GwR wip

resources/recipes/nytimes.recipe

@@ -79,6 +79,7 @@ class NYTimes(BasicNewsRecipe):
                             'doubleRule',
                             'dottedLine',
                             'entry-meta',
+                            'entry-response module',
                             'icon enlargeThis',
                             'leftNavTabs',
                             'module box nav',
@@ -110,6 +111,7 @@ class NYTimes(BasicNewsRecipe):
                             'navigation',
                             'portfolioInline',
                             'relatedArticles',
+                            'respond',
                             'side_search',
                             'side_index',
                             'side_tool',

resources/recipes/nytimes_sub.recipe

@@ -66,6 +66,7 @@ class NYTimes(BasicNewsRecipe):
                             'doubleRule',
                             'dottedLine',
                             'entry-meta',
+                            'entry-response module',
                             'icon enlargeThis',
                             'leftNavTabs',
                             'module box nav',
@@ -97,6 +98,7 @@ class NYTimes(BasicNewsRecipe):
                             'navigation',
                             'portfolioInline',
                             'relatedArticles',
+                            'respond',
                             'side_search',
                             'side_index',
                             'side_tool',
@@ -417,12 +419,11 @@ class NYTimes(BasicNewsRecipe):
 
         return soup
 
-    def postprocess_book(self, oeb, opts, log) :
+    def populate_article_metadata(self,article,soup,first):
-        print "\npostprocess_book()\n"
+        '''
-
+        Extract author and description from article, add to article metadata
-        def extract_byline(href) :
+        '''
-            # <meta name="byline" content=
+        def extract_author(soup):
-            soup = BeautifulSoup(str(oeb.manifest.hrefs[href]))
             byline = soup.find('meta',attrs={'name':['byl','CLMST']})
             if byline :
                 author = byline['content']
@@ -432,50 +433,32 @@ class NYTimes(BasicNewsRecipe):
                 if byline:
                     author = byline.renderContents()
                 else:
-                    print "couldn't find byline in %s" % href
                     print soup.prettify()
                     return None
-            # Kill commas - Kindle switches to '&'
+            return author
-            return re.sub(',','',author)
 
-        def extract_description(href) :
+        def extract_description(soup):
-            soup = BeautifulSoup(str(oeb.manifest.hrefs[href]))
             description = soup.find('meta',attrs={'name':['description','description ']})
             if description :
-#                print repr(description['content'])
-#                print self.massageNCXText(description['content'])
                 return self.massageNCXText(description['content'])
             else:
                 # Take first paragraph of article
-                articleBody = soup.find('div',attrs={'id':'articleBody'})
+                articlebody = soup.find('div',attrs={'id':'articlebody'})
-                if not articleBody:
+                if not articlebody:
                     # Try again with class instead of id
-                    articleBody = soup.find('div',attrs={'class':'articleBody'})
+                    articlebody = soup.find('div',attrs={'class':'articlebody'})
-                    if not articleBody:
+                    if not articlebody:
-                        print 'postprocess_book.extract_description(): Did not find <div id="articleBody">:'
+                        print 'postprocess_book.extract_description(): Did not find <div id="articlebody">:'
                         print soup.prettify()
                         return None
-                paras = articleBody.findAll('p')
+                paras = articlebody.findAll('p')
                 for p in paras:
                     if p.renderContents() > '' :
                         return self.massageNCXText(self.tag_to_string(p,use_alt=False))
                 return None
 
-        # Method entry point here
+        article.author = extract_author(soup)
-        # Single section toc looks different than multi-section tocs
+        article.summary = article.text_summary = extract_description(soup)
-        if oeb.toc.depth() == 2 :
-            for article in oeb.toc :
-                if article.author is None :
-                    article.author = extract_byline(article.href)
-                if article.description is None :
-                    article.description = extract_description(article.href).decode('utf-8')
-        elif oeb.toc.depth() == 3 :
-            for section in oeb.toc :
-                for article in section :
-                    if article.author is None :
-                        article.author = extract_byline(article.href)
-                    if article.description is None :
-                        article.description = extract_description(article.href)
 
     def strip_anchors(self,soup):
         paras = soup.findAll(True)

src/calibre/web/feeds/news.py

@@ -752,7 +752,8 @@ class BasicNewsRecipe(Recipe):
 
 
 
-    def feed2index(self, feed):
+    def feed2index(self, f, feeds):
+        feed = feeds[f]
         if feed.image_url is not None: # Download feed image
             imgdir = os.path.join(self.output_dir, 'images')
             if not os.path.isdir(imgdir):
@@ -808,7 +809,8 @@ class BasicNewsRecipe(Recipe):
 
             templ = templates.TouchscreenFeedTemplate()
             css = touchscreen_css + '\n\n' + (self.extra_css if self.extra_css else '')
-        return templ.generate(feed, self.description_limiter,
+
+        return templ.generate(f, feeds, self.description_limiter,
                               extra_css=css).render(doctype='xhtml')
 
 
@@ -951,7 +953,7 @@ class BasicNewsRecipe(Recipe):
         #feeds.restore_duplicates()
 
         for f, feed in enumerate(feeds):
-            html = self.feed2index(feed)
+            html = self.feed2index(f,feeds)
             feed_dir = os.path.join(self.output_dir, 'feed_%d'%f)
             with open(os.path.join(feed_dir, 'index.html'), 'wb') as fi:
                 fi.write(html)

src/calibre/web/feeds/templates.py

@@ -107,6 +107,8 @@ class TouchscreenNavBarTemplate(Template):
         align = 'center' if center else 'left'
         navbar = DIV(CLASS('calibre_navbar', 'calibre_rescale_100',
             style='text-align:'+align))
+
+        if False:
             if bottom:
                 navbar.append(DIV(style="border-top:1px solid gray;border-bottom:1em solid white"))
                 text = 'This article was downloaded by '
@@ -128,11 +130,43 @@ class TouchscreenNavBarTemplate(Template):
             navbar.append(A('Section Menu', href=href))
             href = '%s../../index.html#feed_%d'%(prefix, feed)
             navbar.iterchildren(reversed=True).next().tail = ' | '
-        navbar.append(A('Main Menu', href=href))
+            navbar.append(A("Sections", href=href))
             if art > 0 and not bottom:
                 href = '%s../article_%d/index.html'%(prefix, art-1)
                 navbar.iterchildren(reversed=True).next().tail = ' | '
                 navbar.append(A('Previous', href=href))
+        else:
+            if bottom:
+                navbar.append(DIV(style="border-top:1px solid gray;border-bottom:1em solid white"))
+                text = 'This article was downloaded by '
+                p = PT(text, STRONG(__appname__), A(url, href=url), style='text-align:left')
+                p[0].tail = ' from '
+                navbar.append(p)
+                navbar.append(BR())
+                navbar.append(BR())
+            else:
+                # | Previous
+                if art > 0 and not bottom:
+                    href = '%s../article_%d/index.html'%(prefix, art-1)
+                    navbar.text = '| '
+                    navbar.append(A('Previous', href=href))
+
+            # | Section | Main |
+            href = '%s../index.html#article_%d'%(prefix, art)
+            if art > 0:
+                navbar.iterchildren(reversed=True).next().tail = ' | '
+            navbar.append(A('Articles', href=href))
+            href = '%s../../index.html#feed_%d'%(prefix, feed)
+            navbar.iterchildren(reversed=True).next().tail = ' | '
+            navbar.append(A("Sections", href=href))
+
+            # | Next
+            next = 'feed_%d'%(feed+1) if art == number_of_articles_in_feed - 1 \
+                    else 'article_%d'%(art+1)
+            up = '../..' if art == number_of_articles_in_feed - 1 else '..'
+            href = '%s%s/%s/index.html'%(prefix, up, next)
+            navbar.iterchildren(reversed=True).next().tail = ' | '
+            navbar.append(A('Next', href=href))
 
         navbar.iterchildren(reversed=True).next().tail = ' | '
         if not bottom:
@@ -200,7 +234,8 @@ class TouchscreenIndexTemplate(Template):
 
 class FeedTemplate(Template):
 
-    def _generate(self, feed, cutoff, extra_css=None, style=None):
+    def _generate(self, f, feeds, cutoff, extra_css=None, style=None):
+        feed = feeds[f]
         head = HEAD(TITLE(feed.title))
         if style:
             head.append(STYLE(style, type='text/css'))
@@ -250,7 +285,41 @@ class FeedTemplate(Template):
 
 class TouchscreenFeedTemplate(Template):
 
-    def _generate(self, feed, cutoff, extra_css=None, style=None):
+    def _generate(self, f, feeds, cutoff, extra_css=None, style=None):
+
+        def trim_title(title,clip=15):
+            if len(title)>clip:
+                tokens = title.split(' ')
+                new_title_tokens = []
+                new_title_len = 0
+                for token in tokens:
+                    if len(token) + new_title_len < clip:
+                        new_title_tokens.append(token)
+                        new_title_len += len(token) + 1
+                    else:
+                        new_title_tokens.append('...')
+                        title = ' '.join(new_title_tokens)
+                        break
+            return title
+
+        feed = feeds[f]
+
+        # Construct the navbar
+        navbar = DIV('| ', CLASS('calibre_navbar', 'calibre_rescale_100'),style='text-align:center')
+        if f > 0:
+            link = A(trim_title(feeds[f-1].title), href = '../feed_%d/index.html' % int(f-1))
+            link.tail = ' |'
+            navbar.append(link)
+
+        link = A("Sections", href="../index.html")
+        link.tail = ' |'
+        navbar.append(link)
+        if f < len(feeds)-1:
+            link = A(trim_title(feeds[f+1].title), href = '../feed_%d/index.html' % int(f+1))
+            link.tail = ' |'
+            navbar.append(link)
+
+        # Build the page
         head = HEAD(TITLE(feed.title))
         if style:
             head.append(STYLE(style, type='text/css'))
@@ -262,6 +331,7 @@ class TouchscreenFeedTemplate(Template):
                 DIV(style="border-top:1px solid gray;border-bottom:1em solid white")
                 )
         body.append(div)
+
         if getattr(feed, 'image', None):
             div.append(DIV(IMG(
                 alt = feed.image_alt if feed.image_alt else '',
@@ -280,7 +350,6 @@ class TouchscreenFeedTemplate(Template):
                 continue
             tr = TR()
 
-            if True:
             div_td = DIV(
                     A(article.title, CLASS('summary_headline','calibre_rescale_120',
                                     href=article.url)),
@@ -292,29 +361,10 @@ class TouchscreenFeedTemplate(Template):
                 div_td.append(DIV(cutoff(article.text_summary),
                     CLASS('summary_text', 'calibre_rescale_100')))
             tr.append(TD(div_td))
-            else:
-                td = TD(
-                        A(article.title, CLASS('summary_headline','calibre_rescale_120',
-                                        href=article.url))
-                        )
-                if article.author:
-                    td.append(DIV(article.author,
-                        CLASS('summary_byline', 'calibre_rescale_100')))
-                if article.summary:
-                    td.append(DIV(cutoff(article.text_summary),
-                        CLASS('summary_text', 'calibre_rescale_100')))
-
-                tr.append(td)
 
             toc.append(tr)
         div.append(toc)
-
-        navbar = DIV('| ', CLASS('calibre_navbar', 'calibre_rescale_100'),style='text-align:center')
-        link = A('Up one level', href="../index.html")
-        link.tail = ' |'
-        navbar.append(link)
         div.append(navbar)
-
         self.root = HTML(head, body)
 
 class EmbeddedContent(Template):