]> git.scottworley.com Git - paperdoorknob/commitdiff
Drop Post as a class
authorScott Worley <scottworley@scottworley.com>
Sat, 25 Nov 2023 09:17:05 +0000 (01:17 -0800)
committerScott Worley <scottworley@scottworley.com>
Wed, 20 Dec 2023 01:37:10 +0000 (17:37 -0800)
paperdoorknob.py
paperdoorknob_test.py

index fb2df1f1cc1c7443bc6e07018bad7148eb12a5c6..8329f83e69e026791f6997a296a10af19ab4d2e1 100644 (file)
@@ -18,30 +18,6 @@ import requests_cache
 from xdg_base_dirs import xdg_cache_home
 
 
-class Post:
-    def __init__(self, html: BeautifulSoup) -> None:
-        self._html = html
-        for eb in self._html.find_all("div", class_="post-edit-box"):
-            eb.decompose()
-        for footer in self._html.find_all("div", class_="post-footer"):
-            footer.decompose()
-
-    def text(self) -> Tag:
-        body = self._html.body
-        assert body
-        text = body.find_next("div", class_="post-post")
-        assert isinstance(text, Tag)
-        return text
-
-    def replies(self) -> Iterable[Tag]:
-        replies = self._html.find_all("div", class_="post-reply")
-        assert all(isinstance(r, Tag) for r in replies)
-        return replies
-
-    def entries(self) -> Iterable[Tag]:
-        return itertools.chain([self.text()], self.replies())
-
-
 def command_line_parser() -> ArgumentParser:
     parser = ArgumentParser(prog='paperdoorknob', description='Print glowfic')
     parser.add_argument(
@@ -63,11 +39,42 @@ def fetch(url: str, session: requests.Session, timeout: int) -> BeautifulSoup:
         return BeautifulSoup(r.text, 'html.parser')
 
 
+def clean(html: BeautifulSoup) -> BeautifulSoup:
+    for eb in html.find_all("div", class_="post-edit-box"):
+        eb.decompose()
+    for footer in html.find_all("div", class_="post-footer"):
+        footer.decompose()
+    return html
+
+
+def replies(html: BeautifulSoup) -> Iterable[Tag]:
+    def text() -> Tag:
+        body = html.body
+        assert body
+        text = body.find_next("div", class_="post-post")
+        assert isinstance(text, Tag)
+        return text
+
+    def the_replies() -> Iterable[Tag]:
+        rs = html.find_all("div", class_="post-reply")
+        assert all(isinstance(r, Tag) for r in rs)
+        return rs
+
+    return itertools.chain([text()], the_replies())
+
+
+def process(
+        url: str,
+        session: requests.Session,
+        timeout: int) -> Iterable[Tag]:
+    html = clean(fetch(url, session, timeout))
+    return replies(html)
+
+
 def main() -> None:
     args = command_line_parser().parse_args()
     with requests_cache.CachedSession(args.cache_path, cache_control=True) as session:
-        html = fetch(args.url, session, args.timeout)
-        Post(html)
+        process(args.url, session, args.timeout)
 
 
 if __name__ == '__main__':
index 7658cf424f82e5485cdcf6a160d821f0bb1654a5..35756cbd0c8897533bcbda12dc8b38b6e8f2e3bd 100644 (file)
@@ -99,14 +99,11 @@ class TestFetch(unittest.TestCase):
             paperdoorknob.fetch(f"http://localhost:{self._port()}", s, TIMEOUT)
             self.assertEqual(self._request_counter, 1)
 
-    def testFetchConents(self) -> None:
+    def testProcess(self) -> None:
         with requests.session() as s:
-            post = paperdoorknob.Post(paperdoorknob.fetch(
-                f"http://localhost:{self._port()}", s, TIMEOUT))
-            self.assertEqual(post.text().text.strip(), "This is glowfic")
-            self.assertEqual([r.text.strip() for r in post.replies()],
-                             ["You sure?", "Pretty sure."])
-            self.assertEqual([r.text.strip() for r in post.entries()],
+            replies = paperdoorknob.process(
+                f"http://localhost:{self._port()}", s, TIMEOUT)
+            self.assertEqual([r.text.strip() for r in replies],
                              ["This is glowfic", "You sure?", "Pretty sure."])
 
     def testFetchErrors(self) -> None: