Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Spectator Magazine

Browse Source
This commit is contained in:
Kovid Goyal 2022-11-03 21:33:30 +05:30
parent 58e506d0cd
commit 9686fb190d
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 20 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
recipes/spectator_magazine.recipe
View File

@ -1,4 +1,4 @@
from calibre.web.feeds.news import BasicNewsRecipe, prefixed_classes
from calibre.web.feeds.news import BasicNewsRecipe, classes
def absurl(url):
@ -21,20 +21,18 @@ class spectator(BasicNewsRecipe):
resolve_internal_links = True
extra_css = '''
[class^="ContentPageFooterAuthor_author"] {font-size:small;}
.author-bio {font-size:small;}
#fig-c {text-align:center; font-size:small;}
blockquote, em {color:#404040;}
'''
keep_only_tags = [
prefixed_classes(
'ContentPageHeader_main ContentPageHero_container ContentPageBody_body__container__'
' ContentPageFooterAuthor_author__'),
classes(
'entry-header__heading entry-header__thumbnail entry-content__wrapper author-bio'),
]
remove_tags = [
dict(name=('aside', 'iframe')),
prefixed_classes('ContentPageBody_measure__ ContentPageAuthor_author__pic')
classes('entry-header__author entry-header__meta entry-meta insert--most-popular')
]
def preprocess_html(self, soup):
@ -43,21 +41,18 @@ class spectator(BasicNewsRecipe):
h2.name = 'h4'
for fc in soup.findAll('figcaption'):
fc['id'] = 'fig-c'
for fig in soup.findAll('figure'):
for nos in fig.findAll('noscript'):
nos.name = 'span'
return soup
def parse_index(self):
soup = self.index_to_soup('https://www.spectator.co.uk/magazine')
self.cover_url = soup.find(**prefixed_classes(
'MagazinePage_spectator-magazine__image-and-subsections__')).img['src']
issue = self.tag_to_string(soup.find(**prefixed_classes(
'MagazinePage_spectator-magazine-issue__title__'))).strip()
self.timefmt = ' (' + issue + ') [' + self.tag_to_string(soup.find(**prefixed_classes(
'MagazinePage_spectator-magazine-issue__date__'))).strip() + ']'
self.cover_url = soup.find(**classes(
'magazine-header__container')).img['src'].split('?')[0]
issue = self.tag_to_string(soup.find(**classes(
'magazine-header__title'))).strip()
self.timefmt = ' (' + issue + ') [' + self.tag_to_string(soup.find(**classes(
'magazine-header__date'))).strip() + ']'
self.log('Downloading Issue: ', self.timefmt)
nav_div = soup.find('ul', **prefixed_classes('Tabs_spectator-table-of-contents__'))
nav_div = soup.find('ul', **classes('archive-entry__nav-list'))
section_list = []
for x in nav_div.findAll(['a']):
@ -78,30 +73,23 @@ class spectator(BasicNewsRecipe):
def articles_from_soup(self, soup):
ans = []
for div in soup.findAll('div', **prefixed_classes(
'MagazineContent_spectator-magazine-content__article-card___'
for div in soup.findAll('div', **classes(
'mosaic__tile mosaic__tile--lead-up'
)):
a = div.find('a', attrs={
'href': lambda x: x and x.startswith(('/article/', '/illustration/', '/poem/'))})
if a is None:
continue
a = div.find('a', href=True, attrs={'class':'article__title-link'})
url = absurl(a['href'])
title = self.tag_to_string(div.find('div', **prefixed_classes(
'ArticleCard_spectator-article-card__headline__'))).strip()
teaser = div.find('p', **prefixed_classes('ArticleCard_spectator-article-card__media-teaser__'))
title = self.tag_to_string(a).strip()
teaser = div.find('p', **classes('article__excerpt-text'))
desc = ''
if teaser:
desc = self.tag_to_string(teaser).strip()
obj = div.find('object')
obj = div.find('a', **classes('article__author article__author--link'))
if obj:
desc = self.tag_to_string(obj).strip() + ' | ' + desc
sec = div.findParent('div').find('a', attrs={'href': lambda x: x and x.startswith('/magazines/')})
sec = div.findParent('div').find('a', attrs={'class': 'magazine-issue__entry-link'})
if sec:
desc = self.tag_to_string(sec).strip() + ' | ' + desc
self.log('\t', title, '\n\t', desc, '\n\t\t', url)
ans.append({
'title': title,
'description':desc,
'url': url})
ans.append({'title': title, 'description':desc, 'url': url})
return ans