diff --git a/recipes/alejakomiksu_com.recipe b/recipes/alejakomiksu_com.recipe index 34cdede724..e03ee25db9 100644 --- a/recipes/alejakomiksu_com.recipe +++ b/recipes/alejakomiksu_com.recipe @@ -10,8 +10,6 @@ class AlejaKomiksu(BasicNewsRecipe): category = 'comics' language = 'pl' extra_css = 'ul {list-style-type: none;} .gfx_news {float: right;}' - preprocess_regexps = [(re.compile(ur'((
  • (Do poczytania)|(Nowości):
  • )|(

    Komentarze

    )).*', - re.DOTALL | re.IGNORECASE), lambda match: '')] cover_url = 'http://www.alejakomiksu.com/gfx/build/logo.png' masthead_url = 'http://www.alejakomiksu.com/gfx/build/logo.png' use_embedded_content = False @@ -23,7 +21,7 @@ class AlejaKomiksu(BasicNewsRecipe): remove_attributes = ['style', 'font'] ignore_duplicate_articles = {'title', 'url'} - keep_only_tags = [dict(attrs={'class': 'cont_tresc'})] + keep_only_tags = dict(attrs={'class': ['akNews__header','akNews__body']}) feeds = [(u'Wiadomości', 'http://www.alejakomiksu.com/rss.php5')] diff --git a/recipes/astroflesz.recipe b/recipes/astroflesz.recipe deleted file mode 100644 index d44aa994e5..0000000000 --- a/recipes/astroflesz.recipe +++ /dev/null @@ -1,30 +0,0 @@ -# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:fdm=marker:ai -from calibre.web.feeds.news import BasicNewsRecipe - - -class Astroflesz(BasicNewsRecipe): - title = u'Astroflesz' - oldest_article = 7 - __author__ = 'fenuks' - description = u'astroflesz.pl - to portal poświęcony astronomii. Informuje zarówno o aktualnych wydarzeniach i odkryciach naukowych, jak również zapowiada ciekawe zjawiska astronomiczne' # noqa - category = 'astronomy' - language = 'pl' - cover_url = 'http://www.astroflesz.pl/templates/astroflesz/images/logo/logo.png' - ignore_duplicate_articles = {'title', 'url'} - max_articles_per_feed = 100 - no_stylesheets = True - use_embedded_content = False - remove_empty_feeds = True - remove_attributes = ['style'] - keep_only_tags = [dict(id="k2Container")] - remove_tags_after = dict(name='div', attrs={'class': 'itemLinks'}) - remove_tags = [dict(name='div', attrs={ - 'class': ['itemLinks', 'itemToolbar', 'itemRatingBlock']})] - feeds = [(u'Wszystkie', u'http://astroflesz.pl/?format=feed')] - - def postprocess_html(self, soup, first_fetch): - t = soup.find(attrs={'class': 'itemIntroText'}) - if t: - for i in t.findAll('img'): - i['style'] = 'float: left; margin-right: 5px;' - return soup diff --git a/recipes/biolog_pl.recipe b/recipes/biolog_pl.recipe deleted file mode 100644 index ae231d89a2..0000000000 --- a/recipes/biolog_pl.recipe +++ /dev/null @@ -1,31 +0,0 @@ -# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai - -from calibre.web.feeds.news import BasicNewsRecipe - - -class Biolog_pl(BasicNewsRecipe): - title = u'Biolog.pl' - oldest_article = 7 - max_articles_per_feed = 100 - remove_empty_feeds = True - __author__ = 'fenuks' - description = u'Przyrodnicze aktualności ze świata nauki (codziennie aktualizowane), kurs biologii, testy i sprawdziany, forum dyskusyjne.' - category = 'biology' - language = 'pl' - masthead_url = 'http://www.biolog.pl/naukowy,portal,biolog.png' - cover_url = 'http://www.biolog.pl/naukowy,portal,biolog.png' - no_stylesheets = True - ignore_duplicate_articles = {'title', 'url'} - # keeps_only_tags=[dict(id='main')] - remove_tags_before = dict(id='main') - remove_tags_after = dict(name='a', attrs={'name': 'komentarze'}) - remove_tags = [dict(name='img', attrs={'alt': 'Komentarze'}), dict( - name='span', attrs={'class': 'menu_odsylacze'})] - feeds = [ - (u'Wszystkie', u'http://www.biolog.pl/backend.php'), - (u'Medycyna', u'http://www.biolog.pl/medycyna-rss.php'), - (u'Ekologia', u'http://www.biolog.pl/rss-ekologia.php'), - (u'Genetyka i biotechnologia', u'http://www.biolog.pl/rss-biotechnologia.php'), - (u'Botanika', u'http://www.biolog.pl/rss-botanika.php'), - (u'Le\u015bnictwo', u'http://www.biolog.pl/rss-lesnictwo.php'), - (u'Zoologia', u'http://www.biolog.pl/rss-zoologia.php')] diff --git a/recipes/icons/astroflesz.png b/recipes/icons/astroflesz.png deleted file mode 100644 index 2a0f5c2d87..0000000000 Binary files a/recipes/icons/astroflesz.png and /dev/null differ diff --git a/recipes/icons/biolog_pl.png b/recipes/icons/biolog_pl.png deleted file mode 100644 index 9fd50301e6..0000000000 Binary files a/recipes/icons/biolog_pl.png and /dev/null differ diff --git a/recipes/icons/websecurity_pl.png b/recipes/icons/websecurity_pl.png deleted file mode 100644 index 6db9045f33..0000000000 Binary files a/recipes/icons/websecurity_pl.png and /dev/null differ diff --git a/recipes/websecurity_pl.recipe b/recipes/websecurity_pl.recipe deleted file mode 100644 index 9a404260b6..0000000000 --- a/recipes/websecurity_pl.recipe +++ /dev/null @@ -1,27 +0,0 @@ -__license__ = 'GPL v3' -from calibre.web.feeds.news import BasicNewsRecipe - - -class WebSecurity(BasicNewsRecipe): - title = u'WebSecurity' - __author__ = 'fenuks' - description = u'WebSecurity.pl to największy w Polsce portal o bezpieczeństwie sieciowym.' - category = '' - language = 'pl' - cover_url = 'http://websecurity.pl/images/websecurity-logo.png' - masthead_url = '' - use_embedded_content = False - oldest_article = 7 - max_articles_per_feed = 100 - no_stylesheets = True - remove_empty_feeds = True - remove_javascript = True - remove_attributes = ['style', 'font'] - ignore_duplicate_articles = {'title', 'url'} - - keep_only_tags = [ - dict(attrs={'class': 'article single'}), dict(id='content')] - remove_tags = [dict(attrs={'class': ['sociable', 'no-comments']})] - remove_tags_after = dict(attrs={'class': 'sociable'}) - feeds = [(u'Wszystkie', u'http://websecurity.pl/feed/'), (u'Aktualno\u015bci', u'http://websecurity.pl/aktualnosci/feed/'), - (u'Artyku\u0142y', u'http://websecurity.pl/artykuly/feed/'), (u'Blogosfera', u'http://websecurity.pl/blogosfera/wpisy/feed/')] diff --git a/recipes/znadplanszy_pl.recipe b/recipes/znadplanszy_pl.recipe index 7e20596824..7d28e62a0e 100644 --- a/recipes/znadplanszy_pl.recipe +++ b/recipes/znadplanszy_pl.recipe @@ -17,7 +17,5 @@ class ZnadPlanszy(BasicNewsRecipe): remove_attributes = ['style', 'font'] ignore_duplicate_articles = {'title', 'url'} - remove_tags = [dict(attrs={'class': 'rounded-container'})] - remove_tags_after = dict(attrs={'id': 'dotEPUBcontent'}) - remove_tags_before = dict(attrs={'class': 'content units nine alpha'}) + keep_only_tags = dict(name='article') feeds = [(u'Wszystkie', 'http://znadplanszy.pl/full-feed/posts/')]