calibre/recipes/philippino_star_ngayon.recipe
Kovid Goyal 567040ee1e Perform PEP8 compliance checks on the entire codebase
Some bits of PEP 8 are turned off via setup.cfg
2016-07-29 21:25:17 +05:30

78 lines
3.7 KiB
Plaintext

'''
www.philstar.com
'''
import time
from calibre.web.feeds.recipes import BasicNewsRecipe
class PilipinoStarNgayon(BasicNewsRecipe):
title = 'Pilipino Star Ngayon'
custom_title = "Pilipino Star Ngayon - " + \
time.strftime('%d %b %Y %I:%M %p')
__author__ = 'jde'
__date__ = '31 May 2012'
__version__ = '1.0'
description = 'A daily Tabloid written in Tagalog, distributed in the Philippines. A tabloid style newspaper published in the national language - philstar.com is a Philippine news and entertainment portal for the Filipino global community. It is the online presence of the STAR Group of Publications, a leading publisher of newspapers and magazines in the Philippines.' # noqa
language = 'tgl'
publisher = 'The Philippine STAR'
category = 'news, Philippines'
tags = 'news, Philippines'
cover_url = 'http://www.philstar.com/images/logo_PSN.jpg'
masthead_url = 'http://www.philstar.com/images/logo_PSN.jpg'
oldest_article = 1.5 # days
max_articles_per_feed = 25
simultaneous_downloads = 10
publication_type = 'newspaper'
timefmt = ' [%a, %d %b %Y %I:%M %p]'
no_stylesheets = True
use_embedded_content = False
encoding = None
recursions = 0
needs_subscription = False
remove_javascript = True
remove_empty_feeds = True
auto_cleanup = False
remove_tags = [dict(name='img', attrs={'id': 'Image1'}) # Logo
# Section (Headlines, Nation, Metro, ...)
# Comments
# View Comments
# Zoom
, dict(name='span', attrs={'id': 'ControlArticle1_LabelHeader'}), dict(name='a', attrs={'id': 'ControlArticle1_FormView1_hlComments'}), dict(name='img', attrs={'src': 'images/post-comments.jpg'}), dict(name='a', attrs={'id': 'ControlArticle1_FormView1_ControlPhotoAndCaption1_hlImageCaption'}) # noqa
]
conversion_options = {'title': custom_title,
'comments': description,
'tags': tags,
'language': language,
'publisher': publisher,
'authors': publisher,
'smarten_punctuation': True
}
feeds = [
('Litra-talk' , 'http://rss.philstar.com/Rss.aspx?publicationSubCategoryId=535'),
('Bansa' , 'http://rss.philstar.com/Rss.aspx?publicationSubCategoryId=92'),
('Probinsiya' , 'http://rss.philstar.com/Rss.aspx?publicationSubCategoryId=49'),
('Metro' , 'http://rss.philstar.com/Rss.aspx?publicationSubCategoryId=93'),
('Opinyon' , 'http://rss.philstar.com/Rss.aspx?publicationSubCategoryId=94'),
('Palaro' , 'http://rss.philstar.com/Rss.aspx?publicationSubCategoryId=95'),
('Showbiz' , 'http://rss.philstar.com/Rss.aspx?publicationSubCategoryId=96'),
('True Confessions' , 'http://rss.philstar.com/Rss.aspx?publicationSubCategoryId=97'),
('Dr. Love' , 'http://rss.philstar.com/Rss.aspx?publicationSubCategoryId=98'),
('Kutob' , 'http://rss.philstar.com/Rss.aspx?publicationSubCategoryId=99'),
('Komiks' , 'http://rss.philstar.com/Rss.aspx?publicationSubCategoryId=100')
]
# process the printer friendly version of article
def print_version(self, url):
return url.replace('/Article', '/ArticlePrinterFriendly')
# obtain title from printer friendly version of article; avoiding
# add_toc_thumbnail changing title when article has image
def populate_article_metadata(self, article, soup, first):
article.title = soup.find(
'span', {'id': 'ControlArticle1_FormView1_ArticleHeaderLabel'}).contents[0].strip()