don't dl subscriber-only articles [skip ci]

recipes_custom/aiweirdness.recipe.py

@@ -26,3 +26,13 @@ def populate_article_metadata(self, article, __, _):
         if (not self.pub_date) or article.utctime > self.pub_date:
             self.pub_date = article.utctime
             self.title = format_title(_name, article.utctime)
+
+    def parse_feeds(self):
+        feeds = BasicNewsRecipe.parse_feeds(self)
+        for feed in feeds:
+            for article in feed.articles[:]:
+                self.log(article)
+                if not article.content:
+                    self.log.warn(f"removing subscriber-only article {article.title} from feed")
+                    feed.articles.remove(article)
+        return feeds

recipes_custom/life-is-a-sacred-text.recipe.py

@@ -7,6 +7,7 @@
 from recipes_shared import BasicNewsrackRecipe, format_title
 from calibre.utils.date import utcnow, parse_date
 from calibre.web.feeds import Feed
+from calibre.ebooks.BeautifulSoup import BeautifulSoup
 
 _name = "Life is a Sacred Text"
 
@@ -59,10 +60,19 @@ def populate_article_metadata(self, article, soup, _):
         desc_el.string = article.summary
         # article_img = soup.find("img")
 
+    def parse_feeds(self):
+        feeds = BasicNewsRecipe.parse_feeds(self)
+        for feed in feeds:
+            for article in feed.articles[:]:
+                raw_soup = BeautifulSoup(article.content)
+                p = raw_soup.find("p")
+                ptxt = self.tag_to_string(p)
+                if "Read more" in ptxt:
+                    self.log.warn(f"removing subscriber-only article {article.title} from feed")
+                    feed.articles.remove(article)
+        return feeds
+
     def preprocess_html(self, soup):
-        paras = soup.find_all("p")
-        if paras and len(paras) < 4:
-            self.abort_article("Subscription required")
         headline = soup.find("h2")
         a_date = soup.new_tag("div")
         a_desc = soup.new_tag("h3")