Science Journal by unkn0wn

recipes/science_journal.recipe

@@ -0,0 +1,85 @@
+#!/usr/bin/env python
+
+from calibre.web.feeds.news import BasicNewsRecipe, classes
+
+
+def absurl(url):
+    if url.startswith('/'):
+        url = 'https://www.science.org' + url
+    return url
+
+
+
+class science(BasicNewsRecipe):
+    title = 'Science Journal'
+    __author__ = 'unkn0wn'
+    description = (
+        'Science continues to publish the very best in research across the sciences, with articles that '
+        'consistently rank among the most cited in the world.'
+    )
+    encoding = 'utf-8'
+    no_javascript = True
+    no_stylesheets = True
+    remove_attributes = ['style', 'height', 'width']
+    language = 'en'
+    extra_css = '''
+        .news-article__figure__caption {font-size:small; text-align:center;}
+        .contributors, .core-self-citation, .meta-panel__left-content, .news-article__hero__top-meta,
+		.news-article__hero__bottom-meta, #bibliography, #elettersSection {font-size:small;}
+        img {display:block; margin:0 auto;}
+        .core-lede {font-style:italic; color:#202020;}
+    '''
+
+    ignore_duplicate_articles = {'url'}
+
+    keep_only_tags = [
+        classes('meta-panel__left-content news-article__hero__info news-article__hero__figure bodySection'),
+        dict(name='h1', attrs={'property':'name'}),
+        classes('core-lede contributors core-self-citation'),
+        dict(attrs={'data-core-wrapper':'content'})
+    ]
+
+    remove_tags = [
+        classes('pb-ad')
+    ]
+    browser_type = 'qt'
+    simultaneous_downloads = 1
+
+    def preprocess_html(self, soup):
+        for p in soup.findAll(attrs={'role':'paragraph'}):
+            p.name = 'p'
+        return soup
+
+    def parse_index(self):
+        url = 'https://www.science.org/toc/science/current'
+
+        soup = self.index_to_soup(url)
+        tme = soup.find(**classes('journal-issue__vol'))
+        if tme:
+            self.timefmt = ' [%s]' % self.tag_to_string(tme).strip()
+        det = soup.find(attrs={'id':'journal-issue-details'})
+        if det:
+            self.description = self.tag_to_string(det).strip()
+
+        feeds = []
+
+        div = soup.find('div', attrs={'class':'toc__body'})
+        for sec in div.findAll('section', **classes('toc__section')):
+            name = sec.find(**classes('sidebar-article-title--decorated'))
+            section = self.tag_to_string(name).strip()
+            self.log(section)
+
+            articles = []
+
+            for card in sec.findAll(**classes('card-header')):
+                ti = card.find(**classes('article-title'))
+                url = absurl(ti.a['href'])
+                title = self.tag_to_string(ti).strip()
+                desc = ''
+                meta = card.find(**classes('card-meta'))
+                if meta:
+                    desc = self.tag_to_string(meta).strip()
+                self.log('          ', title, '\n\t', desc, '\n\t', url)
+                articles.append({'title': title, 'description':desc, 'url': url})
+            feeds.append((section, articles))
+        return feeds