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 Entrepreneur Magazine

Browse Source 
Fixes #1945569 [Fetching news from Entrepreneur Magazine fails](https://bugs.launchpad.net/calibre/+bug/1945569)
This commit is contained in:
Kovid Goyal 2021-10-05 10:03:10 +05:30
parent 5862e8057a
commit afe7d69681
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 19 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
recipes/entrepeneur.recipe
View File

@ -23,40 +23,31 @@ class EntrepeneurMagRecipe(BasicNewsRecipe):
remove_javascript = True remove_javascript = True
keep_only_tags = [ keep_only_tags = [
dict(attrs={'class': ['headline', 'hero topimage']}), dict(attrs={'data-word-count': True}),
dict(itemprop='articlebody'),
] ]
remove_tags = [ remove_tags = [
dict(attrs={'class': ['related-content']}), dict(attrs={'class': ['related-content']}),
] ]
remove_attributes = ['style'] remove_attributes = ['style']
INDEX = 'http://www.entrepreneur.com' INDEX = 'https://www.entrepreneur.com'
def parse_index(self): def parse_index(self):
root = self.index_to_soup( soup = self.index_to_soup(self.INDEX + '/latest')
self.INDEX + '/magazine/index.html', as_tree=True) articles = []
for href in root.xpath('//h2[@class="sectiontitle nb"]/a/@href'): for h3 in soup.findAll('h3'):
return self.parse_ent_index(self.INDEX + href) a = h3.parent
if a.name == 'a' and a.get('href'):
url = self.INDEX + a['href']
title = self.tag_to_string(h3)
desc = ''
if a.next_sibling and a.next_sibling.name == 'p':
desc = self.tag_to_string(a.next_sibling)
articles.append({'title': title, 'url': url, 'description': desc})
self.log(title, url)
return [('Articles', articles)]
def parse_ent_index(self, url): def preprocess_html(self, soup):
root = self.index_to_soup(url, as_tree=True) for img in soup.findAll('img', attrs={'data-src': True}):
img = root.xpath('//a[@class="hero"]/img[@class="lazy"]')[0] img['src'] = img['data-src']
self.cover_url = img.get('data-original') return soup
self.timefmt = ' [%s]' % img.get('alt').rpartition('-')[-1].strip()
body = root.xpath('//div[@id="latest"]')[0]
ans = []
for x in body.xpath('descendant::h3'):
title = self.tag_to_string(x)
try:
a = x.xpath('./a')[0]
except IndexError:
continue
url = self.INDEX + a.get('href')
d = x.getnext()
desc = self.tag_to_string(d) if d is not None else ''
self.log('\t', title, 'at:', url)
self.log('\t\t', desc)
ans.append({'title': title, 'url': url, 'description': desc})
return [('Articles', ans)]