mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
101 lines
3.9 KiB
Python
101 lines
3.9 KiB
Python
#!/usr/bin/env python
|
|
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
|
|
|
|
|
class MoneyControlRecipe(BasicNewsRecipe):
|
|
title = u'Money Control'
|
|
__author__ = 'unkn0wn'
|
|
description = 'Read the latest business news on the Indian economy, global market, upcoming IPOs and more.'
|
|
language = 'en_IN'
|
|
masthead_url = 'https://images.moneycontrol.com/images/ftpopup/moneyloginlogo.png'
|
|
encoding = 'utf-8'
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
remove_attributes = ['width', 'height', 'float', 'style']
|
|
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
remove_empty_feeds = True
|
|
resolve_internal_links = True
|
|
oldest_article = 1 # days
|
|
|
|
extra_css = '''
|
|
img {display:block; margin:0 auto;}
|
|
.article_image_wrapper { font-size:small; text-align:center; }
|
|
.articlename_join_follow, .author_wrapper, .FT_block_article { font-size:small; color:#404040; }
|
|
.article_desc { font-style:italic; color:#202020; }
|
|
'''
|
|
|
|
keep_only_tags = [
|
|
dict(name='div', attrs={'id':lambda x: x and x.startswith('article-')})
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name=['svg', 'style', 'button', 'script']),
|
|
dict(attrs={'id':['social_icon_impression', 'taboola-mid-article-thumbnails']}),
|
|
classes(
|
|
'social_icons_wrapper mid-arti-ad lastPara related_stories_left_block social_icons_mobile_wrapper '
|
|
'advSlotsWithoutGrayBox tags_wrapper maintextdiv page_right_wrapper stockwidget tech_newsletter'
|
|
)
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
desc = soup.find(**classes('article_desc'))
|
|
if desc:
|
|
desc.name = 'p'
|
|
for wrap in soup.findAll(**classes('article_image_wrapper')):
|
|
for h2 in wrap.findAll('h2'):
|
|
h2.name = 'span'
|
|
for img in soup.findAll('img', attrs={'data-src':True}):
|
|
img['src'] = img['data-src']
|
|
return soup
|
|
|
|
def parse_index(self):
|
|
index = 'https://www.moneycontrol.com/'
|
|
|
|
business_sections = [
|
|
'markets', 'stocks', 'ipo', 'budget', 'banks', 'moneycontrol-research', 'economy', 'earnings', 'real-estate',
|
|
'personal-finance', 'commodities', 'trade', 'companies'
|
|
]
|
|
|
|
news_sections = [
|
|
'india', 'world', 'opinion', 'politics', 'technology', 'trends', 'lifestyle'
|
|
]
|
|
|
|
feeds = []
|
|
soup = self.index_to_soup(index)
|
|
for b_sec in business_sections:
|
|
burl = index + 'news/business/'
|
|
section = b_sec.capitalize()
|
|
self.log(section)
|
|
articles = []
|
|
for a in soup.findAll('a', attrs={'href':lambda x: x and x.startswith(burl + b_sec + '/')}):
|
|
url = a['href']
|
|
if url in {burl + b_sec + '/', burl + b_sec}:
|
|
continue
|
|
title = self.tag_to_string(a)
|
|
self.log('\t', title, '\n\t\t', url)
|
|
articles.append({'title': title, 'url': url})
|
|
if articles:
|
|
feeds.append((section, articles))
|
|
for n_sec in news_sections:
|
|
nurl = index + 'news/'
|
|
nsection = n_sec.capitalize()
|
|
self.log(nsection)
|
|
articles = []
|
|
for a in soup.findAll('a', attrs={'href':lambda x: x and x.startswith(nurl + n_sec + '/')}):
|
|
url = a['href']
|
|
if url in {nurl + n_sec + '/', nurl + n_sec}:
|
|
continue
|
|
title = self.tag_to_string(a)
|
|
self.log('\t', title, '\n\t\t', url)
|
|
articles.append({'title': title, 'url': url})
|
|
if articles:
|
|
feeds.append((nsection, articles))
|
|
return feeds
|
|
|
|
def populate_article_metadata(self, article, soup, first):
|
|
desc = soup.find(**classes('article_desc'))
|
|
if desc:
|
|
article.summary = self.tag_to_string(desc)
|
|
article.text_summary = article.summary
|