Update 2.CV_Uploader.py

IT17163682/2.CV_Uploader.py

+#Text to String (utf-8)
+import re
+import os
+from chardet import detect
 import docx2txt
-
-CV = docx2txt.process("se resume.docx")
+#Upload Resume
 
 
+CV = docx2txt.process("C:/Users/User/Desktop/New folder (12)/Applicant_Ranker - Copy/UploadedCV/Mahela.docx")
 with open("Resume.txt", "w") as text_file:
-    print(CV, file=text_file)
+    print(CV, file=text_file)
\ No newline at end of file
+
+# get file encoding type
+def get_encoding_type(file):
+    with open(file, 'rb') as f:
+        rawdata = f.read()
+    return detect(rawdata)['encoding']
+
+from_codec = get_encoding_type('Resume.txt')
+
+#Resume convertion
+try:
+    with open('Resume.txt', 'r', encoding=from_codec) as f, open('ResumeStr.txt', 'w', encoding='utf-8') as e:
+        text = f.read() # for small files, for big use chunks
+        e.write(text)
+
+except UnicodeDecodeError:
+    print('Decode Error')
+except UnicodeEncodeError:
+    print('Encode Error')
+
+
+f = open("ResumeStr.txt", "r")
+content = f.read()
+
+
+def check(string):
+    regex = re.compile("twitter.+\w*")
+    match_object = regex.findall(string)
+    if len(match_object) != 0:
+        for word in match_object:
+            return word
+    else:
+        print("No Twitter Details")
+
+Twitter_link = str(check(content))
+Twitter_ID = Twitter_link[Twitter_link.find("/")+1:]
+with open('TwitterID.txt', 'w') as the_file:
+    the_file.write(Twitter_ID)
+
+#print(Twitter_ID)
\ No newline at end of file