Merge branch 'main' into youtubedlp-rewrite

README.md

@@ -277,9 +277,9 @@ pytest -ra -v # or poetry run pytest -ra -v
 
 #### Docker development
 working with docker locally:
-  * `docker build . -t auto-archiver` to build a local image
+  * `docker compose up` to build the first time and run a local image with the settings in `secrets/orchestration.yaml`
-  * `docker run --rm -v $PWD/secrets:/app/secrets auto-archiver  --config secrets/orchestration.yaml`
+  * To modify/pass additional command line args, use `docker compose run auto-archiver --config secrets/orchestration.yaml [OTHER ARGUMENTS]`
-    * to use local archive, also create a volume `-v` for it by adding `-v $PWD/local_archive:/app/local_archive`
+  * To rebuild after code changes, just pass the `--build` flag, e.g. `docker compose up --build`
 
 
 manual release to docker hub

docker-compose.yaml

@@ -0,0 +1,16 @@
+version: '3.8'
+
+services:
+  auto-archiver:
+  # point to the local dockerfile
+    build:
+      context: .
+      dockerfile: Dockerfile
+    container_name: auto-archiver
+    volumes:
+      - ./secrets:/app/secrets
+      - ./local_archive:/app/local_archive
+    environment:
+      - WACZ_ENABLE_DOCKER=true
+      - RUNNING_IN_DOCKER=true
+    command: --config secrets/orchestration.yaml

pyproject.toml

@@ -23,9 +23,7 @@ classifiers = [
 
 dependencies = [
     "gspread (>=0.0.0)",
-    "argparse (>=0.0.0)",
     "beautifulsoup4 (>=0.0.0)",
-    "tiktok-downloader (>=0.0.0)",
     "bs4 (>=0.0.0)",
     "loguru (>=0.0.0)",
     "ffmpeg-python (>=0.0.0)",
@@ -55,12 +53,10 @@ dependencies = [
     "warcio (>=0.0.0)",
     "jsonlines (>=0.0.0)",
     "pysubs2 (>=0.0.0)",
-    "minify-html (>=0.0.0)",
     "retrying (>=0.0.0)",
     "tsp-client (>=0.0.0)",
     "certvalidator (>=0.0.0)",
-    "toml (>=0.10.2,<0.11.0)",
+    "filetype (>=1.2.0,<2.0.0)",
-    "filetype (>=1.2.0,<2.0.0)"
 ]
 
 [tool.poetry.group.dev.dependencies]

src/auto_archiver/archivers/tiktok_archiver.py

@@ -1,5 +1,4 @@
 import json, os, traceback
-import tiktok_downloader
 from loguru import logger
 
 

src/auto_archiver/core/metadata.py

@@ -21,7 +21,7 @@ class Metadata:
     media: List[Media] = field(default_factory=list)
 
     def __post_init__(self):
-        self.set("_processed_at", datetime.datetime.utcnow())
+        self.set("_processed_at", datetime.datetime.now(datetime.timezone.utc))
 
     def merge(self: Metadata, right: Metadata, overwrite_left=True) -> Metadata:
         """

src/auto_archiver/databases/gsheet_db.py

@@ -65,7 +65,7 @@ class GsheetsDb(Database):
         media: Media = item.get_final_media()
         if hasattr(media, "urls"):
             batch_if_valid('archive', "\n".join(media.urls))
-        batch_if_valid('date', True, datetime.datetime.utcnow().replace(tzinfo=datetime.timezone.utc).isoformat())
+        batch_if_valid('date', True, datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=datetime.timezone.utc).isoformat())
         batch_if_valid('title', item.get_title())
         batch_if_valid('text', item.get("content", ""))
         batch_if_valid('timestamp', item.get_timestamp())

src/auto_archiver/enrichers/meta_enricher.py

@@ -55,5 +55,5 @@ class MetaEnricher(Enricher):
     def enrich_archive_duration(self, to_enrich):
         logger.debug(f"calculating archive duration for url={to_enrich.get_url()} ")
 
-        archive_duration = datetime.datetime.utcnow() - to_enrich.get("_processed_at")
+        archive_duration = datetime.datetime.now(datetime.timezone.utc) - to_enrich.get("_processed_at")
         to_enrich.set("archive_duration_seconds", archive_duration.seconds)

src/auto_archiver/formatters/html_formatter.py

@@ -4,7 +4,7 @@ import mimetypes, os, pathlib
 from jinja2 import Environment, FileSystemLoader
 from urllib.parse import quote
 from loguru import logger
-import minify_html, json
+import json
 import base64
 
 from ..version import __version__
@@ -47,7 +47,6 @@ class HtmlFormatter(Formatter):
             metadata=item.metadata,
             version=__version__
         )
-        content = minify_html.minify(content, minify_js=False, minify_css=True)
 
         html_path = os.path.join(ArchivingContext.get_tmp_dir(), f"formatted{random_str(24)}.html")
         with open(html_path, mode="w", encoding="utf-8") as outf:

tests/archivers/test_tiktok_archiver.py

@@ -0,0 +1,17 @@
+import pytest
+
+from .test_archiver_base import TestArchiverBase
+from auto_archiver.archivers.tiktok_archiver import TiktokArchiver
+
+class TestBlueskyArchiver(TestArchiverBase):
+
+    archiver_class = TiktokArchiver
+    config = {}
+
+    @pytest.mark.xfail(reason="Tiktok API is not working")
+    @pytest.mark.download
+    def test_download_video(self, make_item):
+        # cat video
+        url = "https://www.tiktok.com/@funnycats0ftiktok/video/7345101300750748970?lang=en"
+        item = self.archiver.download(make_item(url))
+        assert item.success