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

http -> https

Browse Source
This commit is contained in:
Kovid Goyal 2017-02-17 20:27:24 +05:30
parent 0858d97f82
commit e76d85ccc5
1 changed files with 11 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
recipes/new_yorker.recipe
View File

@ -11,7 +11,7 @@ class NewYorker(BasicNewsRecipe):
title = u'New Yorker Magazine' title = u'New Yorker Magazine'
description = u'Content from the New Yorker website' description = u'Content from the New Yorker website'
masthead_url = 'http://www.newyorker.com/images/elements/print/newyorker_printlogo.gif' masthead_url = 'https://www.newyorker.com/images/elements/print/newyorker_printlogo.gif'
url_list = [] url_list = []
language = 'en' language = 'en'
@ -27,18 +27,18 @@ class NewYorker(BasicNewsRecipe):
needs_subscription = 'optional' needs_subscription = 'optional'
keep_only_tags = [ keep_only_tags = [
dict(itemprop=['headline', 'alternativeHeadline', 'author', 'articleBody']), dict(itemprop=['headline', 'alternativeHeadline', 'author', 'articleBody']),
dict(id=['featured-item']), dict(id=['featured-item', 'article-content']),
] ]
remove_tags = [ remove_tags = [
dict(attrs={'class': lambda x: x and set(x.split()).intersection( dict(attrs={'class': lambda x: x and set(x.split()).intersection(
{'content-ad-wrapper', 'social-hover'})}), {'content-ad-wrapper', 'social-hover', 'background-image'})}),
dict(id=['newsletter-signup']), dict(id=['newsletter-signup']),
dict(name='meta link'.split()),
] ]
def parse_index(self): def parse_index(self):
soup = self.index_to_soup( soup = self.index_to_soup(
'http://www.newyorker.com/magazine?intcid=magazine') 'https://www.newyorker.com/magazine?intcid=magazine')
ph = soup.find( ph = soup.find(
'div', attrs={'class': lambda x: x and 'cover-info' in x.split()}) 'div', attrs={'class': lambda x: x and 'cover-info' in x.split()})
if ph is not None: if ph is not None:
@ -69,11 +69,14 @@ class NewYorker(BasicNewsRecipe):
if p is not None: if p is not None:
desc += '. \n' + self.tag_to_string(p) desc += '. \n' + self.tag_to_string(p)
self.log('Found article:', title) self.log(' ', title)
self.log('\t', url) self.log(' ', url)
self.log('\t', desc) if desc:
self.log(' ', desc)
articles.append({'title': title, 'url': url, 'date': '', articles.append({'title': title, 'url': url, 'date': '',
'description': desc}) 'description': desc})
if articles:
feeds.append((current_section, articles))
return feeds return feeds