mezzo/buch_des_monats
1
0
Fork 0
Code Issues 7 Pull requests Projects Releases Packages Wiki Activity Actions

Fix the html cover scraping (lovelybooks changed the html again)

Browse source
This commit is contained in:
Aaron Fischer 2018-07-13 23:31:00 +02:00
parent 641fcb8712
commit 695afe17db
1 changed files with 12 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
src/buchdesmonats/core.clj
View file

@ -27,13 +27,16 @@
[me.raynes.fs :as fs])) [me.raynes.fs :as fs]))
(defn imgurl->bytes [lovelybooks-url] (defn imgurl->bytes [lovelybooks-url]
(-> (java.net.URL. lovelybooks-url) (let [urls (-> (java.net.URL. lovelybooks-url)
html/html-resource html/html-resource
(html/select [:div.bookcoverXXL :> :div :> :img]) (html/select [:div.cover-wrapper :> :div.cover :> :img.BookCover])
first first
(get-in [:attrs :src]) (get-in [:attrs :srcset])
(http-client/get {:as :byte-array}) (str/split #" "))
:body)) url-to-fetch (last (filter #(re-matches #"http.+\.jpg" %) urls))
stream (http-client/get url-to-fetch {:as :byte-array})]
(:body stream)))
(defn encode-url-part [part] (defn encode-url-part [part]
(java.net.URLEncoder/encode part "UTF-8")) (java.net.URLEncoder/encode part "UTF-8"))