mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
59 lines
2.4 KiB
Plaintext
59 lines
2.4 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class NewYorkTimesBookReview(BasicNewsRecipe):
|
|
title = u'New York Times Book Review'
|
|
language = 'en'
|
|
description = 'The New York Times Sunday Book Review. Best downloaded on Fridays to avoid the ads that the New York Times shows of the first few days of the week.' # noqa
|
|
__author__ = 'Kovid Goyal'
|
|
|
|
no_stylesheets = True
|
|
no_javascript = True
|
|
auto_cleanup = True
|
|
#keep_only_tags = [dict(id='article'), dict(id=lambda x:x and x.startswith('entry-'))]
|
|
# remove_tags = [
|
|
#dict(attrs={'class':['articleBottomExtra', 'shareToolsBox', 'singleAd']}),
|
|
#dict(attrs={'class':lambda x: x and ('shareTools' in x or 'enlargeThis' in x)}),
|
|
#]
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup('http://www.nytimes.com/pages/books/review/index.html')
|
|
|
|
# Find TOC
|
|
toc = soup.find('div', id='main').find(
|
|
'div', attrs={'class':'abColumn'})
|
|
feeds = []
|
|
articles = []
|
|
section_title = 'Features'
|
|
for x in toc.findAll(['div', 'h3', 'h6'], attrs={'class':['story', 'sectionHeader', 'ledeStory']}):
|
|
if x['class'] == 'sectionHeader':
|
|
if articles:
|
|
feeds.append((section_title, articles))
|
|
section_title = self.tag_to_string(x)
|
|
articles = []
|
|
self.log('Found section:', section_title)
|
|
continue
|
|
if x['class'] in {'story', 'ledeStory'}:
|
|
tt = 'h3' if x['class'] == 'story' else 'h1'
|
|
try:
|
|
a = x.find(tt).find('a', href=True)
|
|
except AttributeError:
|
|
continue
|
|
title = self.tag_to_string(a)
|
|
url = a['href'] + '&pagewanted=all'
|
|
self.log('\tFound article:', title, url)
|
|
desc = ''
|
|
byline = x.find('h6', attrs={'class':'byline'})
|
|
if byline is not None:
|
|
desc = self.tag_to_string(byline)
|
|
summary = x.find('p', attrs={'class':'summary'})
|
|
if summary is not None:
|
|
desc += self.tag_to_string(summary)
|
|
if desc:
|
|
self.log('\t\t', desc)
|
|
articles.append({'title':title, 'url':url, 'date':'',
|
|
'description':desc})
|
|
|
|
return feeds
|
|
|
|
|