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

recipes/science_advances.recipe

@@ -1,50 +1,101 @@
 #!/usr/bin/env python
-# vim:fileencoding=utf-8
-from __future__ import absolute_import, division, print_function, unicode_literals
+from calibre.web.feeds.news import BasicNewsRecipe, classes
 
-from calibre.web.feeds.news import BasicNewsRecipe
+def absurl(url):
+    if url.startswith('/'):
+        url = 'https://www.science.org' + url
+    return url
 
 
-def check_words(words):
-    return lambda x: x and frozenset(words.split()).intersection(x.split())
-
-
-class ScienceAdvances(BasicNewsRecipe):
+class scienceadv(BasicNewsRecipe):
     title = 'Science Advances'
-    __author__ = 'Jose Ortiz'
+    __author__ = 'unkn0wn'
     description = (
-        'Science Advances is a peer-reviewed multidisciplinary open-access'
-        ' scientific journal established in early 2015.  The journal\'s scope'
-        ' includes all areas of science, including the life sciences, physical'
-        ' sciences, social sciences, computer sciences, and environmental'
-        ' sciences.'
+        'Science Advances is the American Association for the Advancement of Science’s (AAAS) open access '
+        'multidisciplinary journal, publishing impactful research papers and reviews in any area of science, in '
+        'both disciplinary-specific and broad, interdisciplinary areas. The mission of Science Advances is to provide '
+        ';fair, fast, and expert peer review to authors and a vetted selection of research, freely available to readers.'
     )
+    encoding = 'utf-8'
+    no_javascript = True
+    no_stylesheets = True
+    remove_attributes = ['style', 'height', 'width']
+    masthead_url = 'https://www.science.org/pb-assets/images/logos/sciadv-logo-1620488349693.svg'
     language = 'en'
-    encoding = 'UTF-8'
-    max_articles_per_feed = 100
-    publication_type = 'magazine'
-    keep_only_tags = [dict(name='article', attrs={'class': check_words('primary')})]
-    feeds = [
-        (
-            'Science Advances: Current Issue',
-            'http://advances.sciencemag.org/rss/current.xml'
-        ),
+    simultaneous_downloads = 1
+    browser_type = 'qt'
+
+    extra_css = '''
+        .news-article__figure__caption {font-size:small; text-align:center;}
+        .core-self-citation, .meta-panel__left-content, .news-article__hero__top-meta {font-size:small;}
+        .contributors, .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'}),
+        dict(name='div', **classes('core-lede contributors core-self-citation')),
+        dict(attrs={'data-core-wrapper':'content'})
     ]
 
-    def get_cover_url(self):
-        soup = self.index_to_soup('http://advances.sciencemag.org/')
-        img = soup.find(id='content-block').find(
-            'img', attrs={'class': check_words('cover-img')}
-        )
-        return img['src']
+    remove_tags = [
+        classes('pb-ad news-article__hero__scroller news-article__version-of-story')
+    ]
+
+    recipe_specific_options = {
+        'issue': {
+            'short': 'Enter the Issue Number you want to download\n(Vol/Issue format)',
+            'long': 'For example, 385/6710',
+            'default': 'current'
+        }
+    }
 
     def preprocess_html(self, soup):
-        for img in soup.findAll('img', attrs={'data-src': True}):
-            if img['data-src'].endswith('medium.gif'):
-                img['src'] = img['data-src'][:-10] + 'large.jpg'
-                a = img.findParent(attrs={'href': True})
-                if a is not None and a['href'].startswith(img['src']):
-                    del a['href']
-            else:
-                img['src'] = img['data-src']
+        for p in soup.findAll(attrs={'role':'paragraph'}):
+            p.name = 'p'
+            p.attrs = {}
         return soup
+
+    def parse_index(self):
+        issue_url = 'https://www.science.org/toc/sciadv/current'
+        d = self.recipe_specific_options.get('issue')
+        if d and isinstance(d, str):
+            issue_url = 'https://www.science.org/toc/sciadv/' + d
+
+        soup = self.index_to_soup(issue_url)
+        tme = soup.find(**classes('journal-issue__vol'))
+        if tme:
+            self.timefmt = ' [%s]' % self.tag_to_string(tme).strip().replace('|', ' | ')
+        det = soup.find(attrs={'id':'journal-issue-details'})
+        if det:
+            self.description = self.tag_to_string(det).strip()
+        cov = soup.find(**classes('cover-image__image'))
+        if cov:
+            self.cover_url = absurl(cov.img['src'])
+
+        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\t', url)
+                articles.append({'title': title, 'description':desc, 'url': url})
+            feeds.append((section, articles))
+        return feeds

recipes/sciimmunol.recipe

@@ -0,0 +1,101 @@
+#!/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 scienceadv(BasicNewsRecipe):
+    title = 'Science Immunology'
+    __author__ = 'unkn0wn'
+    description = (
+        'Immunology is in a period of unprecedented expansion and progress. The broad influence of the immune system on diverse '
+        'aspects of health and disease is beginning to be appreciated, and innovative immunological interventions are proving successful '
+        'in the clinic. New tools are revealing the extent of this influence with exceptional precision and reach. Science Immunology '
+        'provides a platform for the most exciting findings in this growing field.'
+    )
+    encoding = 'utf-8'
+    no_javascript = True
+    no_stylesheets = True
+    remove_attributes = ['style', 'height', 'width']
+    masthead_url = 'https://www.science.org/pb-assets/images/logos/sciimmunol-logo-1620488349717.svg'
+    language = 'en'
+    simultaneous_downloads = 1
+    browser_type = 'qt'
+
+    extra_css = '''
+        .news-article__figure__caption {font-size:small; text-align:center;}
+        .core-self-citation, .meta-panel__left-content, .news-article__hero__top-meta {font-size:small;}
+        .contributors, .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'}),
+        dict(name='div', **classes('core-lede contributors core-self-citation')),
+        dict(attrs={'data-core-wrapper':'content'})
+    ]
+
+    remove_tags = [
+        classes('pb-ad news-article__hero__scroller news-article__version-of-story')
+    ]
+
+    recipe_specific_options = {
+        'issue': {
+            'short': 'Enter the Issue Number you want to download\n(Vol/Issue format)',
+            'long': 'For example, 385/6710',
+            'default': 'current'
+        }
+    }
+
+    def preprocess_html(self, soup):
+        for p in soup.findAll(attrs={'role':'paragraph'}):
+            p.name = 'p'
+            p.attrs = {}
+        return soup
+
+    def parse_index(self):
+        issue_url = 'https://www.science.org/toc/sciimmunol/current'
+        d = self.recipe_specific_options.get('issue')
+        if d and isinstance(d, str):
+            issue_url = 'https://www.science.org/toc/sciimmunol/' + d
+
+        soup = self.index_to_soup(issue_url)
+        tme = soup.find(**classes('journal-issue__vol'))
+        if tme:
+            self.timefmt = ' [%s]' % self.tag_to_string(tme).strip().replace('|', ' | ')
+        det = soup.find(attrs={'id':'journal-issue-details'})
+        if det:
+            self.description = self.tag_to_string(det).strip()
+        cov = soup.find(**classes('cover-image__image'))
+        if cov:
+            self.cover_url = absurl(cov.img['src'])
+
+        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\t', url)
+                articles.append({'title': title, 'description':desc, 'url': url})
+            feeds.append((section, articles))
+        return feeds

recipes/scirobotocs.recipe

@@ -0,0 +1,101 @@
+#!/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 scienceadv(BasicNewsRecipe):
+    title = 'Science Robotics'
+    __author__ = 'unkn0wn'
+    description = (
+        'Science Robotics provides a much-needed forum for the latest technological advances and for the critical social, ethical '
+        'and policy issues surrounding robotics. Science Robotics caters to both researchers and general stakeholders. It is multidisciplinary, '
+        'covering the traditional disciplines of robotics, as well as emerging trends such as advanced materials and bio-inspired designs; it covers '
+        'all scales, from very large systems to micro/nano robots; its scope is broad, addressing both theoretical advances and practical applications.'
+    )
+    encoding = 'utf-8'
+    no_javascript = True
+    no_stylesheets = True
+    remove_attributes = ['style', 'height', 'width']
+    masthead_url = 'https://www.science.org/pb-assets/images/logos/scirobotics-logo-1620488350107.svg'
+    language = 'en'
+    simultaneous_downloads = 1
+    browser_type = 'qt'
+
+    extra_css = '''
+        .news-article__figure__caption {font-size:small; text-align:center;}
+        .core-self-citation, .meta-panel__left-content, .news-article__hero__top-meta {font-size:small;}
+        .contributors, .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'}),
+        dict(name='div', **classes('core-lede contributors core-self-citation')),
+        dict(attrs={'data-core-wrapper':'content'})
+    ]
+
+    remove_tags = [
+        classes('pb-ad news-article__hero__scroller news-article__version-of-story')
+    ]
+
+    recipe_specific_options = {
+        'issue': {
+            'short': 'Enter the Issue Number you want to download\n(Vol/Issue format)',
+            'long': 'For example, 385/6710',
+            'default': 'current'
+        }
+    }
+
+    def preprocess_html(self, soup):
+        for p in soup.findAll(attrs={'role':'paragraph'}):
+            p.name = 'p'
+            p.attrs = {}
+        return soup
+
+    def parse_index(self):
+        issue_url = 'https://www.science.org/toc/scirobotics/current'
+        d = self.recipe_specific_options.get('issue')
+        if d and isinstance(d, str):
+            issue_url = 'https://www.science.org/toc/scirobotics/' + d
+
+        soup = self.index_to_soup(issue_url)
+        tme = soup.find(**classes('journal-issue__vol'))
+        if tme:
+            self.timefmt = ' [%s]' % self.tag_to_string(tme).strip().replace('|', ' | ')
+        det = soup.find(attrs={'id':'journal-issue-details'})
+        if det:
+            self.description = self.tag_to_string(det).strip()
+        cov = soup.find(**classes('cover-image__image'))
+        if cov:
+            self.cover_url = absurl(cov.img['src'])
+
+        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\t', url)
+                articles.append({'title': title, 'description':desc, 'url': url})
+            feeds.append((section, articles))
+        return feeds

recipes/scisignaling.recipe

@@ -0,0 +1,100 @@
+#!/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 scienceadv(BasicNewsRecipe):
+    title = 'Science Signaling'
+    __author__ = 'unkn0wn'
+    description = (
+        'Science Signaling offers researchers the most up-to-date resource for groundbreaking research and commentary '
+        'in the dynamic field of cellular signaling. From basic science to design of therapeutics and from molecules to '
+        'networks and systems design, this weekly e-resource keeps your researchers, faculty, and students ahead of the curve.'
+    )
+    encoding = 'utf-8'
+    no_javascript = True
+    no_stylesheets = True
+    remove_attributes = ['style', 'height', 'width']
+    masthead_url = 'https://www.science.org/pb-assets/images/logos/signaling-logo-1620488350150.svg'
+    language = 'en'
+    simultaneous_downloads = 1
+    browser_type = 'qt'
+
+    extra_css = '''
+        .news-article__figure__caption {font-size:small; text-align:center;}
+        .core-self-citation, .meta-panel__left-content, .news-article__hero__top-meta {font-size:small;}
+        .contributors, .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'}),
+        dict(name='div', **classes('core-lede contributors core-self-citation')),
+        dict(attrs={'data-core-wrapper':'content'})
+    ]
+
+    remove_tags = [
+        classes('pb-ad news-article__hero__scroller news-article__version-of-story')
+    ]
+
+    recipe_specific_options = {
+        'issue': {
+            'short': 'Enter the Issue Number you want to download\n(Vol/Issue format)',
+            'long': 'For example, 385/6710',
+            'default': 'current'
+        }
+    }
+
+    def preprocess_html(self, soup):
+        for p in soup.findAll(attrs={'role':'paragraph'}):
+            p.name = 'p'
+            p.attrs = {}
+        return soup
+
+    def parse_index(self):
+        issue_url = 'https://www.science.org/toc/signaling/current'
+        d = self.recipe_specific_options.get('issue')
+        if d and isinstance(d, str):
+            issue_url = 'https://www.science.org/toc/signaling/' + d
+
+        soup = self.index_to_soup(issue_url)
+        tme = soup.find(**classes('journal-issue__vol'))
+        if tme:
+            self.timefmt = ' [%s]' % self.tag_to_string(tme).strip().replace('|', ' | ')
+        det = soup.find(attrs={'id':'journal-issue-details'})
+        if det:
+            self.description = self.tag_to_string(det).strip()
+        cov = soup.find(**classes('cover-image__image'))
+        if cov:
+            self.cover_url = absurl(cov.img['src'])
+
+        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\t', url)
+                articles.append({'title': title, 'description':desc, 'url': url})
+            feeds.append((section, articles))
+        return feeds

recipes/scistm.recipe

@@ -0,0 +1,101 @@
+#!/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 scienceadv(BasicNewsRecipe):
+    title = 'Science Translational Medicine'
+    __author__ = 'unkn0wn'
+    description = (
+        'Science Translational Medicine is the leading weekly online journal publishing translational research at the intersection of science, '
+        'engineering and medicine. The goal of Science Translational Medicine is to promote human health by providing a forum for communicating '
+        'the latest research advances from biomedical, translational, and clinical researchers from all established and emerging disciplines relevant '
+        'to medicine. In addition to original research, Science Translational Medicine also publishes Reviews, Editorials, Focus articles, and Viewpoints.'
+    )
+    encoding = 'utf-8'
+    no_javascript = True
+    no_stylesheets = True
+    remove_attributes = ['style', 'height', 'width']
+    masthead_url = 'https://www.science.org/pb-assets/images/logos/stm-logo-1620488350153.svg'
+    language = 'en'
+    simultaneous_downloads = 1
+    browser_type = 'qt'
+
+    extra_css = '''
+        .news-article__figure__caption {font-size:small; text-align:center;}
+        .core-self-citation, .meta-panel__left-content, .news-article__hero__top-meta {font-size:small;}
+        .contributors, .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'}),
+        dict(name='div', **classes('core-lede contributors core-self-citation')),
+        dict(attrs={'data-core-wrapper':'content'})
+    ]
+
+    remove_tags = [
+        classes('pb-ad news-article__hero__scroller news-article__version-of-story')
+    ]
+
+    recipe_specific_options = {
+        'issue': {
+            'short': 'Enter the Issue Number you want to download\n(Vol/Issue format)',
+            'long': 'For example, 385/6710',
+            'default': 'current'
+        }
+    }
+
+    def preprocess_html(self, soup):
+        for p in soup.findAll(attrs={'role':'paragraph'}):
+            p.name = 'p'
+            p.attrs = {}
+        return soup
+
+    def parse_index(self):
+        issue_url = 'https://www.science.org/toc/stm/current'
+        d = self.recipe_specific_options.get('issue')
+        if d and isinstance(d, str):
+            issue_url = 'https://www.science.org/toc/stm/' + d
+
+        soup = self.index_to_soup(issue_url)
+        tme = soup.find(**classes('journal-issue__vol'))
+        if tme:
+            self.timefmt = ' [%s]' % self.tag_to_string(tme).strip().replace('|', ' | ')
+        det = soup.find(attrs={'id':'journal-issue-details'})
+        if det:
+            self.description = self.tag_to_string(det).strip()
+        cov = soup.find(**classes('cover-image__image'))
+        if cov:
+            self.cover_url = absurl(cov.img['src'])
+
+        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\t', url)
+                articles.append({'title': title, 'description':desc, 'url': url})
+            feeds.append((section, articles))
+        return feeds