| 1 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 2 |
|
| 3 |
CATEGORIES = { |
| 4 |
'smart-news': 'Smart News', |
| 5 |
'history': 'History', |
| 6 |
'science-nature': 'Science', |
| 7 |
'innovation': 'Innovation', |
| 8 |
'arts-culture': 'Arts & Culture', |
| 9 |
'travel': 'Travel', |
| 10 |
'smithsonian-institution': 'At the Smithsonian', |
| 11 |
} |
| 12 |
|
| 13 |
|
| 14 |
class Smithsonian(BasicNewsRecipe): |
| 15 |
title = 'Smithsonian Magazine' |
| 16 |
__author__ = 'Kovid Goyal' |
| 17 |
|
| 18 |
description = 'This magazine chronicles the arts, environment, sciences and popular culture of the times. It is edited for modern, well-rounded individuals with diverse, general interests. With your order, you become a National Associate Member of the Smithsonian. Membership benefits include your subscription to Smithsonian magazine, a personalized membership card, discounts from the Smithsonian catalog, and more.' # noqa: E501 |
| 19 |
language = 'en' |
| 20 |
category = 'news' |
| 21 |
encoding = 'UTF-8' |
| 22 |
keep_only_tags = [classes('article-header'), classes('articleLeft')] |
| 23 |
remove_tags = [ |
| 24 |
dict(name='source'), |
| 25 |
classes( |
| 26 |
'hidden-phone hidden-tablet hidden-desktop slideshow-nav associated-container share-control' |
| 27 |
' widget-article-pixel tag-list recommended-videos comments widget-related-articles in-article-newsletter' |
| 28 |
), |
| 29 |
] |
| 30 |
no_javascript = True |
| 31 |
no_stylesheets = True |
| 32 |
|
| 33 |
def parse_section(self, url): |
| 34 |
soup = self.index_to_soup(url) |
| 35 |
seen = set() |
| 36 |
for article in soup.findAll(attrs={'class': 'content-list-item'}): |
| 37 |
div = article.find(attrs={'class': 'content-list-text'}) |
| 38 |
if div is None: |
| 39 |
continue |
| 40 |
a = div.find('a') |
| 41 |
if a is None: |
| 42 |
continue |
| 43 |
title = self.tag_to_string(a) |
| 44 |
if title in seen: |
| 45 |
continue |
| 46 |
seen.add(title) |
| 47 |
article_url = a['href'] |
| 48 |
if not article_url.startswith('http'): |
| 49 |
article_url = 'https://www.smithsonianmag.com/' + article_url.lstrip('/') |
| 50 |
if '/tag/' in article_url: |
| 51 |
continue |
| 52 |
desc = '' |
| 53 |
p = div.find(attrs={'class': 'dek'}) |
| 54 |
if p is not None: |
| 55 |
desc = self.tag_to_string(p) |
| 56 |
self.log('\t' + title) |
| 57 |
yield {'title': title, 'url': article_url, 'description': desc} |
| 58 |
|
| 59 |
def parse_index(self): |
| 60 |
ans = [] |
| 61 |
for slug, title in CATEGORIES.items(): |
| 62 |
url = 'https://www.smithsonianmag.com/category/' + slug + '/' |
| 63 |
self.log('Parsing section:', title, 'at:', url) |
| 64 |
articles = list(self.parse_section(url)) |
| 65 |
if articles: |
| 66 |
ans.append((title, articles)) |
| 67 |
if self.test and len(ans) >= self.test[0]: |
| 68 |
break |
| 69 |
return ans |