calibre/recipes/new_yorker.recipe
2016-08-15 12:34:57 +05:30

111 lines
3.6 KiB
Python

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
__license__ = 'GPL v3'
from calibre.web.feeds.news import BasicNewsRecipe
from calibre import browser
class NewYorker(BasicNewsRecipe):
title = u'New Yorker Magazine'
description = u'Content from the New Yorker website'
masthead_url = 'http://www.newyorker.com/images/elements/print/newyorker_printlogo.gif'
url_list = []
language = 'en'
__author__ = 'Kovid Goyal'
no_stylesheets = True
timefmt = ' [%b %d]'
encoding = 'utf-8'
extra_css = '''
.byline { font-size:xx-small; font-weight: bold;}
h3 { margin-bottom: 6px; }
.caption { font-size: xx-small; font-style: italic; font-weight: normal; }
'''
needs_subscription = 'optional'
keep_only_tags = [
dict(itemprop=['headline', 'alternativeHeadline', 'author', 'articleBody']),
dict(id=['featured-item']),
]
remove_tags = [
dict(attrs={'class': lambda x: x and set(x.split()).intersection(
{'content-ad-wrapper', 'social-hover'})}),
dict(id=['newsletter-signup']),
]
def parse_index(self):
soup = self.index_to_soup(
'http://www.newyorker.com/magazine?intcid=magazine')
ph = soup.find(
'div', attrs={'class': lambda x: x and 'cover-info' in x.split()})
if ph is not None:
img = ph.find('img', src=True)
if img is not None:
self.cover_url = img['src'].replace('-320.jpg', '.jpg')
articles = []
current_section = 'Current Issue'
feeds = []
for story in soup.findAll(['h5', 'article']):
if story.name == 'h5':
if articles:
feeds.append((current_section, articles))
current_section, articles = self.tag_to_string(story), []
self.log('\nFound section: ' + current_section)
continue
if story['itemtype'] != 'http://schema.org/Article':
continue
h2 = story.find('h2')
url = h2.find('a', href=True)['href']
a = h2.find('a')
title = self.tag_to_string(a)
h3 = h2.findNextSibling('h3')
desc = ''
if h3 is not None:
desc += self.tag_to_string(h3)
p = h2.findNextSibling('p')
if p is not None:
desc += '. \n' + self.tag_to_string(p)
self.log('Found article:', title)
self.log('\t', url)
self.log('\t', desc)
articles.append({'title': title, 'url': url, 'date': '',
'description': desc})
return feeds
def preprocess_html(self, soup):
for img in soup.findAll('img'):
try:
ds = img['data-src']
except KeyError:
continue
if ds:
img['src'] = ds
return soup
def postprocess_html(self, soup, *a):
ab = soup.find(id='articleBody')
if ab is not None:
fi = soup.find(id='featured-item')
if fi is not None:
p = fi.parent
p.insert(len(p) - 2, fi)
return soup
# The New Yorker changes the content it delivers based on cookies, so the
# following ensures that we send no cookies
def get_browser(self, *args, **kwargs):
return self
def clone_browser(self, *args, **kwargs):
return self.get_browser()
def open_novisit(self, *args, **kwargs):
br = browser()
return br.open_novisit(*args, **kwargs)
open = open_novisit