Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of https://github.com/unkn0w7n/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2023-09-17 07:31:05 +05:30
commit a766370f4e
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 12 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
recipes/bloomberg-business-week.recipe
View File

@ -102,31 +102,27 @@ class Bloomberg(BasicNewsRecipe):
self.log('Downloading ', edition) self.log('Downloading ', edition)
self.cover_url = bw.find('img')['src'].replace('25x19', '600x800') self.cover_url = bw.find('img')['src'].replace('25x19', '600x800')
soup = self.index_to_soup(edition) soup = self.index_to_soup(edition)
timefmt = soup.find(**classes('section-front-header-module__title')) if timefmt := soup.find(attrs={'class':lambda x: x and x.startswith('styles_MagazineTitle__')}):
if timefmt: self.timefmt = ' [' + (self.tag_to_string(timefmt).replace(' Issue', '')).strip() + ']'
self.timefmt = ' [' + (self.tag_to_string(timefmt).replace('Issue', '')).strip() + ']'
feeds = [] feeds = []
for div in soup.findAll('div', attrs={'class':'story-list-module__info'}): for div in soup.findAll(attrs={'class':lambda x: x and x.startswith(
h3 = div.find('h3', attrs={'class':'story-list-module__title'}) ('styles_MagazineFeatures__', 'styles_MagazineStoryList__')
)}):
h3 = div.find(attrs={'class':lambda x: x and x.startswith(
('styles_featuresTitle__', 'styles_magazineSectionTitle__')
)})
sec = self.tag_to_string(h3) sec = self.tag_to_string(h3)
self.log(sec) self.log(sec)
articles = [] articles = []
for art in div.findAll('article'): for art in div.findAll(attrs={'data-component':'headline'}):
a = art.find('a', **classes('story-list-story__info__headline-link')) a = art.find('a', href=True)
url = a['href'] url = a['href']
if url.startswith('http') is False: if url.startswith('http') is False:
url = 'https://www.bloomberg.com' + a['href'] url = 'https://www.bloomberg.com' + a['href']
title = self.tag_to_string(a) title = self.tag_to_string(a)
desc = '' articles.append({'title': title, 'url': url})
sum = art.find(**classes('story-list-story__info__summary')) self.log('\t', title, '\n\t\t', url)
if sum:
desc = self.tag_to_string(sum).strip()
by = art.find(**classes('story-list-story__info__byline'))
if by:
desc = self.tag_to_string(by).strip() + ' | ' + desc
articles.append({'title': title, 'url': url, 'description': desc})
self.log('\t', title, '\n\t', desc, '\n\t\t', url)
if articles: if articles:
feeds.append((sec, articles)) feeds.append((sec, articles))
return feeds return feeds