mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-10-25 07:48:55 -04:00
118 lines
4.1 KiB
Python
118 lines
4.1 KiB
Python
#!/usr/bin/env python
|
|
|
|
__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_US'
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
encoding = 'utf-8'
|
|
extra_css = '''
|
|
.nym-image-figcaption,
|
|
.bylines, .rubric,
|
|
.clay-paragraph_prologue,
|
|
.secondary-area-caption-credits {
|
|
font-size: small;
|
|
}
|
|
'''
|
|
keep_only_tags = [
|
|
dict(name='article', attrs={'class': lambda x: x and 'article' in x.split()})
|
|
]
|
|
remove_tags = [
|
|
dict(name=['svg', 'iframe']),
|
|
classes(
|
|
'related-stories start-discussion newsletter-flex-text package-toc '
|
|
'comments-link tags related secondary-area author-photo error-pop-up'
|
|
),
|
|
dict(id=['minibrowserbox', 'article-related', 'article-tools']),
|
|
]
|
|
remove_attributes = ['style', 'height', 'width', 'srcset']
|
|
|
|
recipe_specific_options = {
|
|
'date': {
|
|
'short': 'The date of the edition to download (YYYY-MM-DD format)',
|
|
'long': 'For example, 2024-07-01',
|
|
}
|
|
}
|
|
|
|
def nymag_get_index(self):
|
|
issue_url = 'https://nymag.com/maglinks/nym-home-05'
|
|
d = self.recipe_specific_options.get('date')
|
|
if d and isinstance(d, str):
|
|
issue_url = 'https://nymag.com/magazine/toc/' + d + '.html'
|
|
return self.index_to_soup(issue_url)
|
|
|
|
def parse_index(self):
|
|
soup = self.nymag_get_index()
|
|
cdiv = soup.find(**classes('magazine-toc-cover-image-wrap'))
|
|
if cdiv is not None:
|
|
for source in cdiv.findAll('source', srcset=True):
|
|
self.cover_url = source['srcset'].split()[0]
|
|
self.log('Cover:', self.cover_url)
|
|
break
|
|
feeds = []
|
|
if cover_art := soup.find(**classes('magazine-toc-cover-text')):
|
|
a = cover_art.find('a', **classes('headline-link'))
|
|
c_url = a['href']
|
|
c_title = self.tag_to_string(
|
|
a.find(**classes('magazine-toc-cover-headline'))
|
|
).strip()
|
|
c_desc = self.tag_to_string(
|
|
a.find(**classes('magazine-toc-cover-teaser'))
|
|
).strip()
|
|
self.log('Cover Story', '\n\t', c_title, c_url)
|
|
feeds.append((
|
|
'Cover Story',
|
|
[{'title': c_title, 'url': c_url, 'description': c_desc}],
|
|
))
|
|
for div in soup.findAll(attrs={'data-editable': 'settingTitle'}):
|
|
section = self.tag_to_string(div).strip().capitalize()
|
|
articles = []
|
|
self.log(section)
|
|
ul = div.findNextSibling('ul')
|
|
for li in ul.findAll('li'):
|
|
a = li.find(href=True, **classes('article-link'))
|
|
if a is None:
|
|
continue
|
|
url = a['href']
|
|
h3 = li.find('h3')
|
|
title = self.tag_to_string(h3)
|
|
desc = ''
|
|
teaser = h3.findNextSibling(**classes('teaser'))
|
|
if teaser is not None:
|
|
desc = self.tag_to_string(teaser)
|
|
self.log('\t', title, url)
|
|
articles.append({'title': title, 'url': url, 'description': desc})
|
|
if articles:
|
|
feeds.append((section, articles))
|
|
|
|
return feeds
|
|
|
|
def preprocess_html(self, soup):
|
|
if lede := soup.findAll(
|
|
'div', attrs={'class': lambda x: x and 'lede-image-wrapper' in x.split()}
|
|
):
|
|
if len(lede) > 1:
|
|
lede[1].extract()
|
|
for img in soup.findAll('img', attrs={'data-src': True}):
|
|
img['src'] = img['data-src']
|
|
for h2 in soup.findAll(['h2', 'h3']):
|
|
h2.name = 'h4'
|
|
return soup
|