Merge pull request #225 from bellingcat/small_issues

## GSheets Columns updates - Update the available columns in the Google Sheet Feeder and Database. - Update the Sheet Template to reflect this. ## Other Fixes - Ensure test file cleanup. - Additional tests. - Correctly mark download test. - Small typos.
2025-03-03 13:06:27 +00:00 · 2025-03-03 13:06:27 +00:00 · 011ded2bde
commit 011ded2bde
--- a/poetry.lock
+++ b/poetry.lock
@ -103,14 +103,14 @@ tests-mypy = ["mypy (>=1.11.1)", "pytest-mypy-plugins"]

 [[package]]
 name = "authlib"
-version = "1.4.1"
+version = "1.5.0"
 description = "The ultimate Python library in building OAuth and OpenID Connect servers and clients."
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "Authlib-1.4.1-py2.py3-none-any.whl", hash = "sha256:edc29c3f6a3e72cd9e9f45fff67fc663a2c364022eb0371c003f22d5405915c1"},
-    {file = "authlib-1.4.1.tar.gz", hash = "sha256:30ead9ea4993cdbab821dc6e01e818362f92da290c04c7f6a1940f86507a790d"},
+    {file = "Authlib-1.5.0-py2.py3-none-any.whl", hash = "sha256:b3cc5ccfc19cf87678046b6e7cb19d402d8a631a33c40e36385232203227953a"},
+    {file = "authlib-1.5.0.tar.gz", hash = "sha256:8fd8bd8f806485a532ac39a17b579982cf54688f956174f995cc938a91725423"},
 ]

 [package.dependencies]
@ -172,18 +172,18 @@ lxml = ["lxml"]

 [[package]]
 name = "boto3"
-version = "1.36.22"
+version = "1.37.0"
 description = "The AWS SDK for Python"
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "boto3-1.36.22-py3-none-any.whl", hash = "sha256:39957eabdce009353d72d131046489fbbfa15891865d5f069f1e8bfa414e6b81"},
-    {file = "boto3-1.36.22.tar.gz", hash = "sha256:768c8a4d4a6227fe2258105efa086f1424cba5ca915a5eb2305b2cd979306ad1"},
+    {file = "boto3-1.37.0-py3-none-any.whl", hash = "sha256:03bd8c93b226f07d944fd6b022e11a307bff94ab6a21d51675d7e3ea81ee8424"},
+    {file = "boto3-1.37.0.tar.gz", hash = "sha256:01015b38017876d79efd7273f35d9a4adfba505237159621365bed21b9b65eca"},
 ]

 [package.dependencies]
-botocore = ">=1.36.22,<1.37.0"
+botocore = ">=1.37.0,<1.38.0"
 jmespath = ">=0.7.1,<2.0.0"
 s3transfer = ">=0.11.0,<0.12.0"

@ -192,14 +192,14 @@ crt = ["botocore[crt] (>=1.21.0,<2.0a0)"]

 [[package]]
 name = "botocore"
-version = "1.36.22"
+version = "1.37.0"
 description = "Low-level, data-driven core of boto 3."
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "botocore-1.36.22-py3-none-any.whl", hash = "sha256:75d6b34acb0686ee4d54ff6eb285e78ccfe318407428769d1e3e13351714d890"},
-    {file = "botocore-1.36.22.tar.gz", hash = "sha256:59520247d5a479731724f97c995d5a1c2aae3b303b324f39d99efcfad1d3019e"},
+    {file = "botocore-1.37.0-py3-none-any.whl", hash = "sha256:d01661f38c0edac87424344cdf4169f3ab9bc1bf1b677c8b230d025eb66c54a3"},
+    {file = "botocore-1.37.0.tar.gz", hash = "sha256:b129d091a8360b4152ab65327186bf4e250de827c4a9b7ddf40a72b1acf1f3c1"},
 ]

 [package.dependencies]
@ -363,14 +363,14 @@ beautifulsoup4 = "*"

 [[package]]
 name = "cachetools"
-version = "5.5.1"
+version = "5.5.2"
 description = "Extensible memoizing collections and decorators"
 optional = false
 python-versions = ">=3.7"
 groups = ["main"]
 files = [
-    {file = "cachetools-5.5.1-py3-none-any.whl", hash = "sha256:b76651fdc3b24ead3c648bbdeeb940c1b04d365b38b4af66788f9ec4a81d42bb"},
-    {file = "cachetools-5.5.1.tar.gz", hash = "sha256:70f238fbba50383ef62e55c6aff6d9673175fe59f7c6782c7a0b9e38f4a9df95"},
+    {file = "cachetools-5.5.2-py3-none-any.whl", hash = "sha256:d26a22bcc62eb95c3beabd9f1ee5e820d3d2704fe2967cbe350e20c8ffcd3f0a"},
+    {file = "cachetools-5.5.2.tar.gz", hash = "sha256:1a661caa9175d26759571b2e19580f9d6393969e5dfca11fdb1f947a23e640d4"},
 ]

 [[package]]
@ -860,14 +860,14 @@ tool = ["click (>=6.0.0)"]

 [[package]]
 name = "googleapis-common-protos"
-version = "1.67.0"
+version = "1.68.0"
 description = "Common protobufs used in Google APIs"
 optional = false
 python-versions = ">=3.7"
 groups = ["main"]
 files = [
-    {file = "googleapis_common_protos-1.67.0-py2.py3-none-any.whl", hash = "sha256:579de760800d13616f51cf8be00c876f00a9f146d3e6510e19d1f4111758b741"},
-    {file = "googleapis_common_protos-1.67.0.tar.gz", hash = "sha256:21398025365f138be356d5923e9168737d94d46a72aefee4a6110a1f23463c86"},
+    {file = "googleapis_common_protos-1.68.0-py2.py3-none-any.whl", hash = "sha256:aaf179b2f81df26dfadac95def3b16a95064c76a5f45f07e4c68a21bb371c4ac"},
+    {file = "googleapis_common_protos-1.68.0.tar.gz", hash = "sha256:95d38161f4f9af0d9423eed8fb7b64ffd2568c3464eb542ff02c5bfa1953ab3c"},
 ]

 [package.dependencies]
@ -1674,14 +1674,14 @@ files = [

 [[package]]
 name = "pydata-sphinx-theme"
-version = "0.16.1"
+version = "0.15.4"
 description = "Bootstrap-based Sphinx theme from the PyData community"
 optional = false
 python-versions = ">=3.9"
 groups = ["docs"]
 files = [
-    {file = "pydata_sphinx_theme-0.16.1-py3-none-any.whl", hash = "sha256:225331e8ac4b32682c18fcac5a57a6f717c4e632cea5dd0e247b55155faeccde"},
-    {file = "pydata_sphinx_theme-0.16.1.tar.gz", hash = "sha256:a08b7f0b7f70387219dc659bff0893a7554d5eb39b59d3b8ef37b8401b7642d7"},
+    {file = "pydata_sphinx_theme-0.15.4-py3-none-any.whl", hash = "sha256:2136ad0e9500d0949f96167e63f3e298620040aea8f9c74621959eda5d4cf8e6"},
+    {file = "pydata_sphinx_theme-0.15.4.tar.gz", hash = "sha256:7762ec0ac59df3acecf49fd2f889e1b4565dbce8b88b2e29ee06fdd90645a06d"},
 ]

 [package.dependencies]
@ -1689,8 +1689,9 @@ accessible-pygments = "*"
 Babel = "*"
 beautifulsoup4 = "*"
 docutils = "!=0.17.0"
+packaging = "*"
 pygments = ">=2.7"
-sphinx = ">=6.1"
+sphinx = ">=5"
 typing-extensions = "*"

 [package.extras]
@ -2265,14 +2266,14 @@ crt = ["botocore[crt] (>=1.36.0,<2.0a.0)"]

 [[package]]
 name = "selenium"
-version = "4.28.1"
+version = "4.29.0"
 description = "Official Python bindings for Selenium WebDriver"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "selenium-4.28.1-py3-none-any.whl", hash = "sha256:4238847e45e24e4472cfcf3554427512c7aab9443396435b1623ef406fff1cc1"},
-    {file = "selenium-4.28.1.tar.gz", hash = "sha256:0072d08670d7ec32db901bd0107695a330cecac9f196e3afb3fa8163026e022a"},
+    {file = "selenium-4.29.0-py3-none-any.whl", hash = "sha256:ce5d26f1ddc1111641113653af33694c13947dd36c2df09cdd33f554351d372e"},
+    {file = "selenium-4.29.0.tar.gz", hash = "sha256:3a62f7ec33e669364a6c0562a701deb69745b569c50d55f1a912bf8eb33358ba"},
 ]

 [package.dependencies]
@ -2425,19 +2426,19 @@ test = ["httpx", "pytest (>=6)"]

 [[package]]
 name = "sphinx-book-theme"
-version = "1.1.3"
+version = "1.1.4"
 description = "A clean book theme for scientific explanations and documentation with Sphinx"
 optional = false
 python-versions = ">=3.9"
 groups = ["docs"]
 files = [
-    {file = "sphinx_book_theme-1.1.3-py3-none-any.whl", hash = "sha256:a554a9a7ac3881979a87a2b10f633aa2a5706e72218a10f71be38b3c9e831ae9"},
-    {file = "sphinx_book_theme-1.1.3.tar.gz", hash = "sha256:1f25483b1846cb3d353a6bc61b3b45b031f4acf845665d7da90e01ae0aef5b4d"},
+    {file = "sphinx_book_theme-1.1.4-py3-none-any.whl", hash = "sha256:843b3f5c8684640f4a2d01abd298beb66452d1b2394cd9ef5be5ebd5640ea0e1"},
+    {file = "sphinx_book_theme-1.1.4.tar.gz", hash = "sha256:73efe28af871d0a89bd05856d300e61edce0d5b2fbb7984e84454be0fedfe9ed"},
 ]

 [package.dependencies]
-pydata-sphinx-theme = ">=0.15.2"
-sphinx = ">=5"
+pydata-sphinx-theme = "0.15.4"
+sphinx = ">=6.1"

 [package.extras]
 code-style = ["pre-commit"]
@ -2584,14 +2585,14 @@ test = ["pytest"]

 [[package]]
 name = "starlette"
-version = "0.45.3"
+version = "0.46.0"
 description = "The little ASGI library that shines."
 optional = false
 python-versions = ">=3.9"
 groups = ["docs"]
 files = [
-    {file = "starlette-0.45.3-py3-none-any.whl", hash = "sha256:dfb6d332576f136ec740296c7e8bb8c8a7125044e7c6da30744718880cdd059d"},
-    {file = "starlette-0.45.3.tar.gz", hash = "sha256:2cbcba2a75806f8a41c722141486f37c28e30a0921c5f6fe4346cb0dcee1302f"},
+    {file = "starlette-0.46.0-py3-none-any.whl", hash = "sha256:913f0798bd90ba90a9156383bcf1350a17d6259451d0d8ee27fc0cf2db609038"},
+    {file = "starlette-0.46.0.tar.gz", hash = "sha256:b359e4567456b28d473d0193f34c0de0ed49710d75ef183a74a5ce0499324f50"},
 ]

 [package.dependencies]
@ -2602,14 +2603,14 @@ full = ["httpx (>=0.27.0,<0.29.0)", "itsdangerous", "jinja2", "python-multipart

 [[package]]
 name = "telethon"
-version = "1.38.1"
+version = "1.39.0"
 description = "Full-featured Telegram client library for Python 3"
 optional = false
 python-versions = ">=3.5"
 groups = ["main"]
 files = [
-    {file = "Telethon-1.38.1-py3-none-any.whl", hash = "sha256:30c187017501bfb982b8af5659f864dda4108f77ea49cfce61e8f6fdb8a18d6e"},
-    {file = "Telethon-1.38.1.tar.gz", hash = "sha256:f9866c1e37197a0894e0c02aa56a6359bffb14a585e88e18e3e819df4fda399a"},
+    {file = "Telethon-1.39.0-py3-none-any.whl", hash = "sha256:aa9f394b94be144799a6f6a93ab463867bc7c63503ede9631751940a98f6c703"},
+    {file = "telethon-1.39.0.tar.gz", hash = "sha256:35d4795d8c91deac515fb0bcb3723866b924de1c724e1d5c230460e96f284a63"},
 ]

 [package.dependencies]
@ -2719,14 +2720,14 @@ sortedcontainers = "*"

 [[package]]
 name = "trio-websocket"
-version = "0.12.1"
+version = "0.12.2"
 description = "WebSocket library for Trio"
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "trio_websocket-0.12.1-py3-none-any.whl", hash = "sha256:608ec746bb287e5d5a66baf483e41194193c5cf05ffaad6240e7d1fcd80d1e6f"},
-    {file = "trio_websocket-0.12.1.tar.gz", hash = "sha256:d55ccd4d3eae27c494f3fdae14823317839bdcb8214d1173eacc4d42c69fc91b"},
+    {file = "trio_websocket-0.12.2-py3-none-any.whl", hash = "sha256:df605665f1db533f4a386c94525870851096a223adcb97f72a07e8b4beba45b6"},
+    {file = "trio_websocket-0.12.2.tar.gz", hash = "sha256:22c72c436f3d1e264d0910a3951934798dcc5b00ae56fc4ee079d46c7cf20fae"},
 ]

 [package.dependencies]
@ -3161,14 +3162,14 @@ h11 = ">=0.9.0,<1"

 [[package]]
 name = "yt-dlp"
-version = "2025.1.26"
+version = "2025.2.19"
 description = "A feature-rich command-line audio/video downloader"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "yt_dlp-2025.1.26-py3-none-any.whl", hash = "sha256:3e76bd896b9f96601021ca192ca0fbdd195e3c3dcc28302a3a34c9bc4979da7b"},
-    {file = "yt_dlp-2025.1.26.tar.gz", hash = "sha256:1c9738266921ad43c568ad01ac3362fb7c7af549276fbec92bd72f140da16240"},
+    {file = "yt_dlp-2025.2.19-py3-none-any.whl", hash = "sha256:3ed218eaeece55e9d715afd41abc450dc406ee63bf79355169dfde312d38fdb8"},
+    {file = "yt_dlp-2025.2.19.tar.gz", hash = "sha256:f33ca76df2e4db31880f2fe408d44f5058d9f135015b13e50610dfbe78245bea"},
 ]

 [package.extras]
--- a/src/auto_archiver/core/base_module.py
+++ b/src/auto_archiver/core/base_module.py
@ -50,7 +50,6 @@ class BaseModule(ABC):

    def config_setup(self, config: dict):

-        authentication = config.get('authentication', {})
        # this is important. Each instance is given its own deepcopied config, so modules cannot
        # change values to affect other modules
        config = deepcopy(config)
--- a/src/auto_archiver/core/consts.py
+++ b/src/auto_archiver/core/consts.py
@ -14,7 +14,7 @@ DEFAULT_MANIFEST = {
    'name': '', # the display name of the module
    'author': 'Bellingcat', # creator of the module, leave this as Bellingcat or set your own name!
    'type': [], # the type of the module, can be one or more of MODULE_TYPES
-    'requires_setup': True, # whether or not this module requires additional setup such as setting API Keys or installing additional softare
+    'requires_setup': True, # whether or not this module requires additional setup such as setting API Keys or installing additional software
    'description': '', # a description of the module
    'dependencies': {}, # external dependencies, e.g. python packages or binaries, in dictionary format
    'entry_point': '', # the entry point for the module, in the format 'module_name::ClassName'. This can be left blank to use the default entry point of module_name::ModuleName
--- a/src/auto_archiver/modules/generic_extractor/generic_extractor.py
+++ b/src/auto_archiver/modules/generic_extractor/generic_extractor.py
@ -86,7 +86,7 @@ class GenericExtractor(Extractor):
        # keep both 'title' and 'fulltitle', but prefer 'title', falling back to 'fulltitle' if it doesn't exist
        result.set_title(video_data.pop('title', video_data.pop('fulltitle', "")))
        result.set_url(url)
-
+        if "description" in video_data: result.set_content(video_data["description"])
        # extract comments if enabled
        if self.comments:
            result.set("comments", [{
--- a/src/auto_archiver/modules/gsheet_feeder/gsheet_feeder.py
+++ b/src/auto_archiver/modules/gsheet_feeder/gsheet_feeder.py
@ -64,7 +64,7 @@ class GsheetsFeeder(Feeder):
            yield m

    def _set_context(self, m: Metadata, gw: GWorksheet, row: int) -> Metadata:
-        # TODO: Check folder value not being recognised
+
        m.set_context("gsheet", {"row": row, "worksheet": gw})

        if gw.get_cell_or_default(row, 'folder', "") is None:
--- a/src/auto_archiver/modules/gsheet_feeder/gworksheet.py
+++ b/src/auto_archiver/modules/gsheet_feeder/gworksheet.py
@ -17,6 +17,7 @@ class GWorksheet:
        'thumbnail': 'thumbnail',
        'timestamp': 'upload timestamp',
        'title': 'upload title',
+        'text': 'text content',
        'screenshot': 'screenshot',
        'hash': 'hash',
        'pdq_hash': 'perceptual hashes',
--- a/src/auto_archiver/utils/misc.py
+++ b/src/auto_archiver/utils/misc.py
@ -1,9 +1,11 @@
-import os
+import hashlib
 import json
+import os
 import uuid
 from datetime import datetime, timezone
+from dateutil.parser import parse as parse_dt
+
 import requests
-import hashlib
 from loguru import logger


@ -68,26 +70,34 @@ def calculate_file_hash(filename: str, hash_algo = hashlib.sha256, chunksize: in
            hash.update(buf)
    return hash.hexdigest()

-def get_current_datetime_iso() -> str:
-    return datetime.now(timezone.utc).replace(tzinfo=timezone.utc).isoformat()

+def get_datetime_from_str(dt_str: str, fmt: str | None = None, dayfirst=True) -> datetime | None:
+    """ parse a datetime string with option of passing a specific format

-def get_datetime_from_str(dt_str: str, fmt: str | None = None) -> datetime | None:
-    # parse a datetime string with option of passing a specific format
+    Args:
+        dt_str: the datetime string to parse
+        fmt: the python date format of the datetime string, if None, dateutil.parser.parse is used
+        dayfirst: Use this to signify between date formats which put the day first, vs the month first:
+                    e.g. DD/MM/YYYY vs MM/DD/YYYY
+    """
    try:
-        return datetime.strptime(dt_str, fmt) if fmt else datetime.fromisoformat(dt_str)
+        return datetime.strptime(dt_str, fmt) if fmt else parse_dt(dt_str, dayfirst=dayfirst)
    except ValueError as e:
        logger.error(f"Unable to parse datestring {dt_str}: {e}")
        return None


-def get_timestamp(ts, utc=True, iso=True) -> str | datetime | None:
-    # Consistent parsing of timestamps
-    # If utc=True, the timezone is set to UTC,
-    # if iso=True, the output is an iso string
+def get_timestamp(ts, utc=True, iso=True, dayfirst=True) -> str | datetime | None:
+    """  Consistent parsing of timestamps.
+    Args:
+         If utc=True, the timezone is set to UTC,
+         if iso=True, the output is an iso string
+         Use dayfirst to signify between date formats which put the date vs month first:
+         e.g. DD/MM/YYYY vs MM/DD/YYYY
+     """
    if not ts: return
    try:
-        if isinstance(ts, str): ts = datetime.fromisoformat(ts)
+        if isinstance(ts, str): ts = parse_dt(ts, dayfirst=dayfirst)
        if isinstance(ts, (int, float)): ts = datetime.fromtimestamp(ts)
        if utc: ts = ts.replace(tzinfo=timezone.utc)
        if iso: return ts.isoformat()
@ -96,5 +106,6 @@ def get_timestamp(ts, utc=True, iso=True) -> str | datetime | None:
        logger.error(f"Unable to parse timestamp {ts}: {e}")
        return None

+
 def get_current_timestamp() -> str:
    return get_timestamp(datetime.now())
--- a/tests/databases/test_gsheet_db.py
+++ b/tests/databases/test_gsheet_db.py
@ -32,9 +32,8 @@ def mock_metadata(mocker):
@pytest.fixture
 def metadata():
    metadata = Metadata()
-    metadata.add_media(Media(filename="screenshot", urls=["http://example.com/screenshot.png"]))
-    metadata.add_media(Media(filename="browsertrix", urls=["http://example.com/browsertrix.wacz"]))
-    metadata.add_media(Media(filename="thumbnail", urls=["http://example.com/thumbnail.png"]))
+    metadata.add_media(Media(filename="screenshot.png", urls=["http://example.com/screenshot.png"]).set("id", "screenshot"))
+    metadata.add_media(Media(filename="browsertrix", urls=["http://example.com/browsertrix.wacz"]).set("id", "browsertrix"))
    metadata.set_url("http://example.com")
    metadata.set_title("Example Title")
    metadata.set_content("Example Content")
@ -53,7 +52,7 @@ def mock_media(mocker):
    return mock_media

@pytest.fixture
-def gsheets_db(mock_gworksheet, setup_module, mocker):
+def gsheets_db(mock_gworksheet, setup_module, mocker) -> GsheetsDb:
    db = setup_module("gsheet_db", {
        "allow_worksheets": "set()",
        "block_worksheets": "set()",
@ -80,10 +79,10 @@ def expected_calls(mock_media, fixed_timestamp):
        (1, 'text', 'Example Content'),
        (1, 'timestamp', '2025-01-01T00:00:00+00:00'),
        (1, 'hash', 'not-calculated'),
-        # (1, 'screenshot', 'http://example.com/screenshot.png'),
-        # (1, 'thumbnail', '=IMAGE("http://example.com/thumbnail.png")'),
-        # (1, 'wacz', 'http://example.com/browsertrix.wacz'),
-        # (1, 'replaywebpage', 'https://replayweb.page/?source=http%3A%2F%2Fexample.com%2Fbrowsertrix.wacz#view=pages&url=')
+        (1, 'screenshot', 'http://example.com/screenshot.png'),
+        (1, 'thumbnail', '=IMAGE("http://example.com/screenshot.png")'),
+        (1, 'wacz', 'http://example.com/browsertrix.wacz'),
+        (1, 'replaywebpage', 'https://replayweb.page/?source=http%3A//example.com/browsertrix.wacz#view=pages&url=http%3A//example.com')
    ]

 def test_retrieve_gsheet(gsheets_db, metadata, mock_gworksheet):
--- a/tests/enrichers/test_pdq_hash_enricher.py
+++ b/tests/enrichers/test_pdq_hash_enricher.py
@ -20,11 +20,9 @@ def metadata_with_images():


 def test_successful_enrich(metadata_with_images, mocker):
-    with (
-        mocker.patch("pdqhash.compute", return_value=([1, 0, 1, 0] * 64, 100)),
-        mocker.patch("PIL.Image.open"),
-        mocker.patch.object(Media, "is_image", return_value=True) as mock_is_image,
-    ):
+    mocker.patch("pdqhash.compute", return_value=([1, 0, 1, 0] * 64, 100))
+    mocker.patch("PIL.Image.open")
+    mocker.patch.object(Media, "is_image", return_value=True)
    enricher = PdqHashEnricher()
    enricher.enrich(metadata_with_images)

--- a/tests/enrichers/test_wayback_enricher.py
+++ b/tests/enrichers/test_wayback_enricher.py
@ -16,7 +16,7 @@ def mock_is_auth_wall(mocker):
 def mock_post_success(mocker):
    """Fixture to mock POST requests with a successful response."""
    def _mock_post(json_data: dict = None, status_code: int = 200):
-        json_data = json_data or {"job_id": "job123"}
+        json_data = {"job_id": "job123"} if json_data is None else json_data
        resp = mocker.Mock(status_code=status_code)
        resp.json.return_value = json_data
        return mocker.patch("requests.post", return_value=resp)
--- a/tests/extractors/test_vk_extractor.py
+++ b/tests/extractors/test_vk_extractor.py
@ -0,0 +1,76 @@
+import pytest
+
+from auto_archiver.core import Metadata
+from auto_archiver.modules.vk_extractor import VkExtractor
+
+
+@pytest.fixture
+def mock_vk_scraper(mocker):
+    """Fixture to mock VkScraper."""
+    return mocker.patch("auto_archiver.modules.vk_extractor.vk_extractor.VkScraper")
+
+@pytest.fixture
+def vk_extractor(setup_module, mock_vk_scraper) -> VkExtractor:
+    """Fixture to initialize VkExtractor with mocked VkScraper."""
+    extractor_module = "vk_extractor"
+    configs = {
+        "username": "name",
+        "password": "password123",
+        "session_file": "secrets/vk_config.v2.json",
+    }
+    vk = setup_module(extractor_module, configs)
+    vk.vks = mock_vk_scraper.return_value
+    return vk
+
+
+def test_netloc(vk_extractor, metadata):
+    # metadata url set as: "https://example.com/"
+    assert vk_extractor.download(metadata) is False
+
+
+def test_vk_url_but_scrape_returns_empty(vk_extractor, metadata):
+    metadata.set_url("https://vk.com/valid-wall")
+    vk_extractor.vks.scrape.return_value = []
+    assert vk_extractor.download(metadata) is False
+    assert metadata.netloc == "vk.com"
+    vk_extractor.vks.scrape.assert_called_once_with(metadata.get_url())
+
+
+def test_successful_scrape_and_download(vk_extractor, metadata, mocker):
+    mock_scrapes = [
+        {"text": "Post Title", "datetime": "2023-01-01T00:00:00", "id": 1},
+        {"text": "Another Post", "datetime": "2023-01-02T00:00:00", "id": 2}
+    ]
+    mock_filenames = ["image1.jpg", "image2.png"]
+    vk_extractor.vks.scrape.return_value = mock_scrapes
+    vk_extractor.vks.download_media.return_value = mock_filenames
+    metadata.set_url("https://vk.com/valid-wall")
+    result = vk_extractor.download(metadata)
+    # Test metadata
+    assert result.is_success()
+    assert result.status == "vk: success"
+    assert result.get_title() == "Post Title"
+    assert result.get_timestamp() == "2023-01-01T00:00:00+00:00"
+    assert "Another Post" in result.metadata["content"]
+    # Test Media objects
+    assert len(result.media) == 2
+    assert result.media[0].filename == "image1.jpg"
+    assert result.media[1].filename == "image2.png"
+    vk_extractor.vks.download_media.assert_called_once_with(
+        mock_scrapes, vk_extractor.tmp_dir
+    )
+
+
+def test_adds_first_title_and_timestamp(vk_extractor):
+    metadata = Metadata().set_url("https://vk.com/no-metadata")
+    metadata.set_url("https://vk.com/no-metadata")
+    mock_scrapes = [{"text": "value", "datetime": "2023-01-01T00:00:00"},
+                    {"text": "value2", "datetime": "2023-01-02T00:00:00"}]
+    vk_extractor.vks.scrape.return_value = mock_scrapes
+    vk_extractor.vks.download_media.return_value = []
+    result = vk_extractor.download(metadata)
+
+    assert result.get_title() == "value"
+    # formatted timestamp
+    assert result.get_timestamp() == "2023-01-01T00:00:00+00:00"
+    assert result.is_success()
--- a/tests/storages/test_local_storage.py
+++ b/tests/storages/test_local_storage.py
@ -9,11 +9,12 @@ from auto_archiver.modules.local_storage import LocalStorage


@pytest.fixture
-def local_storage(setup_module) -> LocalStorage:
+def local_storage(setup_module, tmp_path) -> LocalStorage:
+    save_to = tmp_path / "local_archive"
    configs: dict = {
        "path_generator": "flat",
        "filename_generator": "static",
-        "save_to": "./local_archive",
+        "save_to": str(save_to),
        "save_absolute": False,
    }
    return setup_module("local_storage", configs)