merge all rss

my/_rss.py

@@ -8,5 +8,3 @@ class Subscription(NamedTuple):
     id: str
     subscribed: bool=True
 
-
-

my/feedbin.py

@@ -12,7 +12,6 @@ from dateutil.parser import isoparse
 @listify
 def parse_file(f: Path):
     raw = json.loads(f.read_text())
-    print(raw)
     for r in raw:
         yield Subscription(
             # TODO created_at?

my/feedly.py

@@ -6,7 +6,7 @@ import json
 from pathlib import Path
 from typing import Dict, List
 from datetime import datetime
-from dateutil.parser import isoparse
+import pytz
 
 
 @listify
@@ -14,12 +14,13 @@ def parse_file(f: Path):
     raw = json.loads(f.read_text())
     for r in raw:
         # err, some even don't have website..
-        website = r.get('website')
+        rid = r['id']
+        website = r.get('website', rid) # meh
         yield Subscription(
             # TODO created_at?
             title=r['title'],
             url=website,
-            id=r['id'],
+            id=rid,
         )
 
 def get_states() -> Dict[datetime, List[Subscription]]:
@@ -27,6 +28,7 @@ def get_states() -> Dict[datetime, List[Subscription]]:
     for f in sorted(Path(paths.feedly.export_dir).glob('*.json')):
         dts = f.stem.split('_')[-1]
         dt = datetime.strptime(dts, '%Y%m%d%H%M%S')
+        dt = pytz.utc.localize(dt)
         subs = parse_file(f)
         res[dt] = subs
     return res

my/rss.py

@@ -1,12 +1,29 @@
+from itertools import chain
+from typing import List
+
+from ._rss import Subscription
+
 from . import feedbin
 from . import feedly
-from ._rss import Subscription
 # TODO google reader?
 
 
-def get_history():
+def get_all_subscriptions() -> List[Subscription]:
     """
-    It's useful to keep track of websites you unsubscribed from too,
+    Keeps track of everything I ever subscribed to. It's useful to keep track of unsubscribed too
     so you don't try to subscribe again (or at least take into account why you unsubscribed before)
     """
-    pass
+    states = {}
+    states.update(feedly.get_states())
+    states.update(feedbin.get_states())
+    by_url = {}
+    for d, feeds in sorted(states.items()):
+        for f in feeds:
+            if f.url not in by_url:
+                by_url[f.url] = f
+    res = []
+    last = {x.url: x for x in max(states.items())[1]}
+    for u, x in sorted(by_url.items()):
+        present = u in last
+        res.append(x._replace(subscribed=present))
+    return res