Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

New recipe for The Indian Express by Krittika Goyal

Browse Source
This commit is contained in:
Kovid Goyal 2009-12-31 16:21:18 -07:00
parent 49383b0db5
commit 95cf14a3ad
5 changed files with 271 additions and 214 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
resources/recipes/biggovernment.recipe
View File

@ -1,28 +1,27 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class BigGovernmentRecipe(BasicNewsRecipe):
class BigGovernmentRecipe(BasicNewsRecipe): __license__ = 'GPL v3'
__license__ = 'GPL v3' __author__ = 'kwetal'
__author__ = 'kwetal' language = 'en_US'
language = 'en_US' version = 1
version = 1
title = u'Big Government'
title = u'Big Government' publisher = u'Andrew Breitbart'
publisher = u'Andrew Breitbart' category = u'Political blog'
category = u'Political blog' description = u'Political news from the USA'
description = u'Political news from the USA'
oldest_article = 30
oldest_article = 30 max_articles_per_feed = 100
max_articles_per_feed = 100 use_embedded_content = True
use_embedded_content = True
feeds = [(u'Big Government', u'http://feeds.feedburner.com/BigGovernment')]
feeds = [(u'Big Government', u'http://feeds.feedburner.com/BigGovernment')]
conversion_options = {'comments': description, 'tags': category, 'language': 'en',
conversion_options = {'comments': description, 'tags': category, 'language': 'en', 'publisher': publisher}
'publisher': publisher}
extra_css = '''
extra_css = ''' body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
body{font-family:verdana,arial,helvetica,geneva,sans-serif;} img {float: left; margin-right: 0.5em;}
img {float: left; margin-right: 0.5em;} '''
'''

164
resources/recipes/eluniversalimpresa.recipe
View File

@ -1,82 +1,82 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class ElUniversalImpresaRecipe(BasicNewsRecipe): class ElUniversalImpresaRecipe(BasicNewsRecipe):
__license__ = 'GPL v3' __license__ = 'GPL v3'
__author__ = 'kwetal' __author__ = 'kwetal'
language = 'es' language = 'es'
version = 1 version = 1
title = u'El Universal (Edici\u00F3n Impresa)' title = u'El Universal (Edici\u00F3n Impresa)'
publisher = u'El Universal' publisher = u'El Universal'
category = u'News, Mexico' category = u'News, Mexico'
description = u'News from Mexico' description = u'News from Mexico'
remove_empty_feeds = True remove_empty_feeds = True
remove_javascript = True remove_javascript = True
INDEX = 'http://www.eluniversal.com.mx' INDEX = 'http://www.eluniversal.com.mx'
extra_css = ''' extra_css = '''
body{font-family:verdana,arial,helvetica,geneva,sans-serif;} body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
''' '''
conversion_options = {'comments': description, 'tags': category, 'language': 'en', conversion_options = {'comments': description, 'tags': category, 'language': 'en',
'publisher': publisher, 'linearize_tables': True} 'publisher': publisher, 'linearize_tables': True}
def parse_index(self): def parse_index(self):
soup = self.index_to_soup('http://www.eluniversal.com.mx/edicion_impresa.html') soup = self.index_to_soup('http://www.eluniversal.com.mx/edicion_impresa.html')
index = [] index = []
table = soup.find('table', attrs = {'width': '500'}) table = soup.find('table', attrs = {'width': '500'})
articles = [] articles = []
for td in table.findAll(lambda tag: tag.name == 'td' and tag.has_key('class') and tag['class'] == 'arnegro12'): for td in table.findAll(lambda tag: tag.name == 'td' and tag.has_key('class') and tag['class'] == 'arnegro12'):
a = td.a a = td.a
a.extract() a.extract()
title = self.tag_to_string(a) title = self.tag_to_string(a)
url = self.INDEX + a['href'] url = self.INDEX + a['href']
description = self.tag_to_string(td) description = self.tag_to_string(td)
articles.append({'title': title, 'date': None, 'url': url, 'description' : description}) articles.append({'title': title, 'date': None, 'url': url, 'description' : description})
index.append(('Primera Plana', articles)) index.append(('Primera Plana', articles))
for td in table.findAll(lambda tag: tag.name == 'td' and len(tag.attrs) == 0): for td in table.findAll(lambda tag: tag.name == 'td' and len(tag.attrs) == 0):
articles = [] articles = []
feedTitle = None feedTitle = None
for a in td.findAll('a'): for a in td.findAll('a'):
if not feedTitle: if not feedTitle:
feedTitle = self.tag_to_string(a) feedTitle = self.tag_to_string(a)
continue continue
title = self.tag_to_string(a) title = self.tag_to_string(a)
url = self.INDEX + a['href'] url = self.INDEX + a['href']
articles.append({'title': title, 'date': None, 'url': url, 'description': ''}) articles.append({'title': title, 'date': None, 'url': url, 'description': ''})
index.append((feedTitle, articles)) index.append((feedTitle, articles))
return index return index
def print_version(self, url): def print_version(self, url):
if url.find('wcarton') >= 0: if url.find('wcarton') >= 0:
return None return None
main, sep, id = url.rpartition('/') main, sep, id = url.rpartition('/')
return main + '/vi_' + id return main + '/vi_' + id
def preprocess_html(self, soup): def preprocess_html(self, soup):
table = soup.find('table') table = soup.find('table')
table.extract() table.extract()
for p in soup.findAll('p'): for p in soup.findAll('p'):
if self.tag_to_string(p).strip() == '': if self.tag_to_string(p).strip() == '':
p.extract() p.extract()
tag = soup.find('font', attrs = {'color': '#0F046A'}) tag = soup.find('font', attrs = {'color': '#0F046A'})
if tag: if tag:
for attr in ['color', 'face', 'helvetica,', 'sans-serif', 'size']: for attr in ['color', 'face', 'helvetica,', 'sans-serif', 'size']:
if tag.has_key(attr): if tag.has_key(attr):
del tag[attr] del tag[attr]
tag.name = 'h1' tag.name = 'h1'
return soup return soup

57
resources/recipes/indian_express.recipe Normal file
View File

@ -0,0 +1,57 @@
from calibre.web.feeds.news import BasicNewsRecipe
class IndianExpress(BasicNewsRecipe):
title = u'Indian Express'
language = 'en_IN'
__author__ = 'Krittika Goyal'
oldest_article = 1 #days
max_articles_per_feed = 25
encoding = 'cp1252'
no_stylesheets = True
remove_tags_before = dict(name='div', attrs={'class':'top_head'})
#remove_tags_after = dict(name='td', attrs={'class':'newptool1'})
remove_tags = [
dict(name='iframe'),
dict(name='div', attrs={'class':['bookmarks_div', 'comment_box', 'bookmarks_div_bot', 'box']}),
dict(name='div', attrs={'id':['footer', 'tab_innerhc', 'discussion', 'google_new']}),
dict(name='a', attrs={'class':'nobdr'}),
#dict(name='span', text=':'),
]
feeds = [
('Front Page',
'http://syndication.indianexpress.com/rss/33/front-page.xml'),
('Markets',
'http://syndication.indianexpress.com/rss/793/markets.xml'),
('Editorials',
'http://syndication.indianexpress.com/rss/35/editorials.xml'),
('Crime',
'http://syndication.indianexpress.com/rss/801/crime-&-justice.xml'),
('Cricket',
'http://syndication.indianexpress.com/rss/777/cricket.xml'),
('Health',
'http://syndication.indianexpress.com/rss/697/health.xml'),
('Asia',
'http://syndication.indianexpress.com/rss/790/asia.xml'),
('Politics',
'http://syndication.indianexpress.com/rss/799/politics.xml'),
('Mumbai',
'http://syndication.indianexpress.com/rss/707/mumbai.xml'),
('Op-Ed',
'http://syndication.indianexpress.com/rss/36/oped.xml'),
('Economy',
'http://syndication.indianexpress.com/rss/794/economy.xml'),
('Lifestyle',
'http://syndication.indianexpress.com/rss/713/lifestyle.xml'),
('Letters to the Editor',
'http://syndication.indianexpress.com/rss/40/letters-to-editor.xml'),
('Movie Reviews',
'http://syndication.indianexpress.com/rss/665/movie-reviews.xml'),
('Bollywood',
'http://syndication.indianexpress.com/rss/887/bollywood.xml'),
]
def print_version(self, url):
return url+'/0'

89
resources/recipes/journalofaccountancy.recipe
View File

@ -1,44 +1,45 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.web.feeds.news import BasicNewsRecipe
class JournalOfAccountancyRecipe(BasicNewsRecipe):
__license__ = 'GPL v3' class JournalOfAccountancyRecipe(BasicNewsRecipe):
__author__ = 'kwetal' __license__ = 'GPL v3'
language = 'en' __author__ = 'kwetal'
version = 1 language = 'en'
version = 1
title = u'Journal of Accountancy'
publisher = u'AICPA' title = u'Journal of Accountancy'
category = u'News, Accountancy' publisher = u'AICPA'
description = u'Publication of the American Institute of Certified Public Accountants' category = u'News, Accountancy'
description = u'Publication of the American Institute of Certified Public Accountants'
use_embedded_content = False
remove_empty_feeds = True use_embedded_content = False
oldest_article = 30 remove_empty_feeds = True
max_articles_per_feed = 100 oldest_article = 30
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True no_stylesheets = True
remove_javascript = True
extra_css = '''
body{font-family:verdana,arial,helvetica,geneva,sans-serif;} extra_css = '''
div#Rubricname {font-size: small; color: #666666; margin-bottom: 1em;} body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
div#Headline {font-size: x-large; font-weight: bold; margin-bottom: 0.6em} div#Rubricname {font-size: small; color: #666666; margin-bottom: 1em;}
div#SubHeadline {font-size: medium; font-weight: bold; margin-bottom: 1em} div#Headline {font-size: x-large; font-weight: bold; margin-bottom: 0.6em}
div#Authorname, div#Date {font-size: x-small; color: #696969;} div#SubHeadline {font-size: medium; font-weight: bold; margin-bottom: 1em}
''' div#Authorname, div#Date {font-size: x-small; color: #696969;}
'''
conversion_options = {'comments': description, 'tags': category, 'language': 'en',
'publisher': publisher} conversion_options = {'comments': description, 'tags': category, 'language': 'en',
'publisher': publisher}
keep_only_tags = []
keep_only_tags.append(dict(name = 'div', attrs = {'id': 'Rubricname'})) keep_only_tags = []
keep_only_tags.append(dict(name = 'div', attrs = {'id': 'Headline'})) keep_only_tags.append(dict(name = 'div', attrs = {'id': 'Rubricname'}))
keep_only_tags.append(dict(name = 'div', attrs = {'id': 'SubHeadline'})) keep_only_tags.append(dict(name = 'div', attrs = {'id': 'Headline'}))
keep_only_tags.append(dict(name = 'div', attrs = {'id': 'Authorname'})) keep_only_tags.append(dict(name = 'div', attrs = {'id': 'SubHeadline'}))
keep_only_tags.append(dict(name = 'div', attrs = {'id': 'Date'})) keep_only_tags.append(dict(name = 'div', attrs = {'id': 'Authorname'}))
keep_only_tags.append(dict(name = 'div', attrs = {'id': 'BodyContent'})) keep_only_tags.append(dict(name = 'div', attrs = {'id': 'Date'}))
keep_only_tags.append(dict(name = 'div', attrs = {'id': 'BodyContent'}))
remove_attributes = ['style']
remove_attributes = ['style']
feeds = []
feeds.append((u'Journal of Accountancy', u'http://feeds2.feedburner.com/JournalOfAccountancy')) feeds = []
feeds.append((u'Journal of Accountancy', u'http://feeds2.feedburner.com/JournalOfAccountancy'))

120
resources/recipes/propublica.recipe
View File

@ -1,60 +1,60 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup from calibre.web.feeds.news import BasicNewsRecipe
class ProPublicaRecipe(BasicNewsRecipe): class ProPublicaRecipe(BasicNewsRecipe):
__license__ = 'GPL v3' __license__ = 'GPL v3'
__author__ = 'kwetal' __author__ = 'kwetal'
language = 'en_US' language = 'en_US'
version = 1 version = 1
title = u'Pro Publica' title = u'Pro Publica'
publisher = u'ProPublica.org' publisher = u'ProPublica.org'
category = u'Political blog' category = u'Political blog'
description = u'Independent investigative journalism in the public interest.' description = u'Independent investigative journalism in the public interest.'
oldest_article = 14 oldest_article = 14
max_articles_per_feed = 100 max_articles_per_feed = 100
use_embedded_content = False use_embedded_content = False
remove_empty_feeds = True remove_empty_feeds = True
no_stylesheets = True no_stylesheets = True
remove_javascript = True remove_javascript = True
keep_only_tags = [] keep_only_tags = []
keep_only_tags.append(dict(name = 'div', attrs = {'class': 'article'})) keep_only_tags.append(dict(name = 'div', attrs = {'class': 'article'}))
remove_tags = [] remove_tags = []
remove_tags.append(dict(name = 'div', attrs = {'id': 'rollups'})) remove_tags.append(dict(name = 'div', attrs = {'id': 'rollups'}))
remove_tags.append(dict(name = 'div', attrs = {'class': 'follow_info'})) remove_tags.append(dict(name = 'div', attrs = {'class': 'follow_info'}))
remove_tags.append(dict(name = 'ul', attrs = {'class': 'long-tools-top'})) remove_tags.append(dict(name = 'ul', attrs = {'class': 'long-tools-top'}))
remove_tags.append(dict(name = 'ul', attrs = {'id': 'share-box'})) remove_tags.append(dict(name = 'ul', attrs = {'id': 'share-box'}))
remove_tags.append(dict(name = 'div', attrs = {'class': 'tags'})) remove_tags.append(dict(name = 'div', attrs = {'class': 'tags'}))
remove_tags.append(dict(name = 'ul', attrs = {'class': 'long-tools'})) remove_tags.append(dict(name = 'ul', attrs = {'class': 'long-tools'}))
remove_tags.append(dict(name = 'ul', attrs = {'id': 'share-box2'})) remove_tags.append(dict(name = 'ul', attrs = {'id': 'share-box2'}))
remove_tags.append(dict(name = 'p', attrs = {'id': 'original-url'})) remove_tags.append(dict(name = 'p', attrs = {'id': 'original-url'}))
feeds = [] feeds = []
feeds.append((u'Top Stories', u'http://feeds.propublica.org/propublica/main')) feeds.append((u'Top Stories', u'http://feeds.propublica.org/propublica/main'))
feeds.append((u'Stimulus', u'http://feeds.propublica.org/propublica/watchdog/stimulus')) feeds.append((u'Stimulus', u'http://feeds.propublica.org/propublica/watchdog/stimulus'))
feeds.append((u'Bailout', u'http://feeds.propublica.org/propublica/watchdog/bailout')) feeds.append((u'Bailout', u'http://feeds.propublica.org/propublica/watchdog/bailout'))
feeds.append((u'Business', u'http://feeds.propublica.org/propublica/business-money')) feeds.append((u'Business', u'http://feeds.propublica.org/propublica/business-money'))
feeds.append((u'Justice', u'http://feeds.propublica.org/propublica/justice-law')) feeds.append((u'Justice', u'http://feeds.propublica.org/propublica/justice-law'))
feeds.append((u'Energy & Environment', u'http://feeds.propublica.org/propublica/energy-environment')) feeds.append((u'Energy & Environment', u'http://feeds.propublica.org/propublica/energy-environment'))
feeds.append((u'Government & Politics', u'http://feeds.propublica.org/propublica/government-politics')) feeds.append((u'Government & Politics', u'http://feeds.propublica.org/propublica/government-politics'))
feeds.append((u'Health & Science', u'http://feeds.propublica.org/propublica/health-science')) feeds.append((u'Health & Science', u'http://feeds.propublica.org/propublica/health-science'))
feeds.append((u'Media & Technology', u'http://feeds.propublica.org/propublica/media-technology')) feeds.append((u'Media & Technology', u'http://feeds.propublica.org/propublica/media-technology'))
feeds.append((u'National Security', u'http://feeds.propublica.org/propublica/national-security')) feeds.append((u'National Security', u'http://feeds.propublica.org/propublica/national-security'))
#feeds.append((u'', u'')) #feeds.append((u'', u''))
conversion_options = {'comments': description, 'tags': category, 'language': 'en', conversion_options = {'comments': description, 'tags': category, 'language': 'en',
'publisher': publisher} 'publisher': publisher}
extra_css = ''' extra_css = '''
body{font-family:verdana,arial,helvetica,geneva,sans-serif;} body{font-family:verdana,arial,helvetica,geneva,sans-serif;}
img {float: left; margin-right: 0.5em;} img {float: left; margin-right: 0.5em;}
h1 {text-align: left;} h1 {text-align: left;}
a, a[href] {text-decoration: none; color: blue;} a, a[href] {text-decoration: none; color: blue;}
div.cat {font-size: x-small; color: #666666; margin-bottom: 0.1em;} div.cat {font-size: x-small; color: #666666; margin-bottom: 0.1em;}
div.info {font-size: small; color: #696969;} div.info {font-size: small; color: #696969;}
''' '''