diff --git a/resources/images/news/di.png b/resources/images/news/di.png new file mode 100644 index 0000000000..07c15554b1 Binary files /dev/null and b/resources/images/news/di.png differ diff --git a/resources/images/news/eclicto.png b/resources/images/news/eclicto.png new file mode 100644 index 0000000000..06d7fe65ed Binary files /dev/null and b/resources/images/news/eclicto.png differ diff --git a/resources/images/news/eksiazki.png b/resources/images/news/eksiazki.png new file mode 100644 index 0000000000..6f4f18d991 Binary files /dev/null and b/resources/images/news/eksiazki.png differ diff --git a/resources/images/news/interia_fakty.png b/resources/images/news/interia_fakty.png new file mode 100644 index 0000000000..06b315847c Binary files /dev/null and b/resources/images/news/interia_fakty.png differ diff --git a/resources/images/news/interia_sport.png b/resources/images/news/interia_sport.png new file mode 100644 index 0000000000..06b315847c Binary files /dev/null and b/resources/images/news/interia_sport.png differ diff --git a/resources/images/news/legitymizm.png b/resources/images/news/legitymizm.png new file mode 100644 index 0000000000..027ce91aaa Binary files /dev/null and b/resources/images/news/legitymizm.png differ diff --git a/resources/images/news/michalkiewicz.png b/resources/images/news/michalkiewicz.png new file mode 100644 index 0000000000..a87f30f5a3 Binary files /dev/null and b/resources/images/news/michalkiewicz.png differ diff --git a/resources/recipes/di.recipe b/resources/recipes/di.recipe index 3b3f6e5c7c..932d8e5f08 100644 --- a/resources/recipes/di.recipe +++ b/resources/recipes/di.recipe @@ -15,42 +15,42 @@ class DziennikInternautowRecipe(BasicNewsRecipe): language = 'pl' title = u'Dziennik Internautow' - publisher = u'Dziennik Internaut\xc3\xb3w Sp. z o.o.' - description =u'Internet w \xc5\xbcyciu i biznesie. Porady, wywiady, interwencje, bezpiecze\xc5\x84stwo w Sieci, technologia.' + publisher = u'Dziennik Internaut\u00f3w Sp. z o.o.' + description = u'Internet w \u017cyciu i biznesie. Porady, wywiady, interwencje, bezpiecze\u0144stwo w Sieci, technologia.' max_articles_per_feed = 100 oldest_article = 7 cover_url = 'http://di.com.pl/pic/logo_di_norm.gif' - + no_stylesheets = True remove_javascript = True encoding = 'utf-8' - + extra_css = ''' .fotodesc{font-size: 75%;} .pub_data{font-size: 75%;} .fotonews{clear: both; padding-top: 10px; padding-bottom: 10px;} #pub_foto{font-size: 75%; float: left; padding-right: 10px;} ''' - + feeds = [ - (u'Dziennik Internautów', u'http://feeds.feedburner.com/glowny-di') + (u'Dziennik Internaut\u00f3w', u'http://feeds.feedburner.com/glowny-di') ] - + keep_only_tags = [ dict(name = 'div', attrs = {'id' : 'pub_head'}), dict(name = 'div', attrs = {'id' : 'pub_content'}) ] - + remove_tags = [ dict(name = 'div', attrs = {'class' : 'poradniki_context'}), dict(name = 'div', attrs = {'class' : 'uniBox'}), dict(name = 'object', attrs = {}), dict(name = 'h3', attrs = {}) ] - + preprocess_regexps = [ - (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in + (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in [ (r', ', lambda match: '
'), diff --git a/resources/recipes/eclicto.recipe b/resources/recipes/eclicto.recipe index a1c625b21c..8ef9b8467c 100644 --- a/resources/recipes/eclicto.recipe +++ b/resources/recipes/eclicto.recipe @@ -1,6 +1,6 @@ #!/usr/bin/env python -__license__ = 'GPL v3' +__license__ = 'GPL v3' __author__ = 'Mori' __version__ = 'v. 0.1' ''' @@ -11,39 +11,39 @@ from calibre.web.feeds.news import BasicNewsRecipe import re class BlogeClictoRecipe(BasicNewsRecipe): - __author__ = 'Mori' - language = 'pl' + __author__ = 'Mori' + language = 'pl' - title = u'Blog eClicto' - publisher = u'Blog eClicto' - description = u'Blog o e-papierze i e-bookach' + title = u'Blog eClicto' + publisher = u'Blog eClicto' + description = u'Blog o e-papierze i e-bookach' - max_articles_per_feed = 100 - cover_url = 'http://blog.eclicto.pl/wordpress/wp-content/themes/blog_eclicto/g/logo.gif' - - no_stylesheets = True - remove_javascript = True - encoding = 'utf-8' - - extra_css = ''' - img{float: left; padding-right: 10px; padding-bottom: 5px;} - ''' - - feeds = [ - (u'Blog eClicto', u'http://blog.eclicto.pl/feed/') - ] - - remove_tags = [ - dict(name = 'span', attrs = {'id' : 'tags'}) - ] - - remove_tags_after = [ - dict(name = 'div', attrs = {'class' : 'post'}) - ] - - preprocess_regexps = [ - (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in - [ - (r'\s*' +''' +fronda.pl +''' + +from calibre.web.feeds.news import BasicNewsRecipe +import re + +class Fronda(BasicNewsRecipe): + title = u'Fronda.pl' + publisher = u'Fronda.pl' + description = u'Portal po\u015bwi\u0119cony - Infformacje' + language = 'pl' + __author__ = u'Tomasz D\u0142ugosz' + oldest_article = 7 + max_articles_per_feed = 100 + use_embedded_content = False + + feeds = [(u'Infformacje', u'http://fronda.pl/news/feed')] + + keep_only_tags = [dict(name='h1', attrs={'class':'big'}), + dict(name='ul', attrs={'class':'about clear'}), + dict(name='div', attrs={'class':'content'})] + preprocess_regexps = [ + (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in + [ (r'Drukuj', lambda match: ''), + (r'

.*

', lambda match: ''), + (r'

.*

', lambda match: ''), + (r'

W.* lektury.*

', lambda match: ''), + (r'

Zobacz t.*?', lambda match: '') ] + ] diff --git a/resources/recipes/interia_fakty.recipe b/resources/recipes/interia_fakty.recipe index cdd245fdd7..63f95f3382 100644 --- a/resources/recipes/interia_fakty.recipe +++ b/resources/recipes/interia_fakty.recipe @@ -10,6 +10,7 @@ from calibre.web.feeds.news import BasicNewsRecipe class InteriaFakty(BasicNewsRecipe): title = u'Interia.pl - Fakty' + description = u'Fakty ze strony interia.pl' language = 'pl' oldest_article = 7 __author__ = u'Tomasz D\u0142ugosz' diff --git a/resources/recipes/interia_sport.recipe b/resources/recipes/interia_sport.recipe index 9c72ee28a7..995dd114a8 100644 --- a/resources/recipes/interia_sport.recipe +++ b/resources/recipes/interia_sport.recipe @@ -11,6 +11,7 @@ from calibre.web.feeds.news import BasicNewsRecipe class InteriaSport(BasicNewsRecipe): title = u'Interia.pl - Sport' + description = u'Sport ze strony interia.pl' language = 'pl' oldest_article = 7 __author__ = u'Tomasz D\u0142ugosz' @@ -30,7 +31,8 @@ class InteriaSport(BasicNewsRecipe): keep_only_tags = [dict(name='div', attrs={'id':'article'})] - remove_tags = [dict(name='div', attrs={'class':'object gallery'})] + remove_tags = [dict(name='div', attrs={'class':'object gallery'}), + dict(name='div', attrs={'class':'box fontSizeSwitch'})] extra_css = ''' .articleDate { diff --git a/resources/recipes/legeartis.recipe b/resources/recipes/legeartis.recipe index 7d5de45035..8365d3639d 100644 --- a/resources/recipes/legeartis.recipe +++ b/resources/recipes/legeartis.recipe @@ -1,6 +1,6 @@ #!/usr/bin/env python -__license__ = 'GPL v3' +__license__ = 'GPL v3' __author__ = 'Mori' __version__ = 'v. 0.1' ''' @@ -10,34 +10,34 @@ olgierd.bblog.pl from calibre.web.feeds.news import BasicNewsRecipe class LegeArtisRecipe(BasicNewsRecipe): - __author__ = 'Mori' - language = 'pl' + __author__ = 'Mori' + language = 'pl' - title = u'Lege Artis' - publisher = u'Olgierd Rudak' - description = u'Wszystko, co chcieliby\xc5\x9bcie wiedzie\xc4\x87 o prawie, ale wstydzicie si\xc4\x99 zapyta\xc4\x87' + title = u'Lege Artis' + publisher = u'Olgierd Rudak' + description = u'Wszystko, co chcieliby\u015bcie wiedzie\u0107 o prawie, ale wstydzicie si\u0119 zapyta\u0107' - max_articles_per_feed = 100 - - no_stylesheets = True - remove_javascript = True - - extra_css = ''' - img{clear: both;} - ''' - - feeds = [ - (u'Lege Artis', u'http://olgierd.bblog.pl/rss/rss20.xml') - ] - - keep_only_tags = [ - dict(name = 'div', attrs = {'class' : 'post_title'}), - dict(name = 'div', attrs = {'class' : 'post_date'}), - dict(name = 'div', attrs = {'class' : 'post_content'}) - ] - - remove_tags = [ - dict(name = 'div', attrs = {'id' : 'bb_tools'}), - dict(name = 'div', attrs = {'class' : 'post_comments'}), - dict(name = 'object', attrs = {}) - ] + max_articles_per_feed = 100 + + no_stylesheets = True + remove_javascript = True + + extra_css = ''' + img{clear: both;} + ''' + + feeds = [ + (u'Lege Artis', u'http://olgierd.bblog.pl/rss/rss20.xml') + ] + + keep_only_tags = [ + dict(name = 'div', attrs = {'class' : 'post_title'}), + dict(name = 'div', attrs = {'class' : 'post_date'}), + dict(name = 'div', attrs = {'class' : 'post_content'}) + ] + + remove_tags = [ + dict(name = 'div', attrs = {'id' : 'bb_tools'}), + dict(name = 'div', attrs = {'class' : 'post_comments'}), + dict(name = 'object', attrs = {}) + ] diff --git a/resources/recipes/legitymizm.recipe b/resources/recipes/legitymizm.recipe index 468f1b1d6b..e54d2beefd 100644 --- a/resources/recipes/legitymizm.recipe +++ b/resources/recipes/legitymizm.recipe @@ -10,6 +10,7 @@ from calibre.web.feeds.news import BasicNewsRecipe class Legitymizm(BasicNewsRecipe): title = u'Organizacja Monarchist\xf3w Polskich' + description = u'Portal legitymistyczny' language = 'pl' oldest_article = 7 __author__ = u'Tomasz D\u0142ugosz' diff --git a/resources/recipes/michalkiewicz.recipe b/resources/recipes/michalkiewicz.recipe index ba58ba432b..7a1e424f0b 100644 --- a/resources/recipes/michalkiewicz.recipe +++ b/resources/recipes/michalkiewicz.recipe @@ -12,7 +12,7 @@ from calibre.web.feeds.news import BasicNewsRecipe class michalkiewicz(BasicNewsRecipe): title = u'Stanis\u0142aw Michalkiewicz' - desciption = u'Strona autorska * felietony * artyku\u0142y * komentarze' + description = u'Strona autorska * felietony * artyku\u0142y * komentarze' __author__ = u'Tomasz D\u0142ugosz' language = 'pl' oldest_article = 7 diff --git a/resources/recipes/nczas.recipe b/resources/recipes/nczas.recipe index ccf963e43a..6ca6657765 100644 --- a/resources/recipes/nczas.recipe +++ b/resources/recipes/nczas.recipe @@ -12,7 +12,7 @@ from calibre.web.feeds.news import BasicNewsRecipe class NCzas(BasicNewsRecipe): title = u'Najwy\u017cszy Czas!' - desciption = u'Najwy\u017cszy Czas!\nwydanie internetowe' + description = u'Najwy\u017cszy Czas!\nwydanie internetowe' __author__ = u'Tomasz D\u0142ugosz' language = 'pl' oldest_article = 7 diff --git a/resources/recipes/runa.recipe b/resources/recipes/runa.recipe new file mode 100644 index 0000000000..fe30041581 --- /dev/null +++ b/resources/recipes/runa.recipe @@ -0,0 +1,52 @@ +#!/usr/bin/env python + +__license__ = 'GPL v3' +__author__ = 'Mori' +__version__ = 'v. 0.1' +''' +www.runa.pl/blog +''' + +from calibre.web.feeds.news import BasicNewsRecipe +import re + +class FantazmatyRecipe(BasicNewsRecipe): + __author__ = 'Mori' + language = 'pl' + + title = u'Fantazmaty' + publisher = u'Agencja Wydawnicza Runa' + description = u'Blog Agencji Wydawniczej Runa' + + no_stylesheets = True + remove_javascript = True + encoding = 'utf-8' + + oldest_article = 100 + max_articles_per_feed = 100 + + extra_css = ''' + img{float: left; padding-right: 10px; padding-bottom: 5px;} + ''' + + feeds = [ + (u'Fantazmaty', u'http://www.runa.pl/blog/rss.xml') + ] + + remove_tags = [ + dict(name = 'div', attrs = {'class' : 'path'}), + dict(name = 'div', attrs = {'class' : 'drdot'}), + dict(name = 'div', attrs = {'class' : 'picture'}) + ] + + remove_tags_after = [ + dict(name = 'div', attrs = {'class' : 'content'}) + ] + + preprocess_regexps = [ + (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in + [ + (r'.*?
', lambda match: '') + ] + ] \ No newline at end of file