  """創(chuàng)建word表格以及插入數(shù)據(jù)"""
  doc = Document()
  doc.styles['Normal'].font.name = 'Calibri' # 是用來設(shè)置當(dāng)文字是西文時的字體，
  doc.styles['Normal']._element.rPr.rFonts.set(qn('w:eastAsia'), u'宋體') # 是用來設(shè)置當(dāng)文字是中文時的字體
  # doc.styles['Normal'].font.size = Pt(14) # 設(shè)置所有文字字體大小為14
  distance = Inches(0.5)
  sec = doc.sections[0] # sections對應(yīng)文檔中的“節(jié)”
  sec.left_margin = distance # 以下依次設(shè)置左、右、上、下頁面邊距
  sec.right_margin = distance
  sec.top_margin = distance
  sec.bottom_margin = distance
  sec.page_width = Inches(11.7) # 設(shè)置頁面寬度
  # sec.page_height = Inches(9) # 設(shè)置頁面高度
  # doc.add_heading() # 設(shè)置標(biāo)題，但是不符合我的條件，只能試用下方p.add_run('我是文字')
  p = doc.add_paragraph() # 添加段落
  p.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER # 設(shè)置中央對齊
  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 # 設(shè)置中央對齊
      p.add_run(str(datas[i][j]))
      ph_format = p.paragraph_format
      # ph_format.space_before = Pt(10) # 設(shè)置段前間距
      # ph_format.space_after = Pt(12) # 設(shè)置段后間距
      ph_format.line_spacing = Pt(40) # 設(shè)置行間距
  doc.save('./files/項目總結(jié).docx')