mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-08 02:34:06 -04:00
Remove non-working Newsweek recipe
This commit is contained in:
parent
e73312ffb8
commit
b1a00d0b52
Binary file not shown.
Before Width: | Height: | Size: 8.7 KiB |
@ -1,107 +0,0 @@
|
||||
#!/usr/bin/env python
|
||||
# vim:fileencoding=utf-8
|
||||
# License: GPLv3 Copyright: 2015, Kovid Goyal <kovid at kovidgoyal.net>
|
||||
|
||||
import json
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from collections import defaultdict
|
||||
|
||||
BASE = 'https://www.newsweek.com'
|
||||
|
||||
|
||||
def href_to_url(a, add_piano=False):
|
||||
return BASE + a.get('href') + ('?piano_d=1' if add_piano else '')
|
||||
|
||||
|
||||
def class_sels(*args):
|
||||
q = set(args)
|
||||
return dict(attrs={'class': lambda x: x and set(x.split()).intersection(q)})
|
||||
|
||||
|
||||
class Newsweek(BasicNewsRecipe):
|
||||
|
||||
title = 'Newsweek'
|
||||
__author__ = 'Kovid Goyal'
|
||||
description = 'Weekly news and current affairs in the US'
|
||||
language = 'en'
|
||||
encoding = 'utf-8'
|
||||
no_stylesheets = True
|
||||
requires_version = (1, 40, 0)
|
||||
|
||||
keep_only_tags = [
|
||||
dict(id='block-nw-magazine-article-header'),
|
||||
class_sels('article-header', 'article-body')
|
||||
]
|
||||
remove_tags = [
|
||||
dict(name=['aside', 'meta', 'source']),
|
||||
class_sels(
|
||||
'block-openadstream', 'block-ibtmedia-social', 'issue-next',
|
||||
'most-popular', 'ibt-media-stories', 'user-btn-group',
|
||||
'trial-link', 'trc_related_container',
|
||||
'block-ibtmedia-top-stories', 'videocontent', 'newsletter-signup',
|
||||
'in-text-slideshows', 'content-correction', 'article-navigation'
|
||||
),
|
||||
dict(id=['taboola-below-main-column', 'piano-root',
|
||||
'block-nw-magazine-magazine-more-from-issue']),
|
||||
]
|
||||
remove_attributes = ['style']
|
||||
|
||||
def parse_index(self):
|
||||
root = self.index_to_soup(
|
||||
'https://www.newsweek.com/archive', as_tree=True)
|
||||
li = root.xpath(
|
||||
'//ul[contains(@class, "magazine-archive-items")]/li')[0]
|
||||
a = li.xpath('descendant::a[@href]')[0]
|
||||
url = href_to_url(a, add_piano=True)
|
||||
self.timefmt = self.tag_to_string(a)
|
||||
img = li.xpath('descendant::a[@href]//source[@type="image/jpeg"]/@srcset')[0]
|
||||
self.cover_url = img.partition('?')[0]
|
||||
self.log('Found cover url:', self.cover_url)
|
||||
root = self.index_to_soup(url, as_tree=True)
|
||||
features = []
|
||||
for article in root.xpath('//div[@class="magazine-features"]//article'):
|
||||
a = article.xpath('descendant::a[@class="article-link"]')[0]
|
||||
title = self.tag_to_string(a)
|
||||
url = href_to_url(a)
|
||||
desc = ''
|
||||
s = article.xpath('descendant::div[@class="summary"]')
|
||||
if s:
|
||||
desc = self.tag_to_string(s[0])
|
||||
features.append({'title': title, 'url': href_to_url(a), 'description': desc})
|
||||
self.log(title, url)
|
||||
|
||||
index = [('Features', features)]
|
||||
sections = defaultdict(list)
|
||||
for widget in ('editor-pick',):
|
||||
self.parse_widget(widget, sections)
|
||||
for k in sorted(sections):
|
||||
index.append((k, sections[k]))
|
||||
return index
|
||||
|
||||
def parse_widget(self, widget, sections):
|
||||
raw = self.index_to_soup('https://d.newsweek.com/json/' + widget, raw=True)
|
||||
data = json.loads(raw)['items']
|
||||
for item in data:
|
||||
title = item['title']
|
||||
url = BASE + item['link']
|
||||
self.log(title, url)
|
||||
sections[item['label']].append(
|
||||
{
|
||||
'title': title,
|
||||
'url': url,
|
||||
'description': item['description'],
|
||||
})
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
# Parallax images in the articles are loaded as background images
|
||||
# on <span> tags. Convert them to normal images.
|
||||
for span in soup.findAll('span', attrs={'class': lambda x: x and 'parallax' in x.split()}):
|
||||
s = span.find(style=True)
|
||||
if s is not None:
|
||||
url = s['style'].partition('(')[-1][:-1]
|
||||
s['style'] = 'display: block'
|
||||
s.name = 'img'
|
||||
s['src'] = url
|
||||
for img in soup.findAll('img', attrs={'data-src': True}):
|
||||
img['src'] = img['data-src']
|
||||
return soup
|
Loading…
x
Reference in New Issue
Block a user