python讀取word文檔，插入mysql資料庫執行個體

標籤：對象   esc   exe   pymysql   nec   word   ecif   img   find   

表格內容如下：

1、實現大量匯入word文檔，取文檔標題中的數字作為編號

2、除取上面打鉤的內容需要匹配出來入庫入庫，其他內容全部直接入庫mysql

# wuyanfeng
# -*- coding:utf-8 -*-
# 讀取docx中的文本程式碼範例
import docx
import pymysql
import re
import os

# 建立資料庫連結
conn = pymysql.connect(
    host=‘rm-bp1vu5d84dg12c6d59o.mysql.rds.aliyuncs.com‘,
    port=3306,
    user=‘root‘,
    passwd=‘wYf092415*‘,
    db=‘pays‘,
    charset=‘utf8‘,
)
# 建立遊標
cursor = conn.cursor()

#切片函數
def section(info,key,len11):
    a = len(info)
    print(a, type(a))
    d = []
    e = 0
    g = -1
    i = 0
    task_class=[]
    while i < len(info):
        # for i in range(len(info)):
        # i+=1
        print("i::::", i)
        try:
            #c = info.index("a", e)
            #print("c:::::", c)
            c = info.index(key, e)
            #print("c:::::", c)

            print("c類型判斷",type(c))
        except ValueError:
            print(ValueError)
        try:
            if (c != ‘‘) & (g < int(c)):
                d.append(c)
                g = c
                i = c + 1
                print("illlldddd:", i)
                e = c + 1
                continue

            elif (c == ‘‘):
                 break
        except UnboundLocalError:
            print(UnboundLocalError)

            return task_class
        break
    print("d", d, type(d))
    print(d[0], type(d[0]))
    print("d的長度：",len(d))
    #開始切片
    if len(d) != 0:
        for j in range(len(d)):
            print("info11:::", info, type(info))
            info = ‘‘.join(info)
            print("info222:::",info,type(info))
            print("d[%d]"%j,d[j])
            #print("d[j]:5"%j,info[d[j]:5])

            llll = info[d[j]+1:d[j]+5]
            print("d[%d]:5" % j, llll)
            task_class.append(llll)
            print("task_class::11", task_class)

    task_class=",".join(task_class)
    print("str1112222",task_class)
    return task_class


def insettable(file):
    print("file：：：:::::::::::::::::", file)
    print("type：：：:::::::::::::::::", type(file))
    # file1 = file
    # file1 = str(file1)
    ddd = re.findall("知識庫\\\(\d+)", file)
    print("ddd：::::::::：：", ddd)
    print("ddd[0]:::", ddd[0])
    ddd = int(ddd[0])
    print("ddd::::", type(ddd))

    file = docx.Document(file)
    # 讀取表格：
    t = file.tables[0]
    print(t)
    print("1:", t.cell(0, 0).text)  # 1
    cell1 = t.cell(0, 0).text
    print("tyep::::", type(t.cell(0, 0).text))

    print("2:", t.cell(0, 1).text)  # 2
    cell2 = t.cell(0, 1).text

    print("2:", t.cell(0, 2).text)  # 2
    cell3 = t.cell(0, 2).text

    print("2:", t.cell(0, 3).text)  # 2
    cell4 = t.cell(0, 3).text
    print("cell4:::::::::", cell4)

    print("3:", t.cell(1, 0).text)  # 3
    cell5 = t.cell(1, 0).text

    print("4:", t.cell(1, 2).text)  # 4
    cell6 = t.cell(1, 2).text

    print("5:", t.cell(1, 3).text)  # 5
    task_type = t.cell(1, 3).text
    # task_type = re.findall(‘.*[?√](.*)$‘, cell7)
    # task_type = ‘‘.join(cell7)
    print("task_type111111:", task_type)
    # task_class = task_class[0:4]
    ‘‘‘低級處理方式
    a = int(task_type.count("?"))
    print("a|||||||", a, type(a))
    b = int(task_type.count("√"))
    print("b|||||||", b, type(a))
    if (a == 1) | (b == 1):
        print("111111111111111111")
        # task_type = re.findall(‘.*[?√](.*)$‘, task_type)
        task_type = re.findall(‘.*[?√](.*)$‘, task_type)
        print("task_type1", task_type)
        task_type = ‘‘.join(task_type)
        print("task_type2", task_type)
        task_type = task_type[0:4]
        print("task_type3:d:%s，b=%d" % (a, b), task_type)
    elif (a == 0) & (b == 0):
        print("2222222222222222222")
        task_type = ‘法定職責‘
        print("a:%s，b=%s" % (a, b), task_type)
    elif (a == 2) | (b == 2):
        print("333333333333333333333")
        task_type = ‘法定職責,工作職責 ‘
        print("a:%s，b=%s" % (a, b), task_type)
    ‘‘‘
    #調用切片函數
    task_type1 = section(task_type, "√", 4)
    task_type2 = section(task_type, "?", 4)
    task_type1 = "".join(task_type1)
    task_type2 = "".join(task_type2)
    print("task_type1:::", task_type1,type(task_type1))
    print("task_type2:::", task_type2,type(task_type2))
    if task_type1.strip()!="":
        task_type = task_type1
        print("task_type111:::", task_type1)
    elif task_type2.strip()!="":
        task_type = task_type2
        print("task_type222:::", task_type2)

    print("6:", t.cell(1, 4).text)  # 6
    cell8 = t.cell(1, 4).text

    print("7:", t.cell(2, 1).text)  # 7
    cell9 = t.cell(2, 1).text

    # 擷取文檔對象
    # file = docx.Document("D:\\配置庫\\公案APP\\1.2 系統規格\\知識庫\\14人員死亡先期處置.docx")
    print("段落數:" + str(len(file.paragraphs)))  # 段落數為13，每個斷行符號隔離一段
    lenn = len(file.paragraphs)
    print("len:", lenn)
    # 輸出每一段的內容
    for para in file.paragraphs:
        print(para.text)

    # 輸出段落編號及段落內容
    for i in range(len(file.paragraphs)):
        print("第" + str(i) + "段的內容是：" + file.paragraphs[i].text)

    list6 = []
    for i in range(len(file.paragraphs)):
        if 0 == i:
            print("i:", i)
            lis0 = file.paragraphs[i].text
            print("list0:", lis0)
            print(type(lis0))

        elif 1 == i:
            print("i:", i)
            task_class = file.paragraphs[i].text
            print("lis1", task_class,type(task_class))
            ‘‘‘低級處理方式
            print("task_class111111:", task_class)

            c = int(task_class.count("?"))
            task_class = ‘‘.join(task_class)
            #print(task_class.index(‘?‘))
            print("c|||||||", c, type(c))
            d = int(task_class.count("√"))
            print(task_class.index(‘√‘))

            print("d|||||||", d, type(d))
            task_class = re.findall(r‘[?√](?:.*)‘, task_class)
            task_class = ‘‘.join(task_class)
            task_class = task_class[1:5]
            print("task_class", task_class)
        ‘‘‘
            #調用切片函數
            task_class1 = section(task_class, "√", 4)
            task_class2 = section(task_class, "?", 4)
            task_class1 = "".join(task_class1)
            task_class2 = "".join(task_class2)
            print("task_class1:::", task_class1,type(task_class1))
            print("task_class2:::", task_class2,type(task_class2))
            if task_class1.strip()!="":
                task_class = task_class1
                print("task_class11:::", task_class1)
            elif task_class2.strip()!="":
                task_class = task_class2
                print("task_class22:::", task_class2)


        if 2 == i:
            print("i:", i)
            lis2 = file.paragraphs[i].text

            print("lis2", lis2)
            print(type(lis2))
            preparer = re.findall(‘填表單位：(.*?)$‘, lis2)
            preparer = ‘‘.join(preparer)
            print("preparer:%s" % preparer)

        # elif 3 == i:
        #     print("i:", i)
        #     lis3 = file.paragraphs[i].text
        elif 3 == i:
            print("i:", i)
            lis4 = file.paragraphs[i].text
            print("lis4", lis4)
            print(type(lis4))
        elif 3 < i < lenn - 1:
            print("i:", i)
            print(file.paragraphs[i].text)
            print(type(file.paragraphs[i].text))
            # list6[i-5] = list6.append(file.paragraphs[i].text)
            list6.append(str(file.paragraphs[i].text).strip(‘\xa0‘))
            # list6.append("%s\n" % str(file.paragraphs[i].text).strip(‘\xa0‘))
            print(list6)
    key_steps = "\n".join(list6)
    # print("key_steps:\n",key_steps.strip(‘\n‘))

    cursor.execute(
        "insert into `t_knowledge_base` (`no`, `preparer`, `task_class`, `task_name`, `task_specification`, `task_type`, `task_desc`, `task_basis`, `key_steps`) values (‘%d‘,‘%s‘,‘%s‘,‘%s‘,‘%s‘,‘%s‘,‘%s‘,NULL,‘%s‘)" % (
            ddd, preparer, task_class, cell2, cell4, task_type, cell9, key_steps))
    conn.commit()


def traverse(f):
    fs = os.listdir(f)
    for f1 in fs:
        tmp_path = os.path.join(f, f1)
        if not os.path.isdir(tmp_path):
            print(‘檔案: %s‘ % tmp_path)
            insettable(tmp_path)
        else:
            print(‘檔案夾：%s‘ % tmp_path)
            traverse(tmp_path)


path = ‘D:\\配置庫\公案APP\\1.2 系統規格\\知識庫‘
traverse(path)

#單檔案調測
# path = ‘D:\\配置庫\\公案APP\\1.2 系統規格\\知識庫\\14人員死亡先期處置.docx‘
# insettable(path)

# 關閉遊標
cursor.close()
# 關閉串連
conn.close()

python讀取word文檔，插入mysql資料庫執行個體