TextStorage class

app/main/reports/text_storage/text_storage.py

@@ -0,0 +1,40 @@
+from app.main.reports.docx_uploader import DocxUploader
+
+
+class TextStorage:
+    def __init__(self, filepath, pdf_filepath=''):
+        self.chapters = []
+        self.headers = []
+        self.docx = DocxUploader()
+        self.docx.upload(filepath, pdf_filepath)
+        self.docx.parse()
+        self.docx.chapters = self.docx.make_chapters("VKR")
+        self.docx.headers = self.docx.make_headers("VKR")
+
+    def parse_headers_and_pages(self):
+        text_on_page = self.docx.pdf_file.get_text_on_page()
+        keys = list(text_on_page.keys())
+        values = list(text_on_page.values())
+        for page_text in text_on_page.values():
+            for chapter in self.chapters:
+                if chapter["header"] in page_text:
+                    pos = values.index(page_text)
+                    chapter["start_page"] = keys[pos]
+
+    def parse_chapters(self):
+        for chapter in self.docx.chapters:
+            if chapter["child"] != [] and "heading" in chapter["style"]:
+                temp_text = ""
+                for i in range(len(chapter["child"])):
+                    temp_text += chapter["child"][i]["styled_text"]["text"]
+                self.chapters.append({"header": chapter["styled_text"]["text"], "start_page": 0, "text": temp_text})
+
+
+if __name__ == "__main__":
+    docx_path = "/home/vilka/Downloads/petrov.docx"
+    pdf_path = "/home/vilka/Downloads/petrov.pdf"
+    text_storage = TextStorage(docx_path, pdf_path)
+    text_storage.parse_chapters()
+    text_storage.parse_headers_and_pages()
+    for ch in text_storage.chapters:
+        print(ch)