Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update The Atlantic

Browse Source 
Merge branch 'patch-8' of https://github.com/jfhutson/calibre
This commit is contained in:
Kovid Goyal 2017-02-18 09:53:38 +05:30
commit 7261b9fbc4
1 changed files with 52 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

66
recipes/atlantic.recipe
View File

@ -12,7 +12,9 @@ from calibre.web.feeds.news import BasicNewsRecipe
def classes(classes): def classes(classes):
q = frozenset(classes.split(' ')) q = frozenset(classes.split(' '))
return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}) return dict(
attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}
)
class TheAtlantic(BasicNewsRecipe): class TheAtlantic(BasicNewsRecipe):
@ -26,18 +28,43 @@ class TheAtlantic(BasicNewsRecipe):
keep_only_tags = [ keep_only_tags = [
classes( classes(
'article-header article-body article-magazine article-cover-content lead-img'), 'article-header article-body article-magazine article-cover-content article-cover-extra lead-img '
),
{
'name': ['img']
},
] ]
remove_tags = [ remove_tags = [
{'name': ['meta', 'link', 'noscript']}, classes(
{'attrs': {'class': ['offset-wrapper', 'ad-boxfeatures-wrapper']}}, 'social-kit-top letter-writer-info callout secondary-byline embed-wrapper offset-wrapper boxtop-most-popular'
{'attrs': {'class': lambda x: x and 'article-tools' in x}}, ),
{'src': lambda x: x and 'spotxchange.com' in x}, {
'name': ['meta', 'link', 'noscript', 'aside', 'h3']
},
{
'attrs': {
'class': ['offset-wrapper', 'boxtop-most-popular']
}
},
{
'attrs': {
'class': lambda x: x and 'article-tools' in x
}
},
{
'src': lambda x: x and 'spotxchange.com' in x
},
] ]
remove_tags_after = classes('article-body') remove_tags_after = classes('article-body')
no_stylesheets = True no_stylesheets = True
remove_attributes = ['style'] remove_attributes = ['style']
extra_css = '''
.credit { text-align: right; font-size: 75%; display: block }
.figcaption { font-size: 75% }
.caption { font-size: 75% }
.lead-img { display: block }
'''
def get_browser(self): def get_browser(self):
br = BasicNewsRecipe.get_browser(self) br = BasicNewsRecipe.get_browser(self)
@ -45,14 +72,18 @@ class TheAtlantic(BasicNewsRecipe):
return br return br
def preprocess_raw_html(self, raw, url): def preprocess_raw_html(self, raw, url):
return html.tostring(html5lib.parse(raw, treebuilder='lxml', namespaceHTMLElements=False), method='html', encoding=unicode) return html.tostring(
html5lib.parse(raw, treebuilder='lxml', namespaceHTMLElements=False),
method='html',
encoding=unicode
)
def print_version(self, url): def print_version(self, url):
return url + '?single_page=true' return url + '?single_page=true'
def preprocess_html(self, soup): def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src': True}): for img in soup.findAll('img', attrs={'data-srcset': True}):
img['src'] = img['data-src'] img['src'] = img['data-srcset'].split()[0]
return soup return soup
def parse_index(self): def parse_index(self):
@ -79,21 +110,28 @@ class TheAtlantic(BasicNewsRecipe):
if url.startswith('/'): if url.startswith('/'):
url = 'http://www.theatlantic.com' + url url = 'http://www.theatlantic.com' + url
li = a.findParent( li = a.findParent(
'li', attrs={'class': lambda x: x and 'article' in x.split()}) 'li',
attrs={'class': lambda x: x and 'article' in x.split()}
)
desc = '' desc = ''
dek = li.find( dek = li.find(
attrs={'class': lambda x: x and 'dek' in x.split()}) attrs={'class': lambda x: x and 'dek' in x.split()}
)
if dek is not None: if dek is not None:
desc += self.tag_to_string(dek) desc += self.tag_to_string(dek)
byline = li.find( byline = li.find(
attrs={'class': lambda x: x and 'byline' in x.split()}) attrs={'class': lambda x: x and 'byline' in x.split()}
)
if byline is not None: if byline is not None:
desc += ' -- ' + self.tag_to_string(byline) desc += ' -- ' + self.tag_to_string(byline)
self.log('\t', title, 'at', url) self.log('\t', title, 'at', url)
if desc: if desc:
self.log('\t\t', desc) self.log('\t\t', desc)
current_articles.append( current_articles.append({
{'title': title, 'url': url, 'description': desc}) 'title': title,
'url': url,
'description': desc
})
if current_articles: if current_articles:
feeds.append((current_section, current_articles)) feeds.append((current_section, current_articles))
return feeds return feeds