We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent af84901 commit 3a59150Copy full SHA for 3a59150
python-read-docx/read_docx.py
@@ -0,0 +1,19 @@
1
+import docx
2
+
3
+#Extract text from DOCX
4
+def getDocxContent(filename):
5
+ doc = docx.Document(filename)
6
+ fullText = ""
7
+ for para in doc.paragraphs:
8
+ fullText += para.text
9
+ return fullText
10
11
+resume = getDocxContent("sample.docx")
12
13
+#Importing NLTK for sentence tokenizing
14
+from nltk.tokenize import sent_tokenize
15
16
+sentences = sent_tokenize(resume)
17
+for sentence in sentences:
18
+ print(sentence)
19
+ print("\n")
python-read-docx/readme.rst
@@ -0,0 +1 @@
+You can read tutorial https://www.roytuts.com/read-word-file-using-python/
0 commit comments