| 1 |
#!/usr/bin/env python |
| 2 |
|
| 3 |
""" |
| 4 |
zaobao.com.sg |
| 5 |
""" |
| 6 |
|
| 7 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 8 |
|
| 9 |
|
| 10 |
class ZAOBAO(BasicNewsRecipe): |
| 11 |
title = '联合早报' |
| 12 |
__author__ = 'unkn0wn' |
| 13 |
description = '联合早报 是全球华文用户信任的媒体,每天即时为你提供国际最新新闻和热门新闻。从财经、体育、生活娱乐资讯到评论分析,尽在zaobao.com.sg。' |
| 14 |
no_stylesheets = True |
| 15 |
language = 'zh' |
| 16 |
encoding = 'utf-8' |
| 17 |
masthead_url = 'https://upload.wikimedia.org/wikipedia/en/2/29/Lianhe_Zaobao_new_logo.svg' |
| 18 |
remove_javascript = True |
| 19 |
ignore_duplicate_articles = {'url'} |
| 20 |
remove_attributes = ['width', 'height', 'style'] |
| 21 |
resolve_internal_links = True |
| 22 |
remove_empty_feeds = True |
| 23 |
|
| 24 |
extra_css = ''' |
| 25 |
.calibre-nuked-tag-figcaption {font-size:small; text-align:center; } |
| 26 |
img {display:block; margin:0 auto;} |
| 27 |
''' |
| 28 |
|
| 29 |
def get_cover_url(self): |
| 30 |
soup = self.index_to_soup('https://frontpages.freedomforum.org/newspapers/sing_lz-Lianhe_Zaobao') |
| 31 |
return soup.find( |
| 32 |
'img', |
| 33 |
attrs={ |
| 34 |
'alt': 'Front Page Image', |
| 35 |
'src': lambda x: x and x.endswith('front-page-large.jpg'), |
| 36 |
}, |
| 37 |
)['src'].replace('-large', '-medium') |
| 38 |
|
| 39 |
keep_only_tags = [ |
| 40 |
dict(name='article', attrs={'class': 'max-w-full'}), |
| 41 |
] |
| 42 |
|
| 43 |
remove_tags_after = [classes('articleBody')] |
| 44 |
|
| 45 |
remove_tags = [classes('bff-google-ad bff-recommend-article')] |
| 46 |
|
| 47 |
def parse_index(self): |
| 48 |
index = 'https://www.zaobao.com.sg' |
| 49 |
sections = ['realtime', 'news', 'forum', 'wencui', 'lifestyle', 'entertainment'] |
| 50 |
|
| 51 |
soup = self.index_to_soup(index) |
| 52 |
|
| 53 |
feeds = [] |
| 54 |
|
| 55 |
for sec in sections: |
| 56 |
sectn = sec.capitalize() |
| 57 |
self.log(sectn) |
| 58 |
|
| 59 |
articles = [] |
| 60 |
|
| 61 |
for a in soup.findAll( |
| 62 |
'a', |
| 63 |
attrs={ |
| 64 |
'class': 'article-type-link', |
| 65 |
'href': lambda x: x and x.startswith('/' + sec), |
| 66 |
}, |
| 67 |
): |
| 68 |
if a.find('img'): |
| 69 |
continue |
| 70 |
title = self.tag_to_string(a) |
| 71 |
url = index + a['href'] |
| 72 |
if url == index + '/' + sec: |
| 73 |
continue |
| 74 |
self.log('\t', title, '\n\t\t', url) |
| 75 |
articles.append({'title': title, 'url': url}) |
| 76 |
if articles: |
| 77 |
feeds.append((sectn, articles)) |
| 78 |
return feeds |