calibre/recipes/reuters.recipe
2021-02-05 12:56:43 +05:30

88 lines
2.7 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2020, Kovid Goyal <kovid at kovidgoyal.net>
from __future__ import absolute_import, division, print_function, unicode_literals
from calibre.web.feeds.news import BasicNewsRecipe, classes
country = 'us'
country_defs = {
'us': ('www.reuters.com', {
'Business': 'finance',
'Markets': 'finance/markets',
'World': 'world',
'Politics': 'politics',
'Tech': 'news/technology',
'Wealth': 'finance/wealth',
})
}
def prefixed_classes(classes):
q = frozenset(classes.split(' '))
def matcher(x):
if x:
for candidate in frozenset(x.split()):
for x in q:
if candidate.startswith(x):
return True
return False
return {'attrs': {'class': matcher}}
class Reuters(BasicNewsRecipe):
title = 'Reuters'
description = 'News from all over'
__author__ = 'Kovid Goyal'
language = 'en'
keep_only_tags = [
prefixed_classes('ArticlePage-article-header ArticlePage-article-body'),
]
remove_tags = [
prefixed_classes('ArticleBody-read-time-and-social Slideshow-expand-button- TwoColumnsLayout-footer-'),
dict(name=['button', 'link']),
]
def preprocess_html(self, soup, *a):
meta = soup.find(attrs={'name': "sailthru.image.full"})
if meta is not None:
url = meta['content']
body = soup.find(**prefixed_classes('ArticlePage-article-body'))
if body is not None:
div = soup.new_tag('div')
div.append(soup.new_tag('img', src=url))
body.insert(0, div)
return soup
def parse_index(self):
base, sections = country_defs[country]
ans = []
for section_title in sorted(sections):
slug = sections[section_title]
self.log(section_title)
articles = list(self.parse_reuters_section(base, slug))
if articles:
ans.append((section_title, articles))
if self.test and len(ans) >= self.test[0]:
break
return ans
def parse_reuters_section(self, base, slug):
url = 'https://' + base + '/' + slug
try:
soup = self.index_to_soup(url)
except Exception:
self.log.error('Failed to load Reuters section:', url)
return
for div in soup.findAll(**classes('news-headline-list')):
h3 = div.find(**classes('story-title'))
a = h3.parent
title = self.tag_to_string(h3)
url = 'https://{}{}'.format(base, a['href'])
self.log('\t', title, url)
yield {'title': title, 'url': url}