aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorArjun Satarkar <me@arjunsatarkar.net>2023-08-03 13:33:36 +0000
committerArjun Satarkar <me@arjunsatarkar.net>2023-08-03 13:33:36 +0000
commit0e120e5221478a3140e09de717ec8e0ff2d5178a (patch)
tree2c963a43dec1d9156165846c1621e767d225c872
parentc658002cad0c9b60b28dff8095a6682a43cd10d1 (diff)
downloadtagrss-0e120e5221478a3140e09de717ec8e0ff2d5178a.tar
tagrss-0e120e5221478a3140e09de717ec8e0ff2d5178a.tar.gz
tagrss-0e120e5221478a3140e09de717ec8e0ff2d5178a.zip
Simplify process to update feeds (i.e. fetch & store new entries)
-rwxr-xr-xserve.py25
-rw-r--r--tagrss.py17
2 files changed, 26 insertions, 16 deletions
diff --git a/serve.py b/serve.py
index 87a30bb..6f9dea3 100755
--- a/serve.py
+++ b/serve.py
@@ -72,17 +72,24 @@ def serialise_tags(tags: list[str]) -> str:
@bottle.get("/")
def index():
- per_page: int = min(MAX_PER_PAGE_ENTRIES, int(bottle.request.query.get("per_page", DEFAULT_PER_PAGE_ENTRIES))) # type: ignore
+ per_page: int = min(
+ MAX_PER_PAGE_ENTRIES,
+ int(bottle.request.query.get("per_page", DEFAULT_PER_PAGE_ENTRIES)), # type: ignore
+ )
page_num = int(bottle.request.query.get("page_num", 1)) # type: ignore
offset = (page_num - 1) * per_page
- included_feeds_str: typing.Optional[str] = bottle.request.query.get("included_feeds", None) # type: ignore
+ included_feeds_str: typing.Optional[str] = bottle.request.query.get( # type: ignore
+ "included_feeds", None
+ )
included_feeds: typing.Optional[list[int]] = None
if included_feeds_str:
try:
included_feeds = [int(feed_id) for feed_id in included_feeds_str.split(" ")]
except ValueError:
pass
- included_tags_str: typing.Optional[str] = bottle.request.query.get("included_tags", None) # type: ignore
+ included_tags_str: typing.Optional[str] = bottle.request.query.get( # type: ignore
+ "included_tags", None
+ )
included_tags: typing.Optional[list[str]] = None
if included_tags_str:
included_tags = parse_space_separated_tags(included_tags_str)
@@ -128,7 +135,10 @@ def index():
@bottle.get("/list_feeds")
def list_feeds():
- per_page: int = min(MAX_PER_PAGE_ENTRIES, int(bottle.request.query.get("per_page", DEFAULT_PER_PAGE_ENTRIES))) # type: ignore
+ per_page: int = min(
+ MAX_PER_PAGE_ENTRIES,
+ int(bottle.request.query.get("per_page", DEFAULT_PER_PAGE_ENTRIES)), # type: ignore
+ )
page_num = int(bottle.request.query.get("page_num", 1)) # type: ignore
offset = (page_num - 1) * per_page
total_pages: int = max(1, math.ceil(core.get_feed_count() / per_page))
@@ -252,13 +262,8 @@ def update_feeds(run_event: threading.Event):
for i in range(math.ceil(feed_count / limit)):
feeds = core.get_feeds(limit=limit, offset=limit * i)
for feed in feeds:
- parsed, epoch_downloaded = core.fetch_and_parse_feed(feed.source)
try:
- core.store_feed_entries(
- feed_id=feed.id, # type: ignore
- parsed=parsed,
- epoch_downloaded=epoch_downloaded,
- )
+ core.update_feed(feed.id) # type: ignore
except tagrss.StorageConstraintViolationError:
logging.warning(
f"Failed to update feed {feed.id} with source {feed.source} due"
diff --git a/tagrss.py b/tagrss.py
index 5785fbb..d113a96 100644
--- a/tagrss.py
+++ b/tagrss.py
@@ -53,10 +53,6 @@ Epoch = int
ParsedFeed = feedparser.FeedParserDict
-class StorageProvider(abc.ABC):
- pass
-
-
@dataclasses.dataclass(kw_only=True)
class PartialFeed:
id: typing.Optional[FeedId] = None
@@ -75,6 +71,10 @@ class Entry:
epoch_updated: Epoch
+class StorageProvider(abc.ABC):
+ pass
+
+
class SqliteStorageProvider(StorageProvider):
def __init__(self, storage_path: str | pathlib.Path):
self.__raw_connection = sqlite3.connect(storage_path, check_same_thread=False)
@@ -392,7 +392,7 @@ class TagRss:
def __init__(self, *, storage_path: str | pathlib.Path):
self.__storage = SqliteStorageProvider(storage_path)
- def fetch_and_parse_feed(self, source) -> tuple[ParsedFeed, int]:
+ def __fetch_and_parse_feed(self, source) -> tuple[ParsedFeed, Epoch]:
response = requests.get(source)
epoch_downloaded: int = int(time.time())
if response.status_code != requests.codes.ok:
@@ -412,7 +412,7 @@ class TagRss:
source: str,
tags: list[str],
) -> int:
- parsed, epoch_downloaded = self.fetch_and_parse_feed(source)
+ parsed, epoch_downloaded = self.__fetch_and_parse_feed(source)
title: str = parsed.feed.get("title", "") # type: ignore
feed_id = self.__storage.store_feed(source=source, title=title, tags=tags)
self.__storage.store_entries(
@@ -493,6 +493,11 @@ class TagRss:
included_feeds=included_feeds, included_tags=included_tags
)
+ def update_feed(self, feed_id: FeedId) -> None:
+ source = self.get_feed_source(feed_id)
+ parsed, epoch_downloaded = self.__fetch_and_parse_feed(source)
+ self.store_feed_entries(parsed, feed_id, epoch_downloaded)
+
def store_feed_entries(
self, parsed: ParsedFeed, feed_id: FeedId, epoch_downloaded: int
):