thiswillbeyourgithub · thiswillbeyourgithub · Jun 3, 2025 · Jun 3, 2025 · Jun 3, 2025 · Jun 3, 2025
diff --git a/README.md b/README.md
@@ -211,13 +211,14 @@ Community Scripts are a bunch of scripts made to solve specific issues. They are
 
 They can be found in the [./community_scripts](https://github.com/thiswillbeyourgithub/karakeep_python_api/tree/main/community_scripts) folder. Don't hesitate to submit yours!
 
-| Community Script | Description | Documentation |
-|----------------|-------------|---------------|
+| Community Script | Description                                                                                                                                                                            | Documentation |
+|----------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------|
 | **Karakeep-Time-Tagger** | Automatically adds time-to-read tags (`0-5m`, `5-10m`, etc.) to bookmarks based on content length analysis. Includes systemd service and timer files for automated periodic execution. | [`Link`](https://github.com/thiswillbeyourgithub/karakeep_python_api/tree/main/community_scripts/karakeep-time-tagger) |
-| **Karakeep-List-To-Tag** | Converts a Karakeep list into tags by adding a specified tag to all bookmarks within that list. | [`Link`](https://github.com/thiswillbeyourgithub/karakeep_python_api/tree/main/community_scripts/karakeep-list-to-tag) |
-| **Omnivore2Karakeep-Highlights** | Imports highlights from Omnivore export data to Karakeep, with intelligent position detection and bookmark matching. Supports dry-run mode for testing. | [`Link`](https://github.com/thiswillbeyourgithub/karakeep_python_api/tree/main/community_scripts/omnivore2karakeep-highlights) |
-| **Omnivore2Karakeep-Archived** | (Should not be needed anymore) Fixes the archived status of bookmarks imported from Omnivore by reading export data and updating Karakeep accordingly. | [`Link`](https://github.com/thiswillbeyourgithub/karakeep_python_api/tree/main/community_scripts/omnivore2karakeep-archived) |
-| **pocket2karakeep-archived** | (Should not be needed anymore) Fixes the archived status of bookmarks imported from Pocket by reading export data and updating Karakeep accordingly. | [`Link`](https://github.com/thiswillbeyourgithub/karakeep_python_api/tree/main/community_scripts/pocket2karakeep-archived) |
+| **Karakeep-List-To-Tag** | Converts a Karakeep list into tags by adding a specified tag to all bookmarks within that list.                                                                                        | [`Link`](https://github.com/thiswillbeyourgithub/karakeep_python_api/tree/main/community_scripts/karakeep-list-to-tag) |
+| **Omnivore2Karakeep-Highlights** | Imports highlights from Omnivore export data to Karakeep, with intelligent position detection and bookmark matching. Supports dry-run mode for testing.                                | [`Link`](https://github.com/thiswillbeyourgithub/karakeep_python_api/tree/main/community_scripts/omnivore2karakeep-highlights) |
+| **Omnivore2Karakeep-Archived** | (Should not be needed anymore) Fixes the archived status of bookmarks imported from Omnivore by reading export data and updating Karakeep accordingly.                                 | [`Link`](https://github.com/thiswillbeyourgithub/karakeep_python_api/tree/main/community_scripts/omnivore2karakeep-archived) |
+| **pocket2karakeep-archived** | (Should not be needed anymore) Fixes the archived status of bookmarks imported from Pocket by reading export data and updating Karakeep accordingly.                                   | [`Link`](https://github.com/thiswillbeyourgithub/karakeep_python_api/tree/main/community_scripts/pocket2karakeep-archived) |
+| **karakeep-archive-before-date** | Allow you to archive all not archived post before a given date                                                                                                                         | [`Link`](https://github.com/thiswillbeyourgithub/karakeep_python_api/tree/main/community_scripts/karakeep-archive-before-date) |
 
 ## Development
 

diff --git a/community_scripts/karakeep-archive-before-date/README.md b/community_scripts/karakeep-archive-before-date/README.md
@@ -0,0 +1,22 @@
+# Karakeep Archive before date
+
+Small cleaning script to clean old article not archived after an import from another readlater app.
+
+## Prerequisites
+
+N/A 
+
+## Usage
+
+Define a date to limit archiving. All not archived bookmarks before this date will be archived. 
+
+```bash
+python archiving_before_date.py --before-date 2023-12-24
+```
+
+`--before-date` format is `YYYY-MM-DD`
+
+You might need to set up environment variables for the Karakeep API client or pass them as arguments if the script supports it (e.g., `KARAKEEP_PYTHON_API_BASE_URL` and `KARAKEEP_PYTHON_API_KEY`). Refer to the script's help or the `karakeep-python-api` documentation for more details on authentication.
+
+
+
diff --git a/community_scripts/karakeep-archive-before-date/archiving_before_date.py b/community_scripts/karakeep-archive-before-date/archiving_before_date.py
@@ -0,0 +1,93 @@
+"""
+Small script to clean old article not archived after an import from another readlater app.
+
+Parameters:
+    before_date: Date in YYYY-MM-DD format. Articles created before this date will be archived.
+"""
+import time
+from datetime import datetime
+
+from Levenshtein import ratio
+import pickle
+from fire import Fire
+from typing import Optional
+from pathlib import Path
+import json
+import csv
+from karakeep_python_api import KarakeepAPI
+from tqdm import tqdm
+
+VERSION: str = "1.0.0"
+
+karakeep = KarakeepAPI(verbose=False)
+
+
+def main(before_date: str) -> None:
+    """Archive articles created before the specified date.
+
+    Args:
+        before_date: Date string in YYYY-MM-DD format
+    """
+    before_date = datetime.strptime(before_date, "%Y-%m-%d")
+
+    n = karakeep.get_current_user_stats()["numBookmarks"]
+    pbar = tqdm(total=n, desc="Fetching bookmarks")
+    all_bm = []
+    batch_size = 100  # if you set it too high, you can crash the karakeep instance, 100 being the maximum allowed
+    page = karakeep.get_all_bookmarks(
+        include_content=False,
+        limit=batch_size,
+    )
+    all_bm.extend(page.bookmarks)
+    pbar.update(len(all_bm))
+    while page.nextCursor:
+        page = karakeep.get_all_bookmarks(
+            include_content=False,
+            limit=batch_size,
+            cursor=page.nextCursor,
+        )
+        all_bm.extend(page.bookmarks)
+        pbar.update(len(page.bookmarks))
+
+    assert (
+        len(all_bm) == n
+    ), f"Only retrieved {len(all_bm)} bookmarks instead of {n}"
+    pbar.close()
+
+    failed = []
+    for bookmark in all_bm:
+
+        # skip already archived
+        if bookmark.archived:
+            continue
+
+
+        #tqdm.write(f"Creation Date: {bookmark.createdAt}")
+        creation_date = datetime.strptime(bookmark.createdAt, "%Y-%m-%dT%H:%M:%S.%fZ")
+
+        if creation_date > before_date:
+            continue
+
+        # do the archiving
+        retries = 3
+        for attempt in range(retries):
+            try:
+                res_arch = karakeep.update_a_bookmark(
+                    bookmark_id=bookmark.id,
+                    update_data={"archived": True},
+                )
+                break
+            except Exception as e:
+                if attempt == retries - 1:
+                    raise e
+                tqdm.write(f"Update failed, retrying ({attempt + 1}/{retries})")
+                time.sleep(1)
+        if isinstance(res_arch, dict):
+            assert res_arch["archived"], res_arch
+        else:
+            assert res_arch.archived, res_arch
+        tqdm.write(f"Successfuly archived: {bookmark.title}")
+
+
+if __name__ == "__main__":
+    Fire(main)
diff --git a/community_scripts/pocket2karakeep-archived/pocket_archiving_status_updater.py b/community_scripts/pocket2karakeep-archived/pocket_archiving_status_updater.py
@@ -7,7 +7,6 @@
 It identifies entries with status "archive" and updates their status in Karakeep.
 
 """
-
 import time
 
 from Levenshtein import ratio
@@ -20,6 +19,8 @@
 from karakeep_python_api import KarakeepAPI
 from tqdm import tqdm
 
+VERSION: str = "1.1.0"
+
 karakeep = KarakeepAPI(verbose=False)
 
 
@@ -137,7 +138,9 @@ def main(
             elif hasattr(content, "sourceUrl"):
                 found_url = content.sourceUrl
             else:
-                breakpoint()
+                found_url = ""
+
+
 
             if found_url == url:
                 found_it = True
@@ -175,7 +178,7 @@ def main(
                 r = ratio(pocket["title"].lower(), content.title.lower())
                 if r >= threshold:
                     found_it = True
-                    breakpoint()
+                    #breakpoint()
                     break
 
             if (
@@ -189,11 +192,12 @@ def main(
                     found_it = True
                     break
 
+
         # couldn't be found
         if not found_it:
             failed.append(pocket)
             tqdm.write(f"Failed to find {url}")
-            breakpoint()
+            #breakpoint()
             with open("./omnivore_archiver_failed.txt", "a") as f:
                 f.write(f"\n{pocket}")
             continue
@@ -202,15 +206,21 @@ def main(
         if bookmark.archived:
             tqdm.write(f"Already archived: {url}")
             continue
-        fresh = karakeep.get_a_single_bookmark(
-            bookmark_id=bookmark.id, include_content=False
-        )
+        for attempt in range(5):
+            try:
+                fresh = karakeep.get_a_single_bookmark(bookmark_id=bookmark.id, include_content=False)
+                break
+            except Exception as e:
+                if attempt == 4:
+                    raise e
+                tqdm.write(f"Get single bookmark failed, retrying ({attempt + 1}/5)")
+                time.sleep(1)
         if fresh.archived:
             tqdm.write(f"Already archived: {url}")
             continue
 
         # do the archiving
-        retries = 3
+        retries = 10
         for attempt in range(retries):
             try:
                 res_arch = karakeep.update_a_bookmark(