Update 'Business_cards/Business_cards.py'

Business_cards/Business_cards.py

@@ -1,6 +1,6 @@
 from flask import Flask, render_template, request, redirect, Response, send_file
 import os
-import openai
+# import openai
 import requests
 import pandas as pd
 import pgeocode
@@ -15,6 +15,11 @@ from functools import partial
 from urlextract import URLExtract
 import pytesseract as tess
 from PIL import Image
+# from doctr.io import DocumentFile
+# from doctr.models import ocr_predictor
+# model = ocr_predictor(pretrained=True)
+# load tagger
+######################################################
 import os
 import glob
 
@@ -29,6 +34,9 @@ import time
 import multiprocessing
 from PIL import Image
 from functools import partial
+nlp_model = spacy.load("D:/projects/C01app/Resume_parser/ME")
+nlp_model1 = spacy.load("D:/projects/C01app/Resume_parser/bdeeducation_50_0.2")
+from flask import Flask, render_template, request, redirect, Response, send_file
 
 import pandas as pd
 ################################################################
@@ -49,7 +57,7 @@ model = AutoModelForTokenClassification.from_pretrained("ml6team/bert-base-uncas
 
 from paddleocr import PaddleOCR, draw_ocr
 
-ocr = PaddleOCR(use_angle_cls=True, lang='en', use_space_char=True, show_log=True)
+ocr = PaddleOCR(use_angle_cls=True, lang='en', use_space_char=True, show_log=False)
 tagger = SequenceTagger.load("flair/ner-english-large")
 
 import datetime
@@ -59,7 +67,23 @@ app = Flask(__name__)
 
 # app.config["IMAGE_UPLOADS"] = "C:/inetpub/wwwroot/FlaskApplication/Flask_Demo/upload/"
 
+
 @app.route('/', methods=['GET'])
+def home():
+    return render_template('home.html')
+
+
+@app.route('/resume', methods=['GET'])
+def resume():
+    return render_template('resume.html')
+
+
+@app.route('/invoice', methods=['GET'])
+def invoice():
+    return render_template('invoice.html')
+
+
+@app.route('/card', methods=['GET'])
 def card():
     return render_template('card.html')
 
@@ -407,7 +431,7 @@ def multiplecards():
         htext = x
         # print('------------------------------------------------')
         #print('############################################################# this is verticaltext #################################################################')
-       # print(verticaltext)
+        print(verticaltext)
         htext = htext.replace('\n', ' ')
        # print('############################################################# this is htext #############################################################')
         #print(htext)
@@ -463,9 +487,10 @@ def multiplecards():
                 addrespinlst.append(Address)
 
             except NameError:
+                final.append('ADDRESS--')
 
-                print(
-                    '############################################################ Addressmodelworking #############################################################')
+
+                #print('############################################################ Addressmodelworking #############################################################')
 
                 # doc = nlp_model1(textaddress)
                 # addlist = []
@@ -854,6 +879,32 @@ def multiplecards():
             number = str(number).split(")")
             num.append(number[1])
             # num.append(number[-1])
+
+        print(num)
+        import re
+
+        # Input list of strings
+#         num =[' 7227906777Extn1204634444']
+
+
+        # Define a regular expression pattern to split when text is present
+        pattern = r'[a-zA-Z]+'
+
+        # Function to split a string based on the pattern
+        def split_string(text):
+            return re.split(pattern, text)
+
+        # Process each line in the list
+        split_lines = [split_string(line) for line in num]
+
+        # Flatten the list of lists into a single list
+        split_lines = [item for sublist in split_lines for item in sublist]
+
+        # Remove any empty strings
+        num = [item for item in split_lines if item]
+
+        # Print the split lines
+        print(num)
         if len(num) == 0:
             final.append("ContactNumber--")
             final.append("OrganizationNumber--")
@@ -985,7 +1036,7 @@ def multiplecards():
             final.append(county_name)
 
         except (IndexError, NameError):
-            final.append("PinCode1--")
+            final.append("PinCode1--"+" ")
             final.append("country_code--")
             final.append("LandMark1--")
             final.append("state_name--")
@@ -1004,6 +1055,11 @@ def multiplecards():
         df1.to_csv('path123.csv', index=False)
         df2 = pd.read_csv('path123.csv')
         print(df2)
+        if df2['Values'].isnull().all():
+            print("Column 'Column2' is empty.")
+            return 'Invalid image'
+        else:
+            pass
         df2 = df2.T
         df2.to_csv('path1.csv', index=False, header=False)
         df1 = pd.read_csv('path1.csv')
@@ -1062,7 +1118,11 @@ def multiplecards():
         
         zlist.append(z)
         #############################################creating csv#####################################
-        #print(final)
+       # print(final)
+
+        
+
+        
         #print(imagelist)
         #final.append('image--' + str(imagelist))
        #  import requests
@@ -1111,7 +1171,5 @@ def multiplecards():
     return zlist
 
 
-
-
 if __name__ == "__main__":
     app.run(host='0.0.0.0', port=1112)