Low-hanging improvements to the crawler APIs

docs/crawlers.md

@@ -202,6 +202,8 @@ find the image URL.
         - attrs
         - content
         - contents
+        - element
+        - elements
         - remove
         - url
 
@@ -299,6 +301,8 @@ for entry in feed.for_date(pub_date):
     options:
       heading_level: 4
       members:
+        - title
+        - link
         - summary
         - content0
         - html

src/comics/aggregator/crawler.py

@@ -315,7 +315,6 @@ def crawl(self, pub_date: dt.date) -> CrawlerResult:
         url = page.src('img[id="theComicImage"]')
         if not url:
             url = page.content('meta[property="og:image"]')
-        assert url
         return CrawlerImage(url)
 
 
@@ -361,7 +360,6 @@ def crawl(self, pub_date: dt.date) -> CrawlerResult:
             if release["release"] == pub_date.strftime("%Y-%m-%d"):
                 page = self.parse_page(release["url"])
                 url = page.src('img[itemprop="image"]')
-                assert url
                 return CrawlerImage(url)
 
         return None
@@ -384,7 +382,6 @@ def crawl(self, pub_date: dt.date) -> CrawlerResult:
         for entry in feed.for_date(pub_date):
             page = self.parse_page(entry.link)
             url = page.src("img#cc-comic")
-            assert url
             text = page.title("img#cc-comic")
             title = re.sub(r".+? - (.+)", r"\1", entry.title)
 

src/comics/aggregator/feedparser.py

@@ -56,6 +56,21 @@ class Entry:
     [`content0`][comics.aggregator.feedparser.Entry.content0].
     """
 
+    title: str
+    """The entry's title.
+
+    Commonly passed straight on as the
+    [`CrawlerImage`][comics.aggregator.crawler.CrawlerImage] title.
+    """
+
+    link: str
+    """The URL of the entry, e.g. the comic's page for this release.
+
+    Typically fed to
+    [`Crawler.parse_page()`][comics.aggregator.crawler.CrawlerBase.parse_page]
+    when the feed itself doesn't hold the image.
+    """
+
     summary: LxmlParser
     """The entry's summary, with
     [`LxmlParser`][comics.aggregator.lxmlparser.LxmlParser] methods available