Merge branch 'master' of https://github.com/unkn0w7n/calibre

recipes/20_minutos.recipe

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
 __license__ = 'GPL v3'
 __author__ = 'Luis Hernandez'
 __copyright__ = 'Luis Hernandez<tolyluis@gmail.com>'

recipes/abc_es.recipe

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
 __license__ = 'GPL v3'
 __author__ = 'Ricardo Jurado'
 __copyright__ = 'Ricardo Jurado'

recipes/horizons.recipe

@@ -53,11 +53,8 @@ class horizons(BasicNewsRecipe):
                 url = 'https://www.cirsd.org' + url
             self.cover_url = a.find('img')['src']
             self.log(self.cover_url)
-            issue = a.find('div', attrs={'class':'horizon-gallery-title'})
+        self.title = url.split('/')[-1].replace('-', ' ').title()
-            if issue:
+        self.log('Downloading Issue: ', self.title)
-                self.title = self.tag_to_string(issue).strip()
-                self.timefmt = ' [' + self.tag_to_string(issue).strip().replace('Horizons ', '')  + ']'
-                self.log('Downloading Issue: ', self.timefmt, self.title)
         soup = self.index_to_soup(url)
 
         feeds = []

recipes/huffingtonpost.recipe

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
 from __future__ import print_function
 
 from calibre.web.feeds.news import BasicNewsRecipe
@@ -28,6 +30,20 @@ class HuffingtonPostRecipe(BasicNewsRecipe):
     no_stylesheets = True
     remove_javascript = True
 
+    recipe_specific_options = {
+        'days': {
+            'short': 'Oldest article to download from this news source. In days ',
+            'long': 'For example, 0.5, gives you articles from the past 12 hours',
+            'default': str(oldest_article)
+        }
+    }
+
+    def __init__(self, *args, **kwargs):
+        BasicNewsRecipe.__init__(self, *args, **kwargs)
+        d = self.recipe_specific_options.get('days')
+        if d and isinstance(d, str):
+            self.oldest_article = float(d)
+
     keep_only_tags = [
         classes('entry__header entry__body')
     ]

recipes/la_jornada.recipe

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
 __license__ = 'GPL v3'
 __copyright__ = '2010-2012, Darko Miletic <darko.miletic at gmail.com>, Rogelio Domínguez <rogelio.dominguez@gmail.com>'
 '''

recipes/new_yorker.recipe

@@ -79,9 +79,19 @@ class NewYorker(BasicNewsRecipe):
         # img.save(buf, format='JPEG')
         # return buf.getvalue()
 
+    recipe_specific_options = {
+        'date': {
+            'short': 'The date of the edition to download (YYYY/MM/DD format)',
+            'long': 'For example, 2024/07/08'
+        }
+    }
+
     def parse_index(self):
-        soup = self.index_to_soup(
+        issue_url = 'https://www.newyorker.com/magazine?intcid=magazine'
-            'https://www.newyorker.com/magazine?intcid=magazine')
+        d = self.recipe_specific_options.get('date')
+        if d and isinstance(d, str):
+            issue_url = 'https://www.newyorker.com/magazine/' + d
+        soup = self.index_to_soup(issue_url)
         cover_img = soup.find('picture',
             attrs={'class': lambda x: x and 'asset-embed__responsive-asset' in x})
         if cover_img is not None:

recipes/nhk_news.recipe

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
 from calibre.web.feeds.news import BasicNewsRecipe
 
 # feed source: https://www.nhk.or.jp/toppage/rss/index.html

recipes/nymag.recipe

@@ -19,7 +19,7 @@ class NewYorkMagazine(BasicNewsRecipe):
     title = 'New York Magazine'
     __author__ = 'Kovid Goyal'
     description = 'Food, culture, arts and entertainment in New York'
-    language = 'en'
+    language = 'en_US'
     no_stylesheets = True
     remove_javascript = True
     encoding = 'utf-8'
@@ -32,8 +32,19 @@ class NewYorkMagazine(BasicNewsRecipe):
     ]
     remove_attributes = ['srcset']
 
+    recipe_specific_options = {
+        'date': {
+            'short': 'The date of the edition to download (YYYY-MM-DD format)',
+            'long': 'For example, 2024-07-01'
+        }
+    }
+
     def nymag_get_index(self):
-        return self.index_to_soup('https://nymag.com/maglinks/nym-home-05')
+        issue_url = 'https://nymag.com/maglinks/nym-home-05'
+        d = self.recipe_specific_options.get('date')
+        if d and isinstance(d, str):
+            issue_url = 'https://nymag.com/magazine/toc/' + d + '.html'
+        return self.index_to_soup(issue_url)
 
     def parse_index(self):
         soup = self.nymag_get_index()

recipes/scmp.recipe

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
 """
 scmp.com
 """