mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
ae92ec6efb
Fixes #1673965 [New York Magazine downs loads most articles as symbols. only a few avaliable and readable](https://bugs.launchpad.net/calibre/+bug/1673965)
85 lines
3.0 KiB
Python
85 lines
3.0 KiB
Python
#!/usr/bin/env python2
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
|
|
'''
|
|
theatlantic.com
|
|
'''
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
def classes(classes):
|
|
q = frozenset(classes.split(' '))
|
|
return dict(attrs={
|
|
'class': lambda x: x and frozenset(x.split()).intersection(q)})
|
|
|
|
|
|
class NewYorkMagazine(BasicNewsRecipe):
|
|
|
|
title = 'New York Magazine'
|
|
__author__ = 'Kovid Goyal'
|
|
description = 'Food, culture, arts and entertainment in New York'
|
|
language = 'en'
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
encoding = 'utf-8'
|
|
recursions = 1
|
|
match_regexps = [r'http://nymag.com/.+/index[0-9]{1,2}.html$']
|
|
keep_only_tags = [
|
|
classes('lede-text headline-primary article-timestamp by-authors'),
|
|
dict(id='main'),
|
|
dict(itemprop='articleBody'),
|
|
]
|
|
remove_tags = [
|
|
classes('related-stories start-discussion'),
|
|
dict(id=['minibrowserbox', 'article-related', 'article-tools'])
|
|
]
|
|
remove_attributes = ['srcset']
|
|
handle_gzip = True
|
|
|
|
PREFIX = 'http://nymag.com'
|
|
|
|
def nymag_get_index(self):
|
|
return self.index_to_soup('http://nymag.com/includes/tableofcontents.htm')
|
|
|
|
def parse_index(self):
|
|
soup = self.nymag_get_index()
|
|
self.cover_url = soup.find(attrs={'class': 'cover'}).find('img',
|
|
src=True).get('src')
|
|
feeds = []
|
|
current_section = 'Cover Story'
|
|
current_articles = []
|
|
for h in soup.findAll(['h4', 'h5']):
|
|
if h.name == 'h4':
|
|
if current_section and current_articles:
|
|
feeds.append((current_section, current_articles))
|
|
current_section = self.tag_to_string(h)
|
|
self.log('\tFound section:', current_section)
|
|
current_articles = []
|
|
elif h.name == 'h5':
|
|
title = self.tag_to_string(h)
|
|
a = h.find('a', href=True)
|
|
if a is not None:
|
|
url = a.get('href')
|
|
if url.startswith('/'):
|
|
url = self.PREFIX + url
|
|
if title and url:
|
|
self.log('\t\tFound article:', title)
|
|
self.log('\t\t\t', url)
|
|
desc = ''
|
|
p = h.findNextSibling('p')
|
|
if p is not None:
|
|
desc = self.tag_to_string(p)
|
|
self.log('\t\t\t', desc)
|
|
current_articles.append({'title': title, 'url': url,
|
|
'date': '', 'description': desc})
|
|
return feeds
|
|
|
|
def postprocess_html(self, soup, first):
|
|
for x in soup.findAll(attrs={'class': 'page-navigation'}):
|
|
x.extract()
|
|
if not first:
|
|
for x in soup.findAll(attrs={'class': 'header-spacing'}):
|
|
x.extract()
|
|
return soup
|