" + text.replace("\n", "
") + "
" - - tables = page.extract_tables() - if tables: - for table in tables: - csv_output = StringIO() - csv_writer = csv.writer(csv_output) - csv_writer.writerows(table) - result += f"{csv_output.getvalue()}"
-
- # Извлечение изображений
- if page.images:
- for img in page.images:
- img_data = img["stream"].get_data()
- encoded_img = base64.b64encode(img_data).decode("utf-8")
- result += f'
'
-
- elif file_path.endswith(".docx"):
- doc = docx.Document(file_path)
-
- text_data = []
- table_data = []
- image_data = []
-
- for para in doc.paragraphs:
- if para.text.strip():
- text_data.append(f"{para.text}
") - - for table in doc.tables: - csv_output = StringIO() - csv_writer = csv.writer(csv_output) - for row in table.rows: - csv_writer.writerow([cell.text.strip() for cell in row.cells]) - table_data.append(f"{csv_output.getvalue()}")
-
- # Извлечение изображений
- for rel in doc.part.rels:
- if "image" in doc.part.rels[rel].target_ref:
- image_data_blob = doc.part.rels[rel].target_part.blob
- encoded_img = base64.b64encode(image_data_blob).decode("utf-8")
- image_data.append(f'')
-
- if text_data:
- result += "".join(text_data)
- if table_data:
- result += "".join(table_data)
- if image_data:
- result += "".join(image_data)
-
- return result
+import pdfplumber
+import docx
+import csv
+import os
+from io import StringIO, BytesIO
+from PIL import Image
+import base64
+
+
+def extract_text_tables(file_path: str) -> str:
+ result = ""
+ if file_path.endswith(".pdf"):
+ with pdfplumber.open(file_path) as pdf:
+ for page in pdf.pages:
+ text = page.extract_text()
+ if text:
+ result += "" + text.replace("\n", "
") + "
" + + tables = page.extract_tables() + if tables: + for table in tables: + csv_output = StringIO() + csv_writer = csv.writer(csv_output) + csv_writer.writerows(table) + result += f"{csv_output.getvalue()}"
+
+ # Извлечение изображений
+ if page.images:
+ for img in page.images:
+ img_data = img["stream"].get_data()
+ encoded_img = base64.b64encode(img_data).decode("utf-8")
+ result += f''
+
+ elif file_path.endswith(".docx"):
+ doc = docx.Document(file_path)
+
+ text_data = []
+ table_data = []
+ image_data = []
+
+ for para in doc.paragraphs:
+ if para.text.strip():
+ text_data.append(f"{para.text}
") + + for table in doc.tables: + csv_output = StringIO() + csv_writer = csv.writer(csv_output) + for row in table.rows: + csv_writer.writerow([cell.text.strip() for cell in row.cells]) + table_data.append(f"{csv_output.getvalue()}")
+
+ # Извлечение изображений
+ for rel in doc.part.rels:
+ if "image" in doc.part.rels[rel].target_ref:
+ image_data_blob = doc.part.rels[rel].target_part.blob
+ encoded_img = base64.b64encode(image_data_blob).decode("utf-8")
+ image_data.append(f'')
+
+ if text_data:
+ result += "".join(text_data)
+ if table_data:
+ result += "".join(table_data)
+ if image_data:
+ result += "".join(image_data)
+
+ return result
diff --git a/тесты.txt b/тесты.txt
deleted file mode 100644
index c3da715..0000000
--- a/тесты.txt
+++ /dev/null
@@ -1,13 +0,0 @@
-python manage.py runserver
-
-------------------------------------------
-
-Тест расширения для сканирования:
-
-curl -X POST -F "document=@C:\Users\egord\Desktop\API EasyAccess\api_project\media\uploads\Деев Е.В. Резюме.pdf" http://localhost:8000/api/document-to-text/
-
-------------------------------------------
-
-Тест для аудио транскрипции:
-
-curl -X POST -F audio=@"C:\Users\egord\Desktop\API EasyAccess\api_project\media\uploads\audio.ogg" http://localhost:8000/api/audio-to-text/
\ No newline at end of file