From 02dd95d005be7fb93daf8161f6cfc7f65093f029 Mon Sep 17 00:00:00 2001
From: Jan Willhaus <mail@janwillhaus.de>
Date: Sun, 22 Sep 2024 11:07:22 +0200
Subject: [PATCH] feat: Add support for file url scheme (#183)

Closes #179
---
 README.md                  |  6 ++++++
 podcast_archiver/models.py | 10 +++++++---
 tests/conftest.py          |  5 +++++
 tests/test_fetch.py        | 22 ++++++++++++++++++++++
 4 files changed, 40 insertions(+), 3 deletions(-)
 create mode 100644 tests/test_fetch.py

diff --git a/README.md b/README.md
index f905db7..adeab2e 100644
--- a/README.md
+++ b/README.md
@@ -66,6 +66,12 @@ podcast-archiver -d ~/Music/Podcasts \
 
 This way, you can easily add and remove feeds to the list and let the archiver fetch the newest episodes for example by adding it to your crontab.
 
+Feeds can also be "fetched" from a local file:
+
+```bash
+podcast-archiver -f file:/Users/janw/downloaded_feed.xml
+```
+
 ### Changing the filename format
 
 Podcast Archiver has a `--filename-template` option that allows you to change the particular naming scheme of the archive. The default value for `--filename-template`. is shown in `podcast-archiver --help`, as well as all the available variables. The basic ones are:
diff --git a/podcast_archiver/models.py b/podcast_archiver/models.py
index cd5c2d0..919f14b 100644
--- a/podcast_archiver/models.py
+++ b/podcast_archiver/models.py
@@ -163,9 +163,13 @@ class FeedPage(BaseModel):
 
     @classmethod
     def from_url(cls, url: str) -> FeedPage:
-        response = session.get(url, allow_redirects=True, timeout=REQUESTS_TIMEOUT)
-        response.raise_for_status()
-        feedobj = feedparser.parse(response.content)
+        parsed = urlparse(url)
+        if parsed.scheme == "file":
+            feedobj = feedparser.parse(parsed.path)
+        else:
+            response = session.get(url, allow_redirects=True, timeout=REQUESTS_TIMEOUT)
+            response.raise_for_status()
+            feedobj = feedparser.parse(response.content)
         return cls.model_validate(feedobj)
 
 
diff --git a/tests/conftest.py b/tests/conftest.py
index e3f6cb0..e14570a 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -33,6 +33,11 @@ def feed_lautsprecher(responses: RequestsMock) -> str:
     return FEED_URL
 
 
+@pytest.fixture
+def feed_lautsprecher_file() -> str:
+    return f'file:{FIXTURES_DIR/ "feed_lautsprecher.xml"}'
+
+
 @pytest.fixture
 def feed_lautsprecher_notconsumed(responses: RequestsMock) -> str:
     return FEED_URL
diff --git a/tests/test_fetch.py b/tests/test_fetch.py
new file mode 100644
index 0000000..7ff6540
--- /dev/null
+++ b/tests/test_fetch.py
@@ -0,0 +1,22 @@
+from pathlib import Path
+
+import pytest
+
+from podcast_archiver.models import Feed
+
+FILE_FIXTURE = Path(__file__).parent / "fixtures" / "feed_lautsprecher.xml"
+
+
+def test_fetch_from_http(feed_lautsprecher_onlyfeed: str) -> None:
+    assert Feed.from_url(feed_lautsprecher_onlyfeed)
+
+
+@pytest.mark.parametrize(
+    "url",
+    [
+        f"file:{FILE_FIXTURE}",
+        f"file://{FILE_FIXTURE}",
+    ],
+)
+def test_fetch_from_file(url: str) -> None:
+    assert Feed.from_url(url)