mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
New recipes for Chowk, Dawn and The News by kwetal
This commit is contained in:
Kovid Goyal
parent
d39e71b34a
commit
adddcd996a
46
resources/recipes/chowk.recipe
Normal file
46
resources/recipes/chowk.recipe
Normal file
@ -0,0 +1,46 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class ChowkRecipe(BasicNewsRecipe):
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'kwetal'
|
||||
language = 'en_IN'
|
||||
version = 1
|
||||
|
||||
title = u'Chowk'
|
||||
publisher = u'chowk.com'
|
||||
category = u'Opinion, South Asia'
|
||||
description = u'Ideas & Identities of South Asia'
|
||||
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
oldest_article = 30
|
||||
max_articles_per_feed = 100
|
||||
|
||||
#no_stylesheets = True
|
||||
remove_javascript = True
|
||||
encoding = 'utf-8'
|
||||
|
||||
feeds = []
|
||||
feeds.append(('Chowk Articles', 'http://www.chowk.com/rss'))
|
||||
|
||||
keep_only_tags = []
|
||||
keep_only_tags.append(dict(name = 'div', attrs = {'id': 'content'}))
|
||||
|
||||
conversion_options = {'comments': description, 'tags': category, 'language': 'en',
|
||||
'publisher': publisher}
|
||||
|
||||
extra_css = '''
|
||||
body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
|
||||
a {text-decoration: none; color: blue;}
|
||||
div.pgtitle {font-size: x-large; font-weight: bold;}
|
||||
div.wname, div.date {font-size: x-small; color: #696969;}
|
||||
div.wname {margin-top: 1em;}
|
||||
div.date {margin-bottom: 1em;}
|
||||
div.title {font-weight: bold;}
|
||||
'''
|
||||
|
||||
|
||||
def print_version(self, url):
|
||||
main, sep, id = url.rpartition('/')
|
||||
|
||||
return main + '/print/' + id
|
||||
92
resources/recipes/dawn.recipe
Normal file
92
resources/recipes/dawn.recipe
Normal file
@ -0,0 +1,92 @@
|
||||
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
|
||||
78
resources/recipes/thenews.recipe
Normal file
78
resources/recipes/thenews.recipe
Normal file
@ -0,0 +1,78 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class TheNewsRecipe(BasicNewsRecipe):
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'kwetal'
|
||||
language = 'en_PK'
|
||||
version = 1
|
||||
|
||||
title = u'The News'
|
||||
publisher = u'Jang Group'
|
||||
category = u'News, Pakistan'
|
||||
description = u'English Newspaper from Pakistan'
|
||||
|
||||
use_embedded_content = False
|
||||
remove_empty_feeds = True
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 100
|
||||
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
encoding = 'iso-8859-1'
|
||||
|
||||
remove_tags = []
|
||||
remove_tags.append(dict(name = 'img', attrs = {'src': 'images/thenews.gif'}))
|
||||
remove_tags.append(dict(name = 'img', attrs = {'src': 'images/shim.gif'}))
|
||||
|
||||
# Feeds from http://thenews.com.pk/rss.asp
|
||||
feeds = []
|
||||
feeds.append((u'Latest Stories', u'http://www.thenews.com.pk/rss/thenews_updates.xml'))
|
||||
feeds.append((u'Top Stories', u'http://www.thenews.com.pk/rss/thenews_topstories.xml'))
|
||||
feeds.append((u'World News', u'http://www.thenews.com.pk/rss/thenews_world.xml'))
|
||||
feeds.append((u'National News', u'http://www.thenews.com.pk/rss/thenews_national.xml'))
|
||||
feeds.append((u'Business News', u'http://www.thenews.com.pk/rss/thenews_business.xml'))
|
||||
feeds.append((u'Karachi News', u'http://www.thenews.com.pk/rss/thenews_karachi.xml'))
|
||||
feeds.append((u'Lahore News', u'http://www.thenews.com.pk/rss/thenews_lahore.xml'))
|
||||
feeds.append((u'Islamabad News', u'http://www.thenews.com.pk/rss/thenews_islamabad.xml'))
|
||||
feeds.append((u'Peshawar News', u'http://www.thenews.com.pk/rss/thenews_peshawar.xml'))
|
||||
feeds.append((u'Editorial', u'http://www.thenews.com.pk/rss/thenews_editorial.xml'))
|
||||
feeds.append((u'Opinion', u'http://www.thenews.com.pk/rss/thenews_opinion.xml'))
|
||||
feeds.append((u'Sports News', u'http://www.thenews.com.pk/rss/thenews_sports.xml'))
|
||||
feeds.append((u'Newspost', u'http://www.thenews.com.pk/rss/thenews_newspost.xml'))
|
||||
|
||||
conversion_options = {'comments': description, 'tags': category, 'language': 'en',
|
||||
'publisher': publisher, 'linearize_tables': True}
|
||||
|
||||
extra_css = '''
|
||||
body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
|
||||
.heading_txt {font-size: x-large; font-weight: bold; text-align: left;}
|
||||
.small_txt {text-align: left;}
|
||||
.dateline {font-size: x-small; color: #696969; margin-top: 1em; margin-bottom: 1em}
|
||||
'''
|
||||
|
||||
|
||||
def print_version(self, url):
|
||||
ignore, sep, main = url.rpartition('/')
|
||||
|
||||
if main.startswith('updates.asp'):
|
||||
return url.replace('updates.asp', 'print.asp')
|
||||
elif main.startswith('top_story_detail.asp'):
|
||||
return url.replace('top_story_detail.asp', 'print3.asp')
|
||||
elif main.startswith('daily_detail.asp'):
|
||||
return url.replace('daily_detail.asp', 'print1.asp')
|
||||
else:
|
||||
return None
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for tr in soup.findAll('tr', attrs = {'bgcolor': True}):
|
||||
del tr['bgcolor']
|
||||
|
||||
td = soup.find('td', attrs = {'class': 'small_txt', 'height': '20'})
|
||||
if td:
|
||||
del td['height']
|
||||
td['class'] = 'dateline'
|
||||
|
||||
return soup
|
||||
|
||||
|
||||
|
||||
@ -101,6 +101,7 @@ _extra_lang_codes = {
|
||||
'en_IN' : _('English (IND)'),
|
||||
'en_TH' : _('English (TH)'),
|
||||
'en_CY' : _('English (CY)'),
|
||||
'en_PK' : _('English (PK)'),
|
||||
'de_AT' : _('German (AT)'),
|
||||
'nl' : _('Dutch (NL)'),
|
||||
'nl_BE' : _('Dutch (BE)'),
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user