コード例 #1
0
 def test_extract_lines_from_multiple_boxes(self):
     pages = extract_pages(self.test_pdf)
     for page in pages:
         textboxes = extract_textboxes(page)
         result = extract_lines(textboxes)
         for line in result:
             self.assertIsInstance(line, LTTextLineHorizontal)
コード例 #2
0
 def test_extract_lines_from_single_textboxs(self):
     pages = extract_pages(self.test_pdf)
     for page in pages:
         textboxes = extract_textboxes(page)
         for textbox in textboxes:
             result = extract_lines(textbox)
             for line in result:
                 self.assertIsInstance(line, LTTextLineHorizontal)
コード例 #3
0
 def test_extract_characters_from_multiple_lines(self):
     pages = extract_pages(self.test_pdf)
     for page in pages:
         textboxes = extract_textboxes(page)
         for textbox in textboxes:
             lines = extract_lines(textbox)
             characters = extract_characters(lines)
             for character in characters:
                 self.assertIsInstance(character, LTChar)