How to implement batch data extraction through Python-Python Tutorial-php.cn

Configuration requirements

1.ImageMagick

2.tesseract-OCR

3.Python3.7

4.from PIL import Image as PI

5.import io

6.import os

7.import pyocr.builders

8.from cnocr import CnOcr

import The data is converted into a digital format. Based on this, we need to first complete the conversion of uppercase Chinese characters and numbers.

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 = [&#39;壹&#39;, &#39;贰&#39;, &#39;叁&#39;, &#39;肆&#39;, &#39;伍&#39;, &#39;陆&#39;, &#39;柒&#39;, &#39;捌&#39;, &#39;玖&#39;]
    chArr = [&#39;拾&#39;, &#39;佰&#39;, &#39;仟&#39;, &#39;万&#39;, &#39;亿&#39;]
    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

Copy after login

The above code can be used to convert uppercase letters and numbers. For example, input "Twenty thousand yuan" to export "200000", and then convert it into numbers to greatly simplify the table. Operations can also be beneficial to data archiving while completing table operations. How to implement batch data extraction through Python

Next, we need to analyze the internal content of the invoice. From the following figure, we can see that we need to obtain the following data: "Invoice issuance date", "Bill of exchange arrival date", "Bill number", " Payee", "Bill Amount" and "Drawer" can be accurately positioned through drawing software.

As shown in the picture, the small black dot is where the mouse is, and the lower left corner of the drawing software is its coordinates.

How to implement batch data extraction through Python

Extract the issue date

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)

Copy after login

Withdraw the amount How to implement batch data extraction through Python

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

Copy after login

Extract the biller

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

Copy after login

Extract the payment bank

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

Copy after login

Extract the bill of exchange arrival date

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

Copy after login

Extract the bill document

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

Copy after login

After all the data is extracted, we enter the setting process. We need to extract all the bill files first , get their file names and paths.

ocr=CnOcr()
tool = pyocr.get_available_tools()[0]
filePath=&#39;img&#39;
img_name=[]
for i,j,name in os.walk(filePath):
    img_name=name

Copy after login

After obtaining the complete data, you can import the data into Excel.

count=1
book = xlwt.Workbook(encoding=&#39;utf-8&#39;,style_compression=0)
sheet = book.add_sheet(&#39;test&#39;,cell_overwrite_ok=True)
for i in img_name:
    img_url = filePath+"/"+i
    with open(img_url, &#39;rb&#39;) as f:
        a = f.read()
    new_img = PI.open(io.BytesIO(a))
    ## 写入csv
    col = (&#39;年份&#39;,&#39;出票日期&#39;,&#39;金额&#39;,&#39;出票人&#39;,&#39;付款行全称&#39;,&#39;汇票到日期&#39;,&#39;备注&#39;)
    for j in range(0,7):
        sheet.write(0,j,col[j])
    book.save(&#39;1.csv&#39;)
    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

Copy after login

At this point, the complete process is over.

Attached are all source codes

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 = [&#39;壹&#39;, &#39;贰&#39;, &#39;叁&#39;, &#39;肆&#39;, &#39;伍&#39;, &#39;陆&#39;, &#39;柒&#39;, &#39;捌&#39;, &#39;玖&#39;]
    chArr = [&#39;拾&#39;, &#39;佰&#39;, &#39;仟&#39;, &#39;万&#39;, &#39;亿&#39;]
    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

Copy after login

The above is the detailed content of How to implement batch data extraction through Python. For more information, please follow other related articles on the PHP Chinese website!

How to implement batch data extraction through Python

Configuration requirements

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 txt3Copy after login

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 txt4Copy after login

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 txt5Copy after login

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 txt6Copy after login

ocr=CnOcr() tool = pyocr.get_available_tools()[0] filePath=&#39;img&#39; img_name=[] for i,j,name in os.walk(filePath): img_name=nameCopy after login

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
Copy after login

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
Copy after login

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
Copy after login

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
Copy after login

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