Update app.py

app.py

@@ -18,43 +18,47 @@ Parameters:
 Returns:
 - text (str): The extracted text from the specified section range.
 """
-def get_section(path, wanted_section, next_section):
-    print(wanted_section)
+# def get_section(path, wanted_section, next_section):
+#     print(wanted_section)
 
-    # Open the PDF file
-    doc = pdfplumber.open(path)
-    start_page = []
-    end_page = []
+#     # Open the PDF file
+#     doc = pdfplumber.open(path)
+#     start_page = []
+#     end_page = []
 
-    # Find the all the pages for the specified sections
-    for page in range(len(doc.pages)):
-        if len(doc.pages[page].search(wanted_section, return_chars = False, case = False)) > 0:
-            start_page.append(page)
-        if len(doc.pages[page].search(next_section, return_chars = False, case = False)) > 0:
-            end_page.append(page)
-    print(max(start_page))
-    print(max(end_page))
+#     # Find the all the pages for the specified sections
+#     for page in range(len(doc.pages)):
+#         if len(doc.pages[page].search(wanted_section, return_chars = False, case = False)) > 0:
+#             start_page.append(page)
+#         if len(doc.pages[page].search(next_section, return_chars = False, case = False)) > 0:
+#             end_page.append(page)
+#     print(max(start_page))
+#     print(max(end_page))
 
-    # Extract the text between the start and end page of the wanted section
-    text = []
-    for page_num in range(max(start_page), max(end_page)):
-        page = doc.pages[page_num]
-        text.append(page.extract_text())
-    text = " ".join(text)
-    new_text = text.replace("\n", " ")
-    special_char_unicode_list = ["\u00e4", "\u00f6", "\u00fc", "\u00df"]
-    special_char_replacement_list = ["ae", "oe", "ue", "ss"]
-    for index, special_char in enumerate(special_char_unicode_list):
-        final_text = new_text.replace(special_char, special_char_replacement_list[index])
-    return final_text
+#     # Extract the text between the start and end page of the wanted section
+#     text = []
+#     for page_num in range(max(start_page), max(end_page)):
+#         page = doc.pages[page_num]
+#         text.append(page.extract_text())
+#     text = " ".join(text)
+#     new_text = text.replace("\n", " ")
+#     special_char_unicode_list = ["\u00e4", "\u00f6", "\u00fc", "\u00df"]
+#     special_char_replacement_list = ["ae", "oe", "ue", "ss"]
+#     for index, special_char in enumerate(special_char_unicode_list):
+#         final_text = new_text.replace(special_char, special_char_replacement_list[index])
+#     return final_text
 
 
 def process_pdf(path):
 
-    results_dict = {}
-    results_dict["2.1 Aktualisierte Einordnung des Moduls in das EZ-Programm"] = \
-        get_section(path, "2.1 Aktualisierte Einordnung des Moduls in das EZ-Programm", "2.2 Andere Entwicklungsmaßnahmen im konkreten Interventionsbereich des Moduls")
-    """
+    doc = pdfplumber.open(path)
+
+    return doc
+
+    # results_dict = {}
+    # results_dict["2.1 Aktualisierte Einordnung des Moduls in das EZ-Programm"] = \
+    #     get_section(path, "2.1 Aktualisierte Einordnung des Moduls in das EZ-Programm", "2.2 Andere Entwicklungsmaßnahmen im konkreten Interventionsbereich des Moduls")
+     """
     results_dict["2.1 Aktualisierte Einordnung des Moduls in das EZ-Programm"] = \
         get_section(path,"2.1 Aktualisierte Einordnung des Moduls in das EZ-Programm", "2.2 Andere Entwicklungsmaßnahmen im konkreten Interventionsbereich des Moduls")
     results_dict["2.2 Andere Entwicklungsmaßnahmen im konkreten Interventionsbereich des Moduls"] = \