Feature: streamlit website

.gitignore

@@ -161,4 +161,6 @@ Thumbs.db
 MyClippings.txt
 dist/
 images/
-my_kindle_clippings.json
+my_kindle_clippings.json
+/My Clippings.txt
+.streamlit/secrets.toml

.streamlit/config.toml

@@ -0,0 +1,2 @@
+[theme]
+base="light"

app.py

@@ -0,0 +1,91 @@
+from io import StringIO
+
+import streamlit as st
+
+from kindle2notion.__main__ import (
+    update_kindle_clippings_streamlit,
+)
+
+st.set_page_config(
+    page_title="Kindle 2 Notion",
+    page_icon="📓",
+    layout="wide",
+    initial_sidebar_state="expanded",
+    menu_items={
+        "Get help": "https://github.com/paperboi/kindle2notion",
+        "Report a bug": "https://github.com/paperboi/kindle2notion/issues",
+        "About": "Streamlit adaptation for [Kindle2Notion library](https://github.com/paperboi/kindle2notion)",
+    },
+)
+
+
+def main():
+    st.write(
+        """
+    # Kindle 2 Notion
+
+    Streamlit adaptation for [Kindle2Notion library](https://github.com/paperboi/kindle2notion)
+
+    ## Prerequisites
+    """
+    )
+    with st.expander("**Show requirements**", expanded=False):
+        st.write(
+            """ 
+    1. Create an integration on Notion.
+
+        1. Duplicate this [database template](https://kindle2notion.notion.site/6d26062e3bb04dd89b988806978c1fe7?v=0d394a8162cc481280966b35a37465c2) to your the workspace you want to use for storing your Kindle clippings.
+        2. Open _Settings & Members_ from the left navigation bar.
+        3. Select the _Integrations_ option listed under _Workspaces_ in the settings modal.
+        4. Click on _Develop your own integrations_ to redirect to the integrations page.
+        5. On the integrations page, select the _New integration_ option and enter the name of the integration and the workspace you want to use it with. Hit submit and your internal integration token will be generated.
+
+    2. Go back to your database page and click on the _Share_ button on the top right corner. Use the selector to find your integration by its name and then click _Invite_. Your integration now has the requested permissions on the new database. 
+    """
+        )
+    form = st.form("kindle_form")
+    notion_database_id = form.text_input(
+        "Notion Database ID",
+        help="""
+        Find your _notion_database_id_ from the URL of the database you have copied to your workspace. For reference: 
+
+        `https://www.notion.so/myworkspace/a8aec43384f447ed84390e8e42c2e089?v=...` 
+
+        **_a8aec43384f447ed84390e8e42c2e089_** is the database_id
+        """,
+    )
+    notion_api_auth_token = form.text_input(
+        "Notion API Token",
+        type="password",
+    )
+    clippings_file = form.file_uploader("Upload your clippings file", type=["txt"])
+    enable_highlight_date = form.toggle(
+        "Enable Highlight Date",
+        help="Set to False if you don't want to see the _Date Added_ information in",
+    )
+    enable_book_cover = form.toggle(
+        "Enable Book Cover",
+        help="Set to False if you don't want to store the book cover in Notion.",
+    )
+    clippings_data = None
+
+    submit = form.form_submit_button("Send Kindle Clippings to Notion")
+    if submit:
+        if clippings_file is not None:
+            # To convert to a string based IO:
+            stringio = StringIO(clippings_file.getvalue().decode("utf-8-sig"))
+            # To read file as string:
+            clippings_data = stringio.read()
+        with st.spinner("Uploading data to Notion..."):
+            update_kindle_clippings_streamlit(
+                notion_api_auth_token,
+                notion_database_id,
+                clippings_data,
+                enable_highlight_date,
+                enable_book_cover,
+            )
+        st.success("Kindle Clippings have been synced.")
+
+
+if __name__ == "__main__":
+    main()

kindle2notion/__main__.py

@@ -5,7 +5,81 @@
 
 from kindle2notion.exporting import export_to_notion
 from kindle2notion.parsing import parse_raw_clippings_text
-from kindle2notion.reading import read_raw_clippings
+from kindle2notion.reading import read_raw_clippings, read_raw_clippings_streamlit
+
+
+def process_kindle_clippings(
+    notion_api_auth_token,
+    notion_database_id,
+    all_clippings,
+    enable_highlight_date,
+    enable_book_cover,
+):
+    # Parse all_clippings file and format the content to be sent tp the Notion DB into all_books
+    all_books = parse_raw_clippings_text(all_clippings)
+    # Export all the contents in all_books into the Notion DB.
+    export_to_notion(
+        all_books,
+        enable_highlight_date,
+        enable_book_cover,
+        notion_api_auth_token,
+        notion_database_id,
+    )
+    with open("my_kindle_clippings.json", "w") as out_file:
+        json.dump(all_books, out_file, indent=4)
+    print("Transfer complete... Exiting script...")
+
+
+def update_kindle_clippings_streamlit(
+    notion_api_auth_token,
+    notion_database_id,
+    clippings_data,
+    enable_highlight_date,
+    enable_book_cover,
+):
+    notion = notional.connect(auth=notion_api_auth_token)
+    db = notion.databases.retrieve(notion_database_id)
+    if db:
+        print("Notion page is found. Analyzing clippings file...")
+        # Open the clippings text file and load it into all_clippings
+        all_clippings = read_raw_clippings_streamlit(clippings_data)
+        process_kindle_clippings(
+            notion_api_auth_token,
+            notion_database_id,
+            all_clippings,
+            enable_highlight_date,
+            enable_book_cover,
+        )
+    else:
+        print(
+            "Notion page not found! Please check whether the Notion database ID is assigned properly."
+        )
+
+
+def update_kindle_clippings(
+    notion_api_auth_token,
+    notion_database_id,
+    clippings_file,
+    enable_highlight_date,
+    enable_book_cover,
+):
+    notion = notional.connect(auth=notion_api_auth_token)
+    db = notion.databases.retrieve(notion_database_id)
+    if db:
+        print("Notion page is found. Analyzing clippings file...")
+        # Open the clippings text file and load it into all_clippings
+        all_clippings = read_raw_clippings(clippings_file)
+        process_kindle_clippings(
+            notion_api_auth_token,
+            notion_database_id,
+            all_clippings,
+            enable_highlight_date,
+            enable_book_cover,
+        )
+    else:
+        print(
+            "Notion page not found! Please check whether the Notion database ID is assigned properly."
+        )
 
 
 @click.command()
@@ -29,35 +103,13 @@ def main(
     enable_highlight_date,
     enable_book_cover,
 ):
-    notion = notional.connect(auth=notion_api_auth_token)
-    db = notion.databases.retrieve(notion_database_id)
-
-    if db:
-        print("Notion page is found. Analyzing clippings file...")
-
-        # Open the clippings text file and load it into all_clippings
-        all_clippings = read_raw_clippings(clippings_file)
-
-        # Parse all_clippings file and format the content to be sent tp the Notion DB into all_books
-        all_books = parse_raw_clippings_text(all_clippings)
-
-        # Export all the contents in all_books into the Notion DB.
-        export_to_notion(
-            all_books,
-            enable_highlight_date,
-            enable_book_cover,
-            notion_api_auth_token,
-            notion_database_id,
-        )
-
-        with open("my_kindle_clippings.json", "w") as out_file:
-            json.dump(all_books, out_file, indent=4)
-
-        print("Transfer complete... Exiting script...")
-    else:
-        print(
-            "Notion page not found! Please check whether the Notion database ID is assigned properly."
-        )
+    update_kindle_clippings(
+        notion_api_auth_token,
+        notion_database_id,
+        clippings_file,
+        enable_highlight_date,
+        enable_book_cover,
+    )
 
 
 if __name__ == "__main__":

kindle2notion/exporting.py

@@ -16,11 +16,11 @@
 
 
 def export_to_notion(
-    all_books: Dict,
-    enable_highlight_date: bool,
-    enable_book_cover: bool,
-    notion_api_auth_token: str,
-    notion_database_id: str,
+        all_books: Dict,
+        enable_highlight_date: bool,
+        enable_book_cover: bool,
+        notion_api_auth_token: str,
+        notion_database_id: str,
 ) -> None:
     print("Initiating transfer...\n")
 
@@ -48,7 +48,7 @@ def export_to_notion(
 
 
 def _prepare_aggregated_text_for_one_book(
-    clippings: List, enable_highlight_date: bool
+        clippings: List, enable_highlight_date: bool
 ) -> Tuple[str, str]:
     # TODO: Special case for books with len(clippings) >= 100 characters. Character limit in a Paragraph block in Notion is 100
     formatted_clippings = []
@@ -77,17 +77,17 @@ def _prepare_aggregated_text_for_one_book(
 
 
 def _add_book_to_notion(
-    title: str,
-    author: str,
-    clippings_count: int,
-    formatted_clippings: list,
-    last_date: str,
-    notion_api_auth_token: str,
-    notion_database_id: str,
-    enable_book_cover: bool,
+        title: str,
+        author: str,
+        clippings_count: int,
+        formatted_clippings: list,
+        last_date_string: str,
+        notion_api_auth_token: str,
+        notion_database_id: str,
+        enable_book_cover: bool,
 ):
     notion = notional.connect(auth=notion_api_auth_token)
-    last_date = datetime.strptime(last_date, "%A, %d %B %Y %I:%M:%S %p")
+    last_date = __get_last_date_from_string(last_date_string)
 
     # Condition variables
     title_exists = False
@@ -131,7 +131,19 @@ def _add_book_to_notion(
         )
         # page_content = _update_book_with_clippings(formatted_clippings)
         page_content = Paragraph["".join(formatted_clippings)]
-        notion.blocks.children.append(new_page, page_content)
+        page_content_text_length: int = len(page_content.paragraph.rich_text)
+        MAX_LENGTH = 100
+        # Handles notion limitation
+        if page_content_text_length > MAX_LENGTH:
+            original_page_content = page_content
+            num_of_loops = page_content_text_length // MAX_LENGTH
+            for loop_num in range(1, num_of_loops+1):
+                page_content = Paragraph[original_page_content.paragraph.rich_text[
+                    (loop_num-1)*MAX_LENGTH:loop_num*MAX_LENGTH]
+                ]
+                notion.blocks.children.append(new_page, page_content)
+        else:
+             notion.blocks.children.append(new_page, page_content)
         block_id = new_page.id
         if enable_book_cover:
             # Fetch a book cover from Google Books if the cover for the page is not set
@@ -158,7 +170,7 @@ def _add_book_to_notion(
         page_content = Paragraph["".join(formatted_clippings)]
         notion.blocks.children.append(page, page_content)
         # TODO: Delete existing page children (or figure out how to find changes to be made by comparing it with local json file.)
-        current_clippings_count = int(str(page["Highlights"]))
+        current_clippings_count = int(float(str(page["Highlights"])))
         page["Highlights"] = Number[clippings_count]
         page["Last Highlighted"] = Date[last_date.isoformat()]
         page["Last Synced"] = Date[datetime.now().isoformat()]
@@ -174,6 +186,15 @@ def _add_book_to_notion(
     return message
 
 
+def __get_last_date_from_string(last_date_string: str) -> datetime:
+    if not last_date_string:
+        return datetime.now()
+    try:
+        return datetime.strptime(last_date_string, "%A, %d %B %Y %I:%M:%S %p")
+    except ValueError:
+        # Datetime format is not English, retrying with non AM-PM format
+        return datetime.strptime(last_date_string, "%A, %d %B %Y %H:%M:%S")
+
 # def _create_rich_text_object(text):
 #     if "Note: " in text:
 #         # Bold text

kindle2notion/languages/enums.py

@@ -0,0 +1,38 @@
+from enum import Enum
+
+
+class Locale(Enum):
+    # Enum containing languages
+    ENGLISH = "en"
+    SPANISH = "es"
+
+    def __str__(self):
+        return self.value
+
+
+class Word(Enum):
+    # For each word, we have to handle different languages
+    NOTE = {
+        Locale.ENGLISH: "note",
+        Locale.SPANISH: "nota"
+    }
+    LOCATION = {
+        Locale.ENGLISH: "location",
+        Locale.SPANISH: "posición",
+    }
+    PAGE = {
+        Locale.ENGLISH: "page",
+        Locale.SPANISH: "página",
+    }
+    DATE_ADDED = {
+        Locale.ENGLISH: "added on",
+        Locale.SPANISH: "añadido el",
+    }
+    # Date formats also depend on language
+    DATE_FORMAT = {
+        Locale.ENGLISH: "%A, %d %B %Y %I:%M:%S %p",
+        Locale.SPANISH: "%A, %d %B %Y %H:%M:%S",
+    }
+
+    def __str__(self, language=Locale.ENGLISH):
+        return self.value[language]

kindle2notion/languages/word_detector.py

@@ -0,0 +1,24 @@
+from typing import List
+
+from kindle2notion.languages.enums import Word, Locale
+
+
+class WordDetector:
+
+    def __init__(self, languages: List[Locale]):
+        self.languages = languages
+        self.language_words = {lang: set() for lang in languages}
+
+        for word in Word:
+            for lang in word.value:
+                self.language_words[lang].add(word.value[lang])
+
+    def detect(self, text):
+        scores = {lang: 0 for lang in self.languages}
+        for lang, words in self.language_words.items():
+            scores[lang] = sum([len(word) for word in words if self.has_word(text, word)])
+        return max(scores, key=scores.get)
+
+    def has_word(self, text, word):
+        return word.lower() in text.lower()
+