🦾 New function to check URLS with command-line.

Author: alexjc

src/weboptout/__init__.py

@@ -3,4 +3,4 @@
 __version__ = "dev"
 
 from .types import rsv, Reservation, Status
-from .web import check_domain_reservation
+from .web import check_domain_reservation, check_url_reservation

src/weboptout/__main__.py

@@ -1,10 +1,11 @@
 ## Copyright © 2023, Alex J. Champandard.  Licensed under MIT; see LICENSE! ⚘
 
+import re
 import textwrap
 
 import click
 
-from weboptout import check_domain_reservation, rsv
+from weboptout import check_domain_reservation, check_url_reservation, rsv
 from weboptout.types import Status
 
 
@@ -13,17 +14,13 @@ def main():
     pass
 
 
-@main.command()
-@click.argument('domains', nargs=-1)
-def check(domains):
-    print(f"\n\033[1;97m{'Domain':22} Opt-Out\033[0m\n")
-
-    for domain in domains:
-        res = check_domain_reservation(domain, use_database=True)
+def _run_checks(check_fn, sources):
+    for source in sources:
+        res = check_fn(source)
         if res == rsv.YES:
-            print(f"  {domain:24}✓")
+            print(f"  {source:23} ✓")
         else:
-            print(f"  {domain:24}?")
+            print(f"  {source:23} ?")
 
         for record in res.process:
             print(
@@ -38,5 +35,29 @@ def check(domains):
         print()
 
 
+@main.command()
+@click.argument('domains', nargs=-1)
+def check_domain(domains):
+    print(f"\n\033[1;97m{'Domain':22} Opt-Out\033[0m\n")
+    return _run_checks(check_domain_reservation, domains)
+
+
+@main.command()
+@click.argument('urls', nargs=-1)
+def check_url(urls):
+    print(f"\n\033[1;97m{'Link':22} Opt-Out\033[0m\n")
+    return _run_checks(check_url_reservation, urls)
+
+
+@main.command()
+@click.argument('sources', nargs=-1)
+def check(sources):
+    if all(re.match("^https?://", src) for src in sources):
+        return check_url(sources)
+    if all(not re.match("^https?://", src) for src in sources):
+        return check_domain(sources)
+    raise NotImplementedError
+
+
 if __name__ == "__main__":
     main()

src/weboptout/web.py

@@ -1,8 +1,10 @@
 ## Copyright © 2023, Alex J. Champandard.  Licensed under MIT; see LICENSE! ⚘
 
+from urllib.parse import urlparse
+
 from .types import rsv, Reservation, Status
 from .client import ClientSession
-from .utils import allow_sync_calls, retrieve_result_from_cache
+from .utils import allow_sync_calls
 from .http import search_tos_for_domain
 from .html import check_tos_reservation
 
@@ -11,7 +13,6 @@
 
 
 @allow_sync_calls
-# @retrieve_result_from_cache("cache/rsv.pkl", key="domain")
 async def check_domain_reservation(domain: str) -> Reservation:
     assert not any(domain.startswith(k) for k in ("https://", "http://"))
 
@@ -40,3 +41,8 @@ async def check_domain_reservation(domain: str) -> Reservation:
 
     # This happens when none of the domains can be looked up.
     return rsv.ERROR(url=None, process=client._steps, outcome=client._output)
+
+
+def check_url_reservation(url: str) -> Reservation:
+    domain = urlparse(url).netloc
+    return check_domain_reservation(domain)