Blogger scraper tidied up and documented.

src/html_to_md/blogger_to_md.clj

@@ -0,0 +1,41 @@
+(ns html-to-md.blogger-to-md
+    (:require [clojure.string :as s]
+              [html-to-md.html-to-md :refer [markdown-dispatcher markdown-header]]
+              [html-to-md.transformer :refer [process]]
+              [net.cgrand.enlive-html :as html]))
+
+(defn blogger-scraper
+    "Processor which scrapes the actual post content out of a blogger page.
+    *NOTE:* This was written to scrape *my* blogger pages, yours may be
+    different!"
+    [e d]
+    (let [title (first (html/select e [:h3.post-title]))
+          content (html/select e [:div.post-body])]
+        (if (and title content)
+            (apply
+                str
+                (cons
+                    (markdown-header title d 1)
+                    (process content d))))))
+
+(defn image-table-processor
+    "Blogger's horrible tag soup wraps images in tables. Is this table such
+    a table? If so extract the image from it and process it to markdown;
+    otherwise, fall back on what `markdown-dispatcher` would do with the
+    table (which is currently nothing, but that will change)."
+    [e d]
+    (let [caption (process (first (html/select e [:td.tr-caption])) d)
+          alt (if caption (s/trim (apply str caption)))
+          image (first (html/select e [:img]))
+          src (if image (-> image :attrs :src))]
+        (if image
+            (str "![image: " alt "](" src ")")
+            (process e markdown-dispatcher))))
+
+
+(def blogger-dispatcher
+    "Adaptation of `markdown-dispatcher`, q.v., with the `:table`, `:h3` and
+    `:html` dispatches overridden."
+    (assoc markdown-dispatcher
+        :html blogger-scraper
+        :table image-table-processor))

src/html_to_md/core.clj

@@ -1,6 +1,7 @@
 (ns html-to-md.core
     (:require [html-to-md.transformer :refer [transform process]]
-              [html-to-md.html-to-md :refer [markdown-dispatcher]]))
+              [html-to-md.html-to-md :refer [markdown-dispatcher]]
+              [html-to-md.blogger-to-md :refer [blogger-dispatcher]]))
 
 (defn html-to-md
     "Transform the HTML document referenced by `url` into Markdown, and write
@@ -9,3 +10,12 @@
      (apply str (transform url markdown-dispatcher)))
     ([url output]
      (spit output (html-to-md url))))
+
+(defn blogger-to-md
+    "Transform the Blogger post referenced by `url` into Markdown, and write
+    it to `output`, if supplied. *NOTE:* This was written to scrape *my*
+    blogger pages, yours may be different!"
+    ([url]
+     (apply str (transform url blogger-dispatcher)))
+    ([url output]
+     (spit output (blogger-to-md url))))

src/html_to_md/html_to_md.clj

@@ -18,7 +18,7 @@
     "Process the line-break element `e`, so beloved of tag-soupers, into
     markdown"
     [e d]
-    "\n\n")
+    "\n")
 
 (defn markdown-code
     "Process the code or samp `e` into markdown, using dispatcher `d`."