fix: batch update broken configs and delete unrecoverable (#234)

lib/html2rss/configs/apnews.com/hub.yml

@@ -1,22 +1,16 @@
 ---
 channel:
-  url: https://apnews.com/hub/%<section>s
+  url: https://apnews.com/%<section>s
   language: en
   ttl: 120
   time_zone: UTC
 selectors:
   items:
-    selector: ".FeedCard"
+    selector: ".PagePromo"
   title:
-    selector: h2
+    selector: h3
   link:
     selector: a:first
     extractor: href
   description:
-    selector: p
-  updated:
-    selector: ".Timestamp"
-    extractor: attribute
-    attribute: data-source
-    post_process:
-      name: "parse_time"
+    selector: .PagePromoContentIcons-text

lib/html2rss/configs/bbc.com/mundo.yml

@@ -6,7 +6,7 @@ channel:
   time_zone: UTC
 selectors:
   items:
-    selector: '[data-e2e="story-promo"]'
+    selector: '[data-testid="topic-promos"] > li'
   title:
     selector: a
   link:

lib/html2rss/configs/canarianweekly.com/front.yml

@@ -5,13 +5,9 @@ channel:
   language: en
 selectors:
   items:
-    selector: ".grid-post"
+    selector: ".article__entry"
   title:
-    selector: "h4 > a"
+    selector: "h5 > a"
   link:
-    selector: "h4 > a"
+    selector: "h5 > a"
     extractor: "href"
-  description:
-    selector: "p"
-    post_process:
-      - name: "sanitize_html"

lib/html2rss/configs/formula1.com/latest.yml

@@ -4,15 +4,16 @@ channel:
   ttl: 120
 selectors:
   items:
-    selector: ".f1-latest-listing .f1-latest-listing--grid-item"
+    selector: "#article-list > li"
   title:
-    selector: ".f1--s"
+    selector: "p"
   link:
-    selector: "a.f1-cc"
+    selector: "a"
     extractor: "href"
-    post_process:
-      name: "parse_uri"
   categories:
-    - category
-  category:
-    selector: ".misc--tag"
+    - category_a
+    - category_b
+  category_a:
+    selector: "figcaption>span:first"
+  category_b:
+    selector: "figcaption>span:last"

lib/html2rss/configs/github.com/releases.yml

@@ -5,11 +5,11 @@ channel:
   description: "Releases of %<username>s/%<repository>s on github.com."
 selectors:
   items:
-    selector: '[data-test-selector="release-card"]'
+    selector: ".repository-content section"
   title:
-    selector: "span > a"
+    selector: "h2"
   link:
-    selector: "span > a"
+    selector: "a"
     extractor: "href"
   description:
     selector: '[data-test-selector="body-content"]'

lib/html2rss/configs/imdb.com/ratings.yml

@@ -4,29 +4,18 @@ channel:
   ttl: 1440
 selectors:
   items:
-    selector: "#ratings-container .lister-item"
+    selector: "li.ipc-metadata-list-summary-item"
   title:
-    selector: ".lister-item-header a"
+    selector: ".ipc-title__text"
     post_process:
       name: template
-      string: 'Rated: "%{self}" %{user_rating}/10'
+      string: 'Rated: "%{self}" %{user_rating}/10 [IMDb: %{global_rating}]'
   link:
-    selector: ".lister-item-header a"
+    selector: "a.ipc-title-link-wrapper"
     extractor: "href"
   description:
-    selector: '.lister-item-content > p[class=""]'
-  updated:
-    selector: ".lister-item-content > p.text-muted:not(.text-small)"
-    post_process:
-      name: parse_time
+    selector: ".ipc-html-content-inner-div"
   global_rating:
-    selector: ".ipl-rating-star .ipl-rating-star__rating"
+    selector: ".ipc-rating-star--imdb .ipc-rating-star--rating"
   user_rating:
-    selector: ".ipl-rating-star--other-user .ipl-rating-star__rating"
-  genres:
-    selector: ".genre"
-  pg_rating:
-    selector: ".certificate"
-  categories:
-    - genres
-    - pg_rating
+    selector: ".ipc-rating-star .ipc-rating-star--rating"

lib/html2rss/configs/newyorker.com/magazine.yml

@@ -6,11 +6,11 @@ channel:
   time_zone: UTC
 selectors:
   items:
-    selector: main section ul > li
+    selector: .summary-item
   title:
-    selector: h4
+    selector: h3
   link:
     selector: a:first
     extractor: href
   description:
-    selector: h5
+    selector: .summary-item__dek

lib/html2rss/configs/robinwood.de/aktuelles.yml

@@ -5,16 +5,11 @@ channel:
   language: de
 selectors:
   items:
-    selector: ".view-content article"
+    selector: "article[data-history-node-id]"
   title:
-    selector: ".outer-link__title"
+    selector: "h2"
   link:
     selector: "a"
     extractor: "href"
-  category:
-    selector: ".teaser__category"
   description:
-    selector: ".teaser__text"
-  updated:
-    selector: '[property="dc:date"]'
-    attribute: "content"
+    selector: ".teaser-text"

lib/html2rss/configs/spiegel.de/impressum_autor.yml

@@ -5,16 +5,16 @@ channel:
   language: de
 selectors:
   items:
-    selector: "[data-area='article-teaser-list'] [data-area]"
+    selector: '[data-block-el="articleTeaser"] > article'
   title:
-    selector: "h2 .mb-12"
+    selector: "h2"
   prefixed_title:
-    selector: ".h2 .mb-4"
+    selector: "h2"
   link:
-    selector: "h2 > a"
+    selector: "section > a"
     extractor: "href"
   descripton:
-    selector: ".mb-12 > .leading-loose "
+    selector: ".leading-loose"
   updated:
     selector: "footer"
     extractor: text