Merge branch 'master' of https://github.com/yodha8/calibre

recipes/cacm.recipe

@@ -1,39 +1,30 @@
-import datetime
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
+
 from calibre.web.feeds.news import BasicNewsRecipe
 
-
-class AdvancedUserRecipe1286242553(BasicNewsRecipe):
-    title = u'CACM'
-    oldest_article = 7
+class CACM(BasicNewsRecipe):
+    title          = "ACM CACM Magazine"
+    description    = "Published on day 1 of every month."
+    oldest_article = 30
     max_articles_per_feed = 100
-    needs_subscription = True
-    feeds = [(u'CACM', u'http://cacm.acm.org/magazine.rss')]
-    language = 'en'
-    __author__ = 'jonmisurda'
-    no_stylesheets = True
-    remove_tags = [
-        dict(name='div', attrs={'class': ['FeatureBox', 'ArticleComments', 'SideColumn',
-                                          'LeftColumn', 'RightColumn', 'SiteSearch', 'MainNavBar', 'more', 'SubMenu', 'inner']})
+    auto_cleanup   = True
+
+    feeds          = [
+        ('ACM CACM', 'https://cacm.acm.org/magazine.rss'),
     ]
-    cover_url_pattern = 'http://cacm.acm.org/magazines/%d/%d'
-
-    def get_browser(self):
-        br = BasicNewsRecipe.get_browser(self)
-        if self.username is not None and self.password is not None:
-            br.open('https://cacm.acm.org/login')
-            br.select_form(nr=1)
-            br['current_member[user]'] = self.username
-            br['current_member[passwd]'] = self.password
-            br.submit()
-        return br
-
+    
     def get_cover_url(self):
-        now = datetime.datetime.now()
+        """
+        Parse out cover URL from cover page.
+        Example:
+        From: https://cacm.acm.org/system/assets/0004/2570/April2022.Cover.1000x1338.large.jpg?1647524668&1647524668
+        Get:  https://cacm.acm.org/system/assets/0004/2570/April2022.Cover.1000x1338.jpg
+        """
 
-        cover_url = None
-        soup = self.index_to_soup(self.cover_url_pattern %
-                                  (now.year, now.month))
-        cover_item = soup.find('img', attrs={'alt': 'magazine cover image'})
-        if cover_item:
-            cover_url = cover_item['src']
-        return cover_url
+        soup = self.index_to_soup("https://cacm.acm.org/")
+        a_img = soup.find("a", class_="menuCover")
+        img_url = a_img.img["src"]
+        img_url = img_url.split("?")[0]
+        img_url = img_url.replace(".large", "")
+        return img_url