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

Update 1843

Browse Source 
Fixes #1886805 [Recipes: 1843.recipe not work well now](https://bugs.launchpad.net/calibre/+bug/1886805)
This commit is contained in:
Kovid Goyal 2020-07-08 18:49:24 +05:30
parent 869d429cb3
commit c52574c4d9
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 23 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
recipes/1843.recipe
View File

@ -19,49 +19,35 @@ class E1843(BasicNewsRecipe):
language = 'en_GB' language = 'en_GB'
no_stylesheets = True no_stylesheets = True
remove_javascript = True remove_javascript = True
oldest_article = 365
encoding = 'utf-8' encoding = 'utf-8'
# feeds = [
# 'https://www.1843magazine.com/rss/content',
# ]
keep_only_tags = [ keep_only_tags = [
dict(name='h1', attrs={'class': lambda x: x and 'title' in x.split()}), dict(id='content')
classes('field-name-field-rubric-summary article-header__overlay-main-image meta-info__author article__body'), ]
remove_tags = [
classes('advert ad ds-share-list article__wordmark related-articles newsletter-signup')
] ]
def parse_index(self): def parse_index(self):
soup = self.index_to_soup('https://www.1843magazine.com') soup = self.index_to_soup('https://economist.com/1843/')
a = soup.find(text='Print edition').parent
soup = self.index_to_soup(a['href'])
h1 = soup.find(**classes('cover-image__main'))
self.timefmt = ' [%s]' % self.tag_to_string(h1)
img = soup.find(**classes('cover-image__image')).find('img')
self.cover_url = img['src']
ans = [] ans = []
current_section = articles = None
for div in soup.findAll(**classes('field-name-field-header node-article')): for a in soup.findAll(**classes('headline-link')):
if 'field-header' in ''.join(div['class']): url = a['href']
if current_section and articles: if url.startswith('/'):
ans.append((current_section, articles)) url = 'https://economist.com' + url
current_section = self.tag_to_string(div) title = self.tag_to_string(a)
self.log(current_section) self.log(title, ' at ', url)
articles = [] desc = ''
else: d = a.parent.findNextSibling(itemprop='description')
a = div.find('a', href=True) if d is not None:
title = self.tag_to_string(a) desc = self.tag_to_string(d)
url = a['href'] ans.append({'title': title, 'url': url, 'description': desc})
self.log('\t', title, ' at ', url) return [('Articles', ans)]
desc = ''
r = div.find(**classes('article-rubric'))
if r is not None:
desc = self.tag_to_string(r)
articles.append(
{'title': title, 'url': url, 'description': desc})
if current_section and articles: def postprocess_html(self, soup, *a):
ans.append((current_section, articles)) main = soup.find(id='content')
return ans header = soup.find(**classes('article__header'))
header.extract()
main.insert(0, header)
return soup