mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
124 lines
5.1 KiB
Python
124 lines
5.1 KiB
Python
#!/usr/bin/env python
|
|
|
|
import json
|
|
import re
|
|
from datetime import date
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
|
|
|
is_saturday = date.today().weekday() == 5
|
|
|
|
|
|
class LiveMint(BasicNewsRecipe):
|
|
title = u'Live Mint'
|
|
description = 'Financial News from India.'
|
|
language = 'en_IN'
|
|
__author__ = 'Krittika Goyal, revised by unkn0wn'
|
|
oldest_article = 1.15 # days
|
|
max_articles_per_feed = 50
|
|
encoding = 'utf-8'
|
|
use_embedded_content = False
|
|
no_stylesheets = True
|
|
remove_attributes = ['style', 'height', 'width']
|
|
masthead_url = 'https://images.livemint.com/static/livemint-logo-v1.svg'
|
|
|
|
remove_empty_feeds = True
|
|
|
|
if is_saturday:
|
|
|
|
cover_url = 'https://epsfs.hindustantimes.com/MINT/2022/04/16/Delhi/Delhi/5_01/bf867ea1_01_mr.jpg'
|
|
|
|
keep_only_tags = [
|
|
dict(name='h1'),
|
|
dict(name='h2', attrs={'id':'story-summary-0'}),
|
|
dict(name='picture'),
|
|
dict(name='div', attrs={'class':'innerBanCaption'}),
|
|
dict(name='div', attrs={'id':'date-display-before-content'}),
|
|
dict(name='div', attrs={'class':'storyContent'}),
|
|
]
|
|
remove_tags = [
|
|
classes(
|
|
'sidebarAdv similarStoriesClass moreFromSecClass'
|
|
)
|
|
]
|
|
feeds = [
|
|
('News', 'https://lifestyle.livemint.com/rss/news'),
|
|
('Food','https://lifestyle.livemint.com/rss/food'),
|
|
('Fashion','https://lifestyle.livemint.com/rss/fashion'),
|
|
('How to Lounge','https://lifestyle.livemint.com/rss/how-to-lounge'),
|
|
('Smart Living','https://lifestyle.livemint.com/rss/smart-living'),
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', attrs={'data-img': True}):
|
|
img['src'] = img['data-img']
|
|
return soup
|
|
else:
|
|
# some wsj articles wont load
|
|
extra_css = '''
|
|
#img-cap {font-size:small; text-align:center;}
|
|
#auth-info {font-size:small; text-align:center;}
|
|
.highlights {font-style:italic;}
|
|
.summary{font-style:italic; color:#404040;}
|
|
'''
|
|
cover_url = 'https://epsfs.hindustantimes.com/MINT/2022/04/05/Delhi/Delhi/5_01/1ec7ad14_01_mr.jpg'
|
|
|
|
keep_only_tags = [
|
|
dict(name='h1'),
|
|
dict(name='figure', attrs={'data-vars-mediatype':'image'}),
|
|
classes('articleInfo FirstEle summary highlights paywall'),
|
|
]
|
|
remove_tags = [
|
|
classes(
|
|
'trendingSimilarHeight moreNews mobAppDownload label msgError msgOk taboolaHeight'
|
|
' socialHolder imgbig disclamerText disqus-comment-count'
|
|
)
|
|
]
|
|
|
|
feeds = [
|
|
('Companies', 'https://www.livemint.com/rss/companies'),
|
|
('Opinion', 'https://www.livemint.com/rss/opinion'),
|
|
('Money', 'https://www.livemint.com/rss/money'),
|
|
('Economy', 'https://www.livemint.com/rss/economy'),
|
|
('Politics', 'https://www.livemint.com/rss/politics'),
|
|
('Science', 'https://www.livemint.com/rss/science'),
|
|
('Industry', 'https://www.livemint.com/rss/industry'),
|
|
('Education', 'https://www.livemint.com/rss/education'),
|
|
('Sports', 'https://www.livemint.com/rss/sports'),
|
|
('Technology', 'https://www.livemint.com/rss/technology'),
|
|
('News', 'https://www.livemint.com/rss/news'),
|
|
('Mutual Funds', 'https://www.livemint.com/rss/Mutual Funds'),
|
|
('Markets', 'https://www.livemint.com/rss/markets'),
|
|
('AI', 'https://www.livemint.com/rss/AI'),
|
|
('Insurance', 'https://www.livemint.com/rss/insurance'),
|
|
('Budget', 'https://www.livemint.com/rss/budget'),
|
|
('Elections', 'https://www.livemint.com/rss/elections'),
|
|
]
|
|
|
|
def preprocess_raw_html(self, raw, *a):
|
|
if '<script>var wsjFlag=true;</script>' in raw:
|
|
m = re.search(r'type="application/ld\+json">[^<]+?"@type": "NewsArticle"', raw)
|
|
raw1 = raw[m.start():]
|
|
raw1 = raw1.split('>', 1)[1].strip()
|
|
data = json.JSONDecoder().raw_decode(raw1)[0]
|
|
value = data['hasPart']['value']
|
|
body = data['articleBody'] + '</p> <p>'\
|
|
+ re.sub(r'(([a-z]|[^A-Z])\.|\.”)([A-Z]|“[A-Z])', r'\1 <p> \3', value)
|
|
body = '<div class="FirstEle"> <p>' + body + '</p> </div>'
|
|
raw = re.sub(r'<div class="FirstEle">([^}]*)</div>', body, raw)
|
|
return raw
|
|
else:
|
|
return raw
|
|
|
|
def preprocess_html(self, soup):
|
|
for span in soup.findAll('figcaption'):
|
|
span['id'] = 'img-cap'
|
|
for auth in soup.findAll('span', attrs={'class':['articleInfo pubtime','articleInfo author']}):
|
|
auth['id'] = 'auth-info'
|
|
auth.name = 'div'
|
|
for span in soup.findAll('span', attrs={'class':'exclusive'}):
|
|
span.extract()
|
|
for img in soup.findAll('img', attrs={'data-src': True}):
|
|
img['src'] = img['data-src']
|
|
return soup
|