Here's the best I could do for the Fairbanks Daily News-miner newspaper.
I only know Bash and C well, and little Python.
I figure, when somebody else around Alaska here pulls this in when they're using Calibre, they'll have somewhat of an outline of listed bugs/anomalies to work with rather then starting from nothing and trying to find each bug/anomaly. (These are marked within TODO inline comments.)
Oh, I could pretty this up for you people taking submission to hide the anomalies, but I'm more of an honest guy and know leaving comments (if sometimes too many), is a way better method! This way, another can easily fix rather then struggling from the beginning blind.
This recipe is well commented for anybody willing to fix things more:
1) Article titles should likely be bold font?
2) Only need story_item_date and omit number of views/posts/pipe symbols.
3) Need a newline after each index/toc entry when pulling more then one RSS feed for some reason.
Sorry, I am not a fan of Python or QT!
(... and for some reason, I can't attach this file and only post inline. :-(
Code:
#import re # Provides preprocess_regexps re.compile
#import string # Provides self.tag_to_string
#from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
#from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag, NavigableString # Provides soup
class FairbanksDailyNewsminer(BasicNewsRecipe):
title = u'Fairbanks Daily News-miner'
__author__ = 'Roger'
oldest_article = 7
max_articles_per_feed = 100
description = ''''The voice of interior Alaska since 1903'''
publisher = 'http://www.newsminer.com/'
category = 'news, Alaska, Fairbanks'
language = 'en'
#extra_css = '''
# p{font-weight: normal;text-align: justify}
# '''
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
language = 'en'
encoding = 'utf8'
conversion_options = {'linearize_tables':True}
# TODO: I don't see any photos in my Mobi file with this masterhead_url!
masthead_url = 'http://d2uh5w9wm14i0w.cloudfront.net/sites/635/assets/top_masthead_-_menu_pic.jpg'
# In order to omit seeing number of views, number of posts and the pipe
# symbol for divider after the title and date of the article, a regex or
# manual processing is needed to get just the "story_item_date updated"
# (which contains the date). Everything else on this line is pretty much not needed.
#
# HTML line containing story_item_date:
# <div class="signature_line"><span title="2011-08-22T23:37:14Z" class="story_item_date updated">Aug 22, 2011</span> | 2370 views | 52 <a href="/pages/full_story/push?article-Officials+tout+new+South+Cushman+homeless+living+facility%20&id=15183753#comments_15183753"><img alt="52 comments" class="dont_touch_me" src="http://d2uh5w9wm14i0w.cloudfront.net/images/comments-icon.gif" title="52 comments" /></a> | <span id="number_recommendations_15183753" class="number_recommendations">9</span> <a href="#1" id="recommend_link_15183753" onclick="Element.remove('recommend_link_15183753'); new Ajax.Request('/community/content/recommend/15183753', {asynchronous:true, evalScripts:true}); return false;"><img alt="9 recommendations" class="dont_touch_me" src="http://d2uh5w9wm14i0w.cloudfront.net/images/thumbs-up-icon.gif" title="9 recommendations" /></a> | <a href="#1" onclick="$j.facebox({ajax: '/community/content/email_friend_pane/15183753'}); return false;"><span style="position: relative;"><img alt="email to a friend" class="dont_touch_me" src="http://d2uh5w9wm14i0w.cloudfront.net/images/email-this.gif" title="email to a friend" /></span></a> | <span><a href="/printer_friendly/15183753" target="_blank"><img alt="print" class="dont_touch_me" src="http://d2uh5w9wm14i0w.cloudfront.net/images/print_icon.gif" title="print" /></a></span><span id="email_content_message_15183753" class="signature_email_message"></span></div>
# The following was suggested, but it looks like I also need to define self & soup
# (as well as bring in extra soup depends?)
#date = self.tag_to_string(soup.find('span', attrs={'class':'story_item_date updated'}))
#preprocess_regexps = [(re.compile(r'<span[^>]*addthis_separator*>'), lambda match: '') ]
#preprocess_regexps = [(re.compile(r'span class="addthis_separator">|</span>'), lambda match: '') ]
#preprocess_regexps = [
# (re.compile(r'<start>.*?<end>', re.IGNORECASE | re.DOTALL), lambda match : ''),
# ]
#def get_browser(self):
#def preprocess_html(soup, first_fetch):
# date = self.tag_to_string(soup.find('span', attrs={'class':'story_item_date updated'}))
# return
# Try to keep some tags - some might not be needed here
keep_only_tags = [
#date = self.tag_to_string(soup.find('span', attrs={'class':'story_item_date updated'})),
dict(name='div', attrs={'class':'hnews hentry item'}),
dict(name='div', attrs={'class':'story_item_headline entry-title'}),
#dict(name='span', attrs={'class':'story_item_date updated'}),
dict(name='div', attrs={'class':'full_story'})
]
#remove_tags = [
# dict(name='div', attrs={'class':'story_tools'}),
# dict(name='p', attrs={'class':'ad_label'}),
# ]
# Try to remove some bothersome tags
remove_tags = [
#dict(name='img', attrs={'alt'}),
dict(name='img', attrs={'class':'dont_touch_me'}),
dict(name='span', attrs={'class':'number_recommendations'}),
#dict(name='div', attrs={'class':'signature_line'}),
dict(name='div', attrs={'class':'addthis_toolbox addthis_default_style'}),
dict(name='div', attrs={'class':['addthis_toolbox','addthis_default_style']}),
dict(name='span', attrs={'class':'addthis_separator'}),
dict(name='div', attrs={'class':'related_content'}),
dict(name='div', attrs={'class':'comments_container'}),
#dict(name='div', attrs={'class':'signature_line'}),
dict(name='div', attrs={'class':'addthis_toolbox addthis_default_style'}),
dict(name='div', attrs={'id':'comments_container'})
]
# This one works but only gets title, date and clips article content!
#remove_tags_after = [
# dict(name='span', attrs={'class':'story_item_date updated'})
# ]
#remove_tags_after = [
# dict(name='div', attrs={'class':'advertisement'}),
# ]
# Try clipping tags before and after to prevent pulling img views/posts numbers after date?
#remove_tags_before = [
# dict(name='span', attrs={'class':'story_item_date updated'})
# ]
#extra_css # tweak the appearance # TODO: Change article titles <h2?> to bold?
# Comment-out or uncomment any of the following RSS feeds according to your
# liking.
#
# TODO: Adding more then one RSS Feed, and newline will be omitted for
# entries within the Table of Contents or Index of Articles
#
# TODO: Some random bits of text is trailing the last page (or TOC on MOBI
# files), these are bits of public posts and comments and need to also be
# removed.
#
feeds = [
(u'Alaska News', u'http://newsminer.com/rss/rss_feeds/alaska_news?content_type=article&tags=alaska_news&page_name=rss_feeds&instance=alaska_news'),
(u'Local News', u'http://newsminer.com/rss/rss_feeds/local_news?content_type=article&tags=local_news&page_name=rss_feeds&offset=0&instance=local_news'),
# (u'Business', u'http://newsminer.com/rss/rss_feeds/business_news?content_type=article&tags=business_news&page_name=rss_feeds&instance=business_news'),
# (u'Politics', u'http://newsminer.com/rss/rss_feeds/politics_news?content_type=article&tags=politics_news&page_name=rss_feeds&instance=politics_news'),
# (u'Sports', u'http://newsminer.com/rss/rss_feeds/sports_news?content_type=article&tags=sports_news&page_name=rss_feeds&instance=sports_news'),
# (u'Latitude 65 feed', u'http://newsminer.com/rss/rss_feeds/latitude_65?content_type=article&tags=latitude_65&page_name=rss_feeds&offset=0&instance=latitude_65'),
(u'Sundays', u'http://newsminer.com/rss/rss_feeds/Sundays?content_type=article&tags=alaska_science_forum+scott_mccrea+interior_gardening+in_the_bush+judy_ferguson+book_reviews+theresa_bakker+judith_kleinfeld+interior_scrapbook+nuggets_comics+freeze_frame&page_name=rss_feeds&tag_inclusion=or&instance=Sundays'),
# (u'Outdoors', u'http://newsminer.com/rss/rss_feeds/Outdoors?content_type=article&tags=outdoors&page_name=rss_feeds&instance=Outdoors'),
# (u'Fairbanks Grizzlies', u'http://newsminer.com/rss/rss_feeds/fairbanks_grizzlies?content_type=article&tags=fairbanks_grizzlies&page_name=rss_feeds&instance=fairbanks_grizzlies'),
(u'Newsminer', u'http://newsminer.com/rss/rss_feeds/Newsminer?content_type=article&tags=ted_stevens_bullets+ted_stevens+sports_news+business_news+fairbanks_grizzlies+dermot_cole_column+outdoors+alaska_science_forum+scott_mccrea+interior_gardening+in_the_bush+judy_ferguson+book_reviews+theresa_bakker+judith_kleinfeld+interior_scrapbook+nuggets_comics+freeze_frame&page_name=rss_feeds&tag_inclusion=or&instance=Newsminer'),
# (u'Opinion', u'http://newsminer.com/rss/rss_feeds/Opinion?content_type=article&tags=editorials&page_name=rss_feeds&instance=Opinion'),
# (u'Youth', u'http://newsminer.com/rss/rss_feeds/Youth?content_type=article&tags=youth&page_name=rss_feeds&instance=Youth'),
# (u'Dermot Cole Blog', u'http://newsminer.com/rss/rss_feeds/dermot_cole_blog+rss?content_type=blog+entry&sort_by=posted_on&user_ids=3015275&page_name=blogs_dermot_cole&limit=10&instance=dermot_cole_blog+rss'),
# (u'Dermot Cole Column', u'http://newsminer.com/rss/rss_feeds/Dermot_Cole_column?content_type=article&tags=dermot_cole_column&page_name=rss_feeds&instance=Dermot_Cole_column'),
# (u'Sarah Palin', u'http://newsminer.com/rss/rss_feeds/sarah_palin?content_type=article&tags=palin_in_the_news+palin_on_the_issues&page_name=rss_feeds&tag_inclusion=or&instance=sarah_palin')
]