home *** CD-ROM | disk | FTP | other *** search
/ Chip 2011 November / CHIP_2011_11.iso / Programy / Narzedzia / Calibre / calibre-0.8.18.msi / file_280 / fairbanks_daily.recipe < prev    next >
Text File  |  2011-09-09  |  9KB  |  114 lines
  1. from calibre.web.feeds.news import BasicNewsRecipe
  2.  
  3. class FairbanksDailyNewsminer(BasicNewsRecipe):
  4.     title          = u'Fairbanks Daily News-miner'
  5.     __author__ = 'Roger'
  6.     oldest_article = 7
  7.     max_articles_per_feed = 100
  8.  
  9.     description = 'The voice of interior Alaska since 1903'
  10.     publisher   = 'http://www.newsminer.com/'
  11.     category    = 'news, Alaska, Fairbanks'
  12.     language    = 'en'
  13.  
  14.     # Make article titles, author and date bold, italic or small font.
  15.     # http://assets.matchbin.com/sites/635/stylesheets/newsminer.com.css
  16.     # (signature_line contains date, views, comments)
  17.     extra_css = '''
  18.                     .story_item_headline { font-size: medium; font-weight: bold; }
  19.                     .story_item_author { font-size: small; font-style:italic; }
  20.                     .signature_line { font-size: small; }
  21.                 '''
  22.  
  23.     remove_javascript = True
  24.     use_embedded_content = False
  25.     no_stylesheets = True
  26.     language = 'en'
  27.     encoding = 'utf8'
  28.     conversion_options = {'linearize_tables':True}
  29.  
  30.     # TODO: The News-miner cover image seems a bit small.  Can this be enlarged by 10-30%?
  31.     masthead_url = 'http://d2uh5w9wm14i0w.cloudfront.net/sites/635/assets/top_masthead_-_menu_pic.jpg'
  32.  
  33.  
  34.     # In order to omit seeing number of views, number of posts and the pipe
  35.     # symbol for divider after the title and date of the article, a regex or
  36.     # manual processing is needed to get just the "story_item_date updated"
  37.     # (which contains the date).  Everything else on this line is pretty much not needed.
  38.     #
  39.     # Currently, you will see  the following:
  40.     # | Aug 24, 2011 | 654 views | 6 | |
  41.     # (ie. 6 comments)
  42.     #
  43.     # HTML line containing story_item_date:
  44.     # <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>
  45.  
  46.     # The following was suggested, but it looks like I also need to define self & soup
  47.     # (as well as bring in extra soup depends?)
  48.     #date = self.tag_to_string(soup.find('span', attrs={'class':'story_item_date updated'}))
  49.  
  50.     #preprocess_regexps = [(re.compile(r'<span[^>]*addthis_separator*>'), lambda match: '') ]
  51.     #preprocess_regexps = [(re.compile(r'span class="addthis_separator">|</span>'), lambda match: '') ]
  52.  
  53.     #preprocess_regexps = [
  54.     #           (re.compile(r'<start>.*?<end>', re.IGNORECASE | re.DOTALL), lambda match : ''),
  55.     #               ]
  56.  
  57.     #def get_browser(self):
  58.     #def preprocess_html(soup, first_fetch):
  59.     #    date = self.tag_to_string(soup.find('span', attrs={'class':'story_item_date updated'}))
  60.     #    return
  61.  
  62.     #preprocess_regexps = [(re.compile(r' |.*?', re.DOTALL), lambda m: '')]
  63.  
  64.  
  65.     keep_only_tags = [
  66.                         #dict(name='div', attrs={'class':'hnews hentry item'}),
  67.                         dict(name='div', attrs={'class':'story_item_headline entry-title'}),
  68.                         #dict(name='div', attrs={'class':'story_item_author'}),
  69.                         #dict(name='span', attrs={'class':'story_item_date updated'}),
  70.                         #dict(name='div', attrs={'class':'story_item_author'}),
  71.                         dict(name='div', attrs={'class':'full_story'})
  72.                      ]
  73.  
  74.     remove_tags = [
  75.                     # Try getting rid of some signature_line (date line) stuff
  76.                     #dict(name='img', attrs={'alt'}),
  77.                     dict(name='img', attrs={'class':'dont_touch_me'}),
  78.                     dict(name='span', attrs={'class':'number_recommendations'}),
  79.                     #dict(name='div', attrs={'class':'signature_line'}),
  80.  
  81.                     # Removes div within <!-- AddThis Button BEGIN --> <!-- AddThis Button END -->
  82.                     dict(name='div', attrs={'class':'addthis_toolbox addthis_default_style'}),
  83.  
  84.                     dict(name='div', attrs={'class':'related_content'}),
  85.                     dict(name='div', attrs={'id':'comments_container'})
  86.                   ]
  87.  
  88.  
  89.     # Comment-out or uncomment any of the following RSS feeds according to your
  90.     # liking.
  91.     #
  92.     # TODO: Some random bits of text might be trailing the last page (or TOC on
  93.     # MOBI files), these are bits of public posts and comments and need to also
  94.     # be removed.
  95.     #
  96.     feeds = [
  97.         (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'),
  98.         (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'),
  99.         (u'Business', u'http://newsminer.com/rss/rss_feeds/business_news?content_type=article&tags=business_news&page_name=rss_feeds&instance=business_news'),
  100.         (u'Politics', u'http://newsminer.com/rss/rss_feeds/politics_news?content_type=article&tags=politics_news&page_name=rss_feeds&instance=politics_news'),
  101.         (u'Sports', u'http://newsminer.com/rss/rss_feeds/sports_news?content_type=article&tags=sports_news&page_name=rss_feeds&instance=sports_news'),
  102.         (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'),
  103.         #(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'),
  104.         (u'Outdoors', u'http://newsminer.com/rss/rss_feeds/Outdoors?content_type=article&tags=outdoors&page_name=rss_feeds&instance=Outdoors'),
  105.         #(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'),
  106.         #(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'),
  107.         (u'Opinion', u'http://newsminer.com/rss/rss_feeds/Opinion?content_type=article&tags=editorials&page_name=rss_feeds&instance=Opinion'),
  108.         (u'Youth', u'http://newsminer.com/rss/rss_feeds/Youth?content_type=article&tags=youth&page_name=rss_feeds&instance=Youth'),
  109.         #(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'),
  110.         (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'),
  111.         #(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')
  112.              ]
  113.  
  114.