Bagaimana untuk melaksanakan pengekstrakan data kelompok melalui Python

Keperluan konfigurasi

1.ImageMagick

2.tesseract-OCR

3.Python3.7

4.dari PIL import Imej sebagai PI

5.import io

6.import os

7.import pyocr.builders

8.daripada cnocr import CnOcr

9.import xlwt

Analisis angka di atas menunjukkan bahawa amaun bil ialah "Dua puluh satu ratus ribu yuan", dan jumlah data adalah dalam huruf besar Cina, jadi kita perlu menukar jumlah bil sebelum mengimportnya ke dalam Excel Data ditukar kepada format digital Berdasarkan ini, kita perlu terlebih dahulu melengkapkan penukaran aksara dan nombor Cina.

def chineseNumber2Int(strNum: str):
    result = 0
    temp = 1  # 存放一个单位的数字如：十万
    count = 0  # 判断是否有chArr
    cnArr = ['壹', '贰', '叁', '肆', '伍', '陆', '柒', '捌', '玖']
    chArr = ['拾', '佰', '仟', '万', '亿']
    for i in range(len(strNum)):
        b = True
        c = strNum[i]
        for j in range(len(cnArr)):
            if c == cnArr[j]:
                if count != 0:
                    result += temp
                    count = 0
                temp = j + 1
                b = False
                break
        if b:
            for j in range(len(chArr)):
                if c == chArr[j]:
                    if j == 0:
                        temp *= 10
                    elif j == 1:
                        temp *= 100
                    elif j == 2:
                        temp *= 1000
                    elif j == 3:
                        temp *= 10000
                    elif j == 4:
                        temp *= 100000000
                count += 1
        if i == len(strNum) - 1:
            result += temp
    return result

Kod di atas boleh digunakan untuk menukar huruf besar dan nombor Sebagai contoh, masukkan "Dua puluh ribu yuan" untuk mengeksport "200000", dan kemudian menukarnya kepada nombor untuk memudahkan operasi juga berfaedah kepada pengarkiban data semasa menyelesaikan operasi jadual.

Seterusnya, kita perlu menganalisis kandungan dalaman invois Menganalisis gambar di bawah menunjukkan bahawa kita perlu mendapatkan data berikut: "Tarikh pengeluaran invois", "Tarikh ketibaan bil pertukaran", "Nombor bil. ", " Penerima", "Amaun Bil" dan "Laci" boleh diletakkan dengan tepat melalui perisian lukisan.

Seperti yang ditunjukkan dalam gambar, titik hitam kecil adalah tempat tetikus berada, dan sudut kiri bawah perisian lukisan ialah koordinatnya.

Ekstrak tarikh pengebilan

def text1(new_img):
    #提取出票日期
    left = 80
    top = 143
    right = 162
    bottom = 162
    image_text1 = new_img.crop((left, top, right, bottom))
    #展示图片
    #image_text1.show()
    txt1 = tool.image_to_string(image_text1)
    print(txt1)
    return str(txt1)

Ekstrak amaun

def text2(new_img):
    #提取金额
    left = 224
    top = 355
    right = 585
    bottom = 380
    image_text2 = new_img.crop((left, top, right, bottom))
    #展示图片
    #image_text2.show()
    image_text2.save("img/tmp.png")
    temp = ocr.ocr("img/tmp.png")
    temp="".join(temp[0])
    txt2=chineseNumber2Int(temp)
    print(txt2)
    return txt2

Ekstrak pengebil

def text3(new_img):
    #提取出票人
    left = 177
    top = 207
    right = 506
    bottom = 231
    image_text3 = new_img.crop((left, top, right, bottom))
    #展示图片
    #image_text3.show()
    image_text3.save("img/tmp.png")
    temp = ocr.ocr("img/tmp.png")
    txt3="".join(temp[0])
    print(txt3)
    return txt3

Ekstrak baris pembayaran

def text4(new_img):
    #提取付款行
    left = 177
    top = 274
    right = 492
    bottom = 311
    image_text4 = new_img.crop((left, top, right, bottom))
    #展示图片
    #image_text4.show()
    image_text4.save("img/tmp.png")
    temp = ocr.ocr("img/tmp.png")
    txt4="".join(temp[0])
    print(txt4)
    return txt4

Ekstrak bil tarikh ketibaan pertukaran

def text5(new_img):
    #提取汇票到日期
    left = 92
    top = 166
    right = 176
    bottom = 184
    image_text5 = new_img.crop((left, top, right, bottom))
    #展示图片
    #image_text5.show()
    txt5 = tool.image_to_string(image_text5)
    print(txt5)
    return txt5

Ekstrak dokumen bil

def text6(new_img):
    #提取票据号码
    left = 598
    top = 166
    right = 870
    bottom = 182
    image_text6 = new_img.crop((left, top, right, bottom))
    #展示图片
    #image_text6.show()
    txt6 = tool.image_to_string(image_text6)
    print(txt6)
    return txt6

Selepas semua data diekstrak, kami memasuki proses persediaan Kami perlu mengekstrak semua fail bil dahulu , dapatkan nama fail dan laluannya.

ocr=CnOcr()
tool = pyocr.get_available_tools()[0]
filePath='img'
img_name=[]
for i,j,name in os.walk(filePath):
    img_name=name

Selepas mendapatkan data lengkap, anda boleh mengimport data ke dalam Excel.

count=1
book = xlwt.Workbook(encoding='utf-8',style_compression=0)
sheet = book.add_sheet('test',cell_overwrite_ok=True)
for i in img_name:
    img_url = filePath+"/"+i
    with open(img_url, 'rb') as f:
        a = f.read()
    new_img = PI.open(io.BytesIO(a))
    ## 写入csv
    col = ('年份','出票日期','金额','出票人','付款行全称','汇票到日期','备注')
    for j in range(0,7):
        sheet.write(0,j,col[j])
    book.save('1.csv')
    shijian=text1(new_img)
    sheet.write(count,0,shijian[0:4])
    sheet.write(count,1,shijian[5:])
    sheet.write(count,2,text2(new_img))
    sheet.write(count,3,text3(new_img))
    sheet.write(count,4,text4(new_img))
    sheet.write(count,5,text5(new_img))
    sheet.write(count,6,text6(new_img))
    count = count + 1

Pada ketika ini, proses lengkap telah berakhir.

Semua kod sumber dilampirkan

from  wand.image import  Image
from PIL import Image as PI
import pyocr
import io
import re
import os
import shutil
import pyocr.builders
from cnocr import CnOcr
import requests
import xlrd
import xlwt
from openpyxl import load_workbook
 
def chineseNumber2Int(strNum: str):
    result = 0
    temp = 1  # 存放一个单位的数字如：十万
    count = 0  # 判断是否有chArr
    cnArr = ['壹', '贰', '叁', '肆', '伍', '陆', '柒', '捌', '玖']
    chArr = ['拾', '佰', '仟', '万', '亿']
    for i in range(len(strNum)):
        b = True
        c = strNum[i]
        for j in range(len(cnArr)):
            if c == cnArr[j]:
                if count != 0:
                    result += temp
                    count = 0
                temp = j + 1
                b = False
                break
        if b:
            for j in range(len(chArr)):
                if c == chArr[j]:
                    if j == 0:
                        temp *= 10
                    elif j == 1:
                        temp *= 100
                    elif j == 2:
                        temp *= 1000
                    elif j == 3:
                        temp *= 10000
                    elif j == 4:
                        temp *= 100000000
                count += 1
        if i == len(strNum) - 1:
            result += temp
    return result
 
 
def text1(new_img):
    #提取出票日期
 
    left = 80
    top = 143
    right = 162
    bottom = 162
    image_text1 = new_img.crop((left, top, right, bottom))
    #展示图片
    #image_text1.show()
    txt1 = tool.image_to_string(image_text1)
 
    print(txt1)
    return str(txt1)
def text2(new_img):
    #提取金额
 
    left = 224
    top = 355
    right = 585
    bottom = 380
    image_text2 = new_img.crop((left, top, right, bottom))
    #展示图片
    #image_text2.show()
    image_text2.save("img/tmp.png")
 
    temp = ocr.ocr("img/tmp.png")
 
    temp="".join(temp[0])
    txt2=chineseNumber2Int(temp)
    print(txt2)
 
    return txt2
 
def text3(new_img):
    #提取出票人
 
    left = 177
    top = 207
    right = 506
    bottom = 231
    image_text3 = new_img.crop((left, top, right, bottom))
    #展示图片
    #image_text3.show()
    image_text3.save("img/tmp.png")
 
    temp = ocr.ocr("img/tmp.png")
    txt3="".join(temp[0])
 
    print(txt3)
    return txt3
def text4(new_img):
    #提取付款行
 
    left = 177
    top = 274
    right = 492
    bottom = 311
    image_text4 = new_img.crop((left, top, right, bottom))
    #展示图片
    #image_text4.show()
    image_text4.save("img/tmp.png")
 
    temp = ocr.ocr("img/tmp.png")
    txt4="".join(temp[0])
 
    print(txt4)
    return txt4
def text5(new_img):
    #提取汇票到日期
 
    left = 92
    top = 166
    right = 176
    bottom = 184
    image_text5 = new_img.crop((left, top, right, bottom))
    #展示图片
    #image_text5.show()
    txt5 = tool.image_to_string(image_text5)
 
    print(txt5)
    return txt5
def text6(new_img):
    #提取票据号码
 
    left = 598
    top = 166
    right = 870
    bottom = 182
    image_text6 = new_img.crop((left, top, right, bottom))
    #展示图片
    #image_text6.show()
    txt6 = tool.image_to_string(image_text6)
 
    print(txt6)
    return txt6
 
 
 
ocr=CnOcr()
 
tool = pyocr.get_available_tools()[0]
 
filePath='img'
img_name=[]
for i,j,name in os.walk(filePath):
    img_name=name
count=1
 
book = xlwt.Workbook(encoding='utf-8',style_compression=0)
sheet = book.add_sheet('test',cell_overwrite_ok=True)
 
for i in img_name:
    img_url = filePath+"/"+i
    with open(img_url, 'rb') as f:
        a = f.read()
    new_img = PI.open(io.BytesIO(a))
    ## 写入csv
    col = ('年份','出票日期','金额','出票人','付款行全称','汇票到日期','备注')
    for j in range(0,7):
        sheet.write(0,j,col[j])
    book.save('1.csv')
    shijian=text1(new_img)
    sheet.write(count,0,shijian[0:4])
    sheet.write(count,1,shijian[5:])
    sheet.write(count,2,text2(new_img))
    sheet.write(count,3,text3(new_img))
    sheet.write(count,4,text4(new_img))
    sheet.write(count,5,text5(new_img))
    sheet.write(count,6,text6(new_img))
    count = count + 1

Atas ialah kandungan terperinci Bagaimana untuk melaksanakan pengekstrakan data kelompok melalui Python. Untuk maklumat lanjut, sila ikut artikel berkaitan lain di laman web China PHP!