feat(text-extraction): Remove try except for simple logic

doctor/lib/text_extraction.py

@@ -43,33 +43,26 @@ def get_page_text(page: pdfplumber.PDF.pages, strip_margin: bool) -> str:
     :param strip_margin: a flag to crop out the margin of a document and skewed content
     :return: Text from the pdf plumber page
     """
-    if strip_margin:
+    _, _, width, height = page.bbox
+    if strip_margin and (height > width):
         # Crop margins and remove skewed text
-        _, _, width, height = page.bbox
         pixels_per_inch = width / 8.5
         bbox = (
             0,
             pixels_per_inch * 1,  # 1 inch down from top
             width,  #
             pixels_per_inch * 10,  # 10 inches from top (1 inch from bottom)
         )
-        try:
-            page_text = (
-                page.crop(bbox)
-                .filter(is_skewed)
-                .extract_text(
-                    layout=True,
-                    keep_blank_chars=True,
-                    y_tolerance=5,
-                    y_density=25,
-                )
-            )
-        except ValueError:
-            # If bounding box is non standard we do not want to apply strip margin
-            page_text = page.extract_text(
-                layout=True, keep_blank_chars=True, y_tolerance=5, y_density=25
+        page_text = (
+            page.crop(bbox)
+            .filter(is_skewed)
+            .extract_text(
+                layout=True,
+                keep_blank_chars=True,
+                y_tolerance=5,
+                y_density=25,
             )
-
+        )
     else:
         page_text = page.extract_text(
             layout=True, keep_blank_chars=True, y_tolerance=5, y_density=25