mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
93 lines
3.7 KiB
Plaintext
93 lines
3.7 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import Tag
|
|
|
|
class DawnRecipe(BasicNewsRecipe):
|
|
__license__ = 'GPL v3'
|
|
__author__ = 'kwetal'
|
|
language = 'en_PK'
|
|
version = 1
|
|
|
|
title = u'Dawn'
|
|
publisher = u'Dawn Media Group'
|
|
category = u'News, Pakistan'
|
|
description = u'Leading English Newspaper of Pakistan covering national & international news'
|
|
|
|
use_embedded_content = False
|
|
remove_empty_feeds = True
|
|
oldest_article = 2
|
|
max_articles_per_feed = 100
|
|
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
encoding = 'utf-8'
|
|
|
|
# Feeds from http://www.dawn.com/wps/wcm/connect/dawn-content-library/dawn/services/rss
|
|
feeds = []
|
|
feeds.append((u'Latest News', u'http://feedproxy.google.com/Dawn-All-News'))
|
|
feeds.append((u'Pakistan News', u'http://feeds2.feedburner.com/dawn/news/pakistan'))
|
|
feeds.append((u'World News', u'http://feeds2.feedburner.com/dawn/news/world'))
|
|
feeds.append((u'Business News', u'http://feeds2.feedburner.com/dawn/news/business'))
|
|
feeds.append((u'Sport News', u'http://feeds2.feedburner.com/dawn/news/sport'))
|
|
feeds.append((u'Cricket News', u'http://feeds2.feedburner.com/dawn/news/cricket'))
|
|
feeds.append((u'Sci-tech News', u'http://feeds2.feedburner.com/dawn/news/technology'))
|
|
feeds.append((u'Entertainment News', u'http://feeds2.feedburner.com/dawn/news/entertainment'))
|
|
feeds.append((u'Columnists', u'http://feeds2.feedburner.com/dawn/news/columnists'))
|
|
#feeds.append((u'', u''))
|
|
|
|
conversion_options = {'comments': description, 'tags': category, 'language': 'en',
|
|
'publisher': publisher}
|
|
|
|
extra_css = '''
|
|
body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
|
|
center {font-size: xx-small; color: #666666;}
|
|
strong {font-size: small; font-weight: bold;}
|
|
span.news_headline {font-size: xx-large; font-weight: bold; margin: 0em; padding: 0em}
|
|
span.news_byline {font-size: x-small; color: #696969; margin-top: 1em;}
|
|
'''
|
|
|
|
def print_version(self, url):
|
|
return url + '?pagedesign=Dawn_PrintlyFriendlyPage'
|
|
|
|
def preprocess_html(self, soup):
|
|
newBody = Tag(soup, 'body')
|
|
|
|
for cl in ['page_title', 'news_headline', 'news_byline']:
|
|
tag = soup.find('span', attrs = {'class': cl})
|
|
if tag:
|
|
# They like their <br> tags; I don't: does not work well on small screens.
|
|
if tag['class'] == 'news_byline':
|
|
for br in tag.findAll('br'):
|
|
br.extract()
|
|
|
|
newBody.append(tag)
|
|
|
|
table = soup.find('table', attrs = {'id': 'body table'})
|
|
if table:
|
|
for td in table.findAll('td', attrs = {'class': 'news_story'}):
|
|
for tag in td.findAll(True):
|
|
if tag.has_key('id') and tag['id'] == 'banner-img_slide':
|
|
tag.extract()
|
|
elif tag.has_key('style'):
|
|
del tag['style']
|
|
elif tag.name == 'script':
|
|
tag.extract()
|
|
|
|
# They like their <br> tags; I don't: does not work well on small screens.
|
|
center = td.find('center')
|
|
if center:
|
|
for br in center.findNextSiblings('br'):
|
|
br.extract()
|
|
for br in center.findPreviousSiblings('br'):
|
|
br.extract()
|
|
|
|
for attr in ['align', 'valign']:
|
|
if td.has_key(attr):
|
|
del td[attr]
|
|
|
|
td.name = 'div'
|
|
newBody.append(td)
|
|
|
|
soup.body.replaceWith(newBody)
|
|
|
|
return soup
|