init

.gitignore

@@ -0,0 +1 @@
+*.pdf

app.py

@@ -0,0 +1,13 @@
+import fitz
+import re
+
+doc = fitz.open("test.pdf")
+index_page = doc[0]
+blocks = index_page.get_text("blocks")
+
+for block in blocks:
+    text = block[4].strip()
+    print(int(text))
+    match = re.search(r'(\d+)', text)
+    if match:
+        print(match.group(1))