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

recipes/newslaundry.recipe

@@ -0,0 +1,36 @@
+from calibre.web.feeds.news import BasicNewsRecipe, classes
+
+class newslaundry(BasicNewsRecipe):
+    title = 'Newslaundry'
+    __author__ = 'unkn0wn'
+    description = (
+        'Newslaundry is a reader-supported, independent news media company. In an industry driven by corporate'
+        ' and government interests, we strongly believe in the need for an independent news model, and a free'
+        ' and accountable press.'
+    )
+    language = 'en_IN'
+    masthead_url = 'https://images.assettype.com/newslaundry/2020-01/d91cad07-9650-47e9-8bdc-9a6247354d95/Header_logo_NL__2_New.png'
+    encoding = 'utf-8'
+    no_stylesheets = True
+    remove_javascript = True
+    oldest_article = 7 # days
+    resolve_internal_links = True
+
+    ignore_duplicate_articles = {'url'}
+
+    # keep_only_tags = [classes('headline subheadline authorWithTimeStamp story-card')]
+
+    feeds = [
+        ('Articles', 'https://www.newslaundry.com/stories.rss?time-period=last-7-days')
+    ]
+
+    # def preprocess_html(self, soup):
+    #     if h1 := soup.find(**classes('headline')):
+    #        h1.name = 'h1'
+    #     if h3 := soup.find(**classes('subheadline')):
+    #        h3.name = 'h3'
+    #    return soup
+
+    def print_version(self, url):
+        if 'hindi.newslaundry' in url: self.abort_article('Skipping hindi article') # remove this line if you want hindi articles.
+        return url

recipes/reuters.recipe

@@ -58,27 +58,29 @@ class Reuters(BasicNewsRecipe):
     __author__ = 'Kovid Goyal'
     language = 'en'
 
+
     keep_only_tags = [
         prefixed_classes('article-body__container__ article-header__container__'),
     ]
     remove_tags = [
         prefixed_classes(
-            'context-widget__tabs___'
+            'context-widget__tabs___ article-header__toolbar__ read-next-mobile__container__ toolbar__container__ button__link__'
             ' ArticleBody-read-time-and-social Slideshow-expand-button- TwoColumnsLayout-footer- RegistrationPrompt__container___'
-            ' SocialEmbed__inner___'
+            ' SocialEmbed__inner___ trust-badge author-bio__social__ with-spinner__spinner__ author-bio__author-image__'
         ),
-        dict(name=['button', 'link']),
+        dict(name=['button', 'link', 'svg']),
     ]
-    remove_attributes = ['style']
-    extra_css = '''
-    img { max-width: 100%; }
-    '''
+    remove_attributes = ['style', 'height', 'width']
 
-    def preprocess_html(self, soup, *a):
-        for noscript in soup.findAll('noscript'):
-            if noscript.findAll('img'):
-                noscript.name = 'div'
-        return soup
+    extra_css = '''
+        img { max-width: 100%; }
+        [class^="article-header__tags__"],
+        [class^="author-bio__author-card__"],
+        [class^="article-header__author-date__"] {
+            font-size:small;
+        }
+        [data-testid="primary-gallery"], [data-testid="primary-image"] { font-size:small; text-align:center; }
+    '''
 
     def parse_index(self):
         base, sections = country_defs[country]
@@ -103,6 +105,9 @@ class Reuters(BasicNewsRecipe):
             self.log('\t', article['title'], article['url'])
 
     def preprocess_html(self, soup):
+        for noscript in soup.findAll('noscript'):
+            if noscript.findAll('img'):
+                noscript.name = 'div'
         for img in soup.findAll('img', attrs={'srcset':True}):
             img['src'] = img['srcset'].split()[0]
         return soup