diff --git a/recipes/benchmark_pl.recipe b/recipes/benchmark_pl.recipe index c934cc4ac4..6572130389 100644 --- a/recipes/benchmark_pl.recipe +++ b/recipes/benchmark_pl.recipe @@ -12,14 +12,17 @@ class BenchmarkPl(BasicNewsRecipe): language = 'pl' oldest_article = 8 max_articles_per_feed = 100 + extra_css = 'ul {list-style-type: none;}' no_stylesheets = True - remove_attributes = ['style'] + #remove_attributes = ['style'] preprocess_regexps = [(re.compile(ur'

 Zobacz poprzednie Opinie dnia:.*', re.DOTALL|re.IGNORECASE), lambda match: ''), (re.compile(ur'Więcej o .*?', re.DOTALL|re.IGNORECASE), lambda match: '')] - keep_only_tags = [dict(name='div', attrs={'class':['m_zwykly', 'gallery']}), dict(id='article')] + + keep_only_tags = [dict(id=['articleHeader', 'articleGallery']), dict(name='div', attrs={'class':['m_zwykly', 'gallery']}), dict(id='article')] remove_tags_after = dict(id='article') remove_tags = [dict(name='div', attrs={'class':['comments', 'body', 'kategoria', 'socialize', 'thumb', 'panelOcenaObserwowane', 'categoryNextToSocializeGallery', 'breadcrumb', 'footer', 'moreTopics']}), dict(name='table', attrs = {'background':'http://www.benchmark.pl/uploads/backend_img/a/fotki_newsy/opinie_dnia/bg.png'}), dict(name='table', attrs={'width':'210', 'cellspacing':'1', 'cellpadding':'4', 'border':'0', 'align':'right'})] + INDEX = 'http://www.benchmark.pl' - feeds = [(u'Aktualności', u'http://www.benchmark.pl/rss/aktualnosci-pliki.xml'), + feeds = [(u'Aktualności', u'http://www.benchmark.pl/rss/aktualnosci-pliki.xml'), (u'Testy i recenzje', u'http://www.benchmark.pl/rss/testy-recenzje-minirecenzje.xml')] @@ -42,46 +45,16 @@ class BenchmarkPl(BasicNewsRecipe): for r in appendtag.findAll(attrs={'class':'changePage'}): r.extract() - - def image_article(self, soup, appendtag): - nexturl = soup.find('div', attrs={'class':'preview'}) - if nexturl: - nexturl = nexturl.find('a', attrs={'class':'move_next'}) - image = appendtag.find('div', attrs={'class':'preview'}).div['style'][16:] - image = self.INDEX + image[:image.find("')")] - appendtag.find(attrs={'class':'preview'}).name='img' - appendtag.find(attrs={'class':'preview'})['src']=image - appendtag.find('a', attrs={'class':'move_next'}).extract() - while nexturl: - nexturl = self.INDEX + nexturl['href'] - soup2 = self.index_to_soup(nexturl) - nexturl = soup2.find('a', attrs={'class':'move_next'}) - image = soup2.find('div', attrs={'class':'preview'}).div['style'][16:] - image = self.INDEX + image[:image.find("')")] - soup2.find(attrs={'class':'preview'}).name='img' - soup2.find(attrs={'class':'preview'})['src']=image - pagetext = soup2.find('div', attrs={'class':'gallery'}) - pagetext.find('div', attrs={'class':'title'}).extract() - pagetext.find('div', attrs={'class':'thumb'}).extract() - pagetext.find('div', attrs={'class':'panelOcenaObserwowane'}).extract() - if nexturl: - pagetext.find('a', attrs={'class':'move_next'}).extract() - pagetext.find('a', attrs={'class':'move_back'}).extract() - comments = pagetext.findAll(text=lambda text:isinstance(text, Comment)) - for comment in comments: - comment.extract() - pos = len(appendtag.contents) - appendtag.insert(pos, pagetext) - - def preprocess_html(self, soup): - if soup.find('div', attrs={'class':'preview'}): - self.image_article(soup, soup.body) - else: - self.append_page(soup, soup.body) + self.append_page(soup, soup.body) for a in soup('a'): if a.has_key('href') and not a['href'].startswith('http'): a['href'] = self.INDEX + a['href'] for r in soup.findAll(attrs={'class':['comments', 'body']}): r.extract() + tag1 = soup.find(attrs={'class':'inlineGallery'}) + if tag1: + for tag in tag1.findAll('li'): + tag['style'] = 'float: left; margin-right: 10px;' + tag1.findNext('p')['style'] = 'clear: both;' return soup diff --git a/recipes/computerworld_pl.recipe b/recipes/computerworld_pl.recipe index 6d4e2a179f..8bf1f55124 100644 --- a/recipes/computerworld_pl.recipe +++ b/recipes/computerworld_pl.recipe @@ -16,7 +16,7 @@ class Computerworld_pl(BasicNewsRecipe): preprocess_regexps = [(re.compile(u'Zobacz również:', re.IGNORECASE), lambda m: ''), (re.compile(ur'[*]+reklama[*]+', re.IGNORECASE), lambda m: ''),] keep_only_tags = [dict(id=['szpaltaL', 's2011'])] remove_tags_after = dict(name='div', attrs={'class':'tresc'}) - remove_tags = [dict(attrs={'class':['nnav', 'rMobi', 'tagi', 'rec']}),] + remove_tags = [dict(attrs={'class':['nnav', 'rMobi', 'tagi', 'rec']}), dict(name='a', attrs={'target':'_blank'})] feeds = [(u'Wiadomo\u015bci', u'http://rssout.idg.pl/cw/news_iso.xml')] def skip_ad_pages(self, soup): diff --git a/recipes/conowego_pl.recipe b/recipes/conowego_pl.recipe index 7e6549e713..982497f453 100644 --- a/recipes/conowego_pl.recipe +++ b/recipes/conowego_pl.recipe @@ -15,6 +15,7 @@ class CoNowegoPl(BasicNewsRecipe): no_stylesheets = True remove_empty_feeds = True use_embedded_content = False + ignore_duplicate_articles = {'title', 'url'} keep_only_tags = [dict(name='div', attrs={'class':'news_list single_view'})] remove_tags = [dict(name='div', attrs={'class':['ni_bottom', 'ni_rank', 'ni_date']})] feeds = [(u'Aktualno\u015bci', u'http://www.conowego.pl/rss/aktualnosci-5/?type=100'), (u'Gaming', u'http://www.conowego.pl/rss/gaming-6/?type=100'), (u'Porady', u'http://www.conowego.pl/rss/porady-3/?type=100'), (u'Testy', u'http://www.conowego.pl/rss/testy-2/?type=100')] diff --git a/recipes/di.recipe b/recipes/di.recipe index dad0fdd648..511220c755 100644 --- a/recipes/di.recipe +++ b/recipes/di.recipe @@ -14,7 +14,7 @@ class DziennikInternautowRecipe(BasicNewsRecipe): __author__ = 'Mori' language = 'pl' - title = u'Dziennik Internautow' + title = u'Dziennik Internautów' publisher = u'Dziennik Internaut\u00f3w Sp. z o.o.' description = u'Internet w \u017cyciu i biznesie. Porady, wywiady, interwencje, bezpiecze\u0144stwo w Sieci, technologia.' diff --git a/recipes/dziennik_lodzki.recipe b/recipes/dziennik_lodzki.recipe index 93a86fdaa2..ecde189e64 100644 --- a/recipes/dziennik_lodzki.recipe +++ b/recipes/dziennik_lodzki.recipe @@ -16,7 +16,7 @@ class DziennikLodzki(BasicNewsRecipe): ignore_duplicate_articles = {'title', 'url'} #preprocess_regexps = [(re.compile(ur'Czytaj także:.*?', re.DOTALL), lambda match: ''), (re.compile(ur',Czytaj też:.*?', re.DOTALL), lambda match: ''), (re.compile(ur'Zobacz także:.*?', re.DOTALL), lambda match: ''), (re.compile(ur'

', re.DOTALL), lambda match: ''), (re.compile(ur'CZYTAJ TEŻ:.*?', re.DOTALL), lambda match: ''), (re.compile(ur'CZYTAJ WIĘCEJ:.*?', re.DOTALL), lambda match: ''), (re.compile(ur'CZYTAJ TAKŻE:.*?', re.DOTALL), lambda match: ''), (re.compile(ur'\* CZYTAJ KONIECZNIE:.*', re.DOTALL), lambda match: ''), (re.compile(ur'Nasze serwisy:.*', re.DOTALL), lambda match: '') ] remove_tags_after= dict(attrs={'src':'http://nm.dz.com.pl/dz.png'}) - remove_tags=[dict(id='mat-podobne'), dict(name='a', attrs={'class':'czytajDalej'}), dict(attrs={'src':'http://nm.dz.com.pl/dz.png'})] + remove_tags=[dict(id='mat-podobne'), dict(name='a', attrs={'class':'czytajDalej'}), dict(attrs={'src':'http://nm.dz.com.pl/dz.png'}), dict(name='a', attrs={'href':'http://www.dzienniklodzki.pl/piano'})] feeds = [(u'Na sygnale', u'http://www.dzienniklodzki.pl/rss/dzienniklodzki_nasygnale.xml?201302'), (u'\u0141\xf3d\u017a', u'http://www.dzienniklodzki.pl/rss/dzienniklodzki_lodz.xml?201302'), (u'Opinie', u'http://www.dzienniklodzki.pl/rss/dzienniklodzki_opinie.xml?201302'), (u'Pieni\u0105dze', u'http://dzienniklodzki.feedsportal.com/c/32980/f/533763/index.rss?201302'), (u'Kultura', u'http://dzienniklodzki.feedsportal.com/c/32980/f/533762/index.rss?201302'), (u'Sport', u'http://dzienniklodzki.feedsportal.com/c/32980/f/533761/index.rss?201302'), (u'Akcje', u'http://www.dzienniklodzki.pl/rss/dzienniklodzki_akcje.xml?201302'), (u'M\xf3j Reporter', u'http://www.dzienniklodzki.pl/rss/dzienniklodzki_mojreporter.xml?201302'), (u'Studni\xf3wki', u'http://www.dzienniklodzki.pl/rss/dzienniklodzki_studniowki.xml?201302'), (u'Kraj', u'http://www.dzienniklodzki.pl/rss/dzienniklodzki_kraj.xml?201302'), (u'Zdrowie', u'http://www.dzienniklodzki.pl/rss/dzienniklodzki_zdrowie.xml?201302')] diff --git a/recipes/dziennik_zachodni.recipe b/recipes/dziennik_zachodni.recipe index 126c876937..3fc6512bef 100644 --- a/recipes/dziennik_zachodni.recipe +++ b/recipes/dziennik_zachodni.recipe @@ -16,7 +16,7 @@ class DziennikZachodni(BasicNewsRecipe): ignore_duplicate_articles = {'title', 'url'} #preprocess_regexps = [(re.compile(ur'Czytaj także:.*?', re.DOTALL), lambda match: ''), (re.compile(ur',Czytaj też:.*?', re.DOTALL), lambda match: ''), (re.compile(ur'Zobacz także:.*?', re.DOTALL), lambda match: ''), (re.compile(ur'

', re.DOTALL), lambda match: ''), (re.compile(ur'CZYTAJ TEŻ:.*?', re.DOTALL), lambda match: ''), (re.compile(ur'CZYTAJ WIĘCEJ:.*?', re.DOTALL), lambda match: ''), (re.compile(ur'CZYTAJ TAKŻE:.*?', re.DOTALL), lambda match: ''), (re.compile(ur'\* CZYTAJ KONIECZNIE:.*', re.DOTALL), lambda match: ''), (re.compile(ur'Nasze serwisy:.*', re.DOTALL), lambda match: '') ] remove_tags_after= dict(attrs={'src':'http://nm.dz.com.pl/dz.png'}) - remove_tags=[dict(id='mat-podobne'), dict(name='a', attrs={'class':'czytajDalej'}), dict(attrs={'src':'http://nm.dz.com.pl/dz.png'}), dict(attrs={'href':'http://www.dziennikzachodni.pl/piano'})] + remove_tags=[dict(id='mat-podobne'), dict(name='a', attrs={'class':'czytajDalej'}), dict(attrs={'src':'http://nm.dz.com.pl/dz.png'}), dict(attrs={'href':'http://www.dziennikzachodni.pl/piano'}), dict(name='aside')] feeds = [(u'Wszystkie', u'http://dziennikzachodni.feedsportal.com/c/32980/f/533764/index.rss?201302'), (u'Wiadomo\u015bci', u'http://dziennikzachodni.feedsportal.com/c/32980/f/533765/index.rss?201302'), (u'Regiony', u'http://www.dziennikzachodni.pl/rss/dziennikzachodni_regiony.xml?201302'), (u'Opinie', u'http://www.dziennikzachodni.pl/rss/dziennikzachodni_regiony.xml?201302'), (u'Blogi', u'http://www.dziennikzachodni.pl/rss/dziennikzachodni_blogi.xml?201302'), (u'Serwisy', u'http://www.dziennikzachodni.pl/rss/dziennikzachodni_serwisy.xml?201302'), (u'Sport', u'http://dziennikzachodni.feedsportal.com/c/32980/f/533766/index.rss?201302'), (u'M\xf3j Reporter', u'http://www.dziennikzachodni.pl/rss/dziennikzachodni_mojreporter.xml?201302'), (u'Na narty', u'http://www.dziennikzachodni.pl/rss/dziennikzachodni_nanarty.xml?201302'), (u'Drogi', u'http://www.dziennikzachodni.pl/rss/dziennikzachodni_drogi.xml?201302'), (u'Pieni\u0105dze', u'http://dziennikzachodni.feedsportal.com/c/32980/f/533768/index.rss?201302')] diff --git a/recipes/echo_dnia.recipe b/recipes/echo_dnia.recipe index def87ce0e1..7dc913d062 100644 --- a/recipes/echo_dnia.recipe +++ b/recipes/echo_dnia.recipe @@ -16,6 +16,7 @@ class EchoDnia(BasicNewsRecipe): max_articles_per_feed = 100 remove_empty_feeds = True no_stylesheets = True + use_embedded_content = False ignore_duplicate_articles = {'title', 'url'} preprocess_regexps = [(re.compile(ur'Czytaj:.*?', re.DOTALL), lambda match: ''), (re.compile(ur'Przeczytaj także:.*?', re.DOTALL|re.IGNORECASE), lambda match: ''), diff --git a/recipes/ekundelek_pl.recipe b/recipes/ekundelek_pl.recipe index ebc5d39bbd..bf0963092f 100644 --- a/recipes/ekundelek_pl.recipe +++ b/recipes/ekundelek_pl.recipe @@ -12,7 +12,7 @@ class swiatczytnikow(BasicNewsRecipe): __author__ = u'Artur Stachecki' oldest_article = 7 max_articles_per_feed = 100 - + remove_empty_feeds = True remove_tags = [dict(name = 'div', attrs = {'class' : 'feedflare'})] feeds = [(u'Wpisy', u'http://feeds.feedburner.com/Ekundelekpl?format=xml')] diff --git a/recipes/emuzica_pl.recipe b/recipes/emuzica_pl.recipe index 0b3b207c5e..18a7ab2726 100644 --- a/recipes/emuzica_pl.recipe +++ b/recipes/emuzica_pl.recipe @@ -11,6 +11,7 @@ class eMuzyka(BasicNewsRecipe): cover_url='http://s.emuzyka.pl/img/emuzyka_invert_small.jpg' no_stylesheets = True oldest_article = 7 + remove_empty_feeds = True max_articles_per_feed = 100 remove_attributes = ['style'] keep_only_tags=[dict(name='div', attrs={'id':'news_container'}), dict(name='h3'), dict(name='div', attrs={'class':'review_text'})] diff --git a/recipes/gazeta_wyborcza.recipe b/recipes/gazeta_wyborcza.recipe index 310077cdec..880aea5bc1 100644 --- a/recipes/gazeta_wyborcza.recipe +++ b/recipes/gazeta_wyborcza.recipe @@ -9,6 +9,7 @@ class Gazeta_Wyborcza(BasicNewsRecipe): description = 'Wiadomości z Polski i ze świata. Serwisy tematyczne i lokalne w 20 miastach.' category = 'newspaper' publication_type = 'newspaper' + #encoding = 'iso-8859-2' masthead_url = 'http://bi.gazeta.pl/im/5/10285/z10285445AA.jpg' INDEX = 'http://wyborcza.pl' remove_empty_feeds = True @@ -16,6 +17,7 @@ class Gazeta_Wyborcza(BasicNewsRecipe): max_articles_per_feed = 100 remove_javascript = True no_stylesheets = True + use_embedded_content = False ignore_duplicate_articles = {'title', 'url'} remove_tags_before = dict(id='k0') remove_tags_after = dict(id='banP4') @@ -24,7 +26,19 @@ class Gazeta_Wyborcza(BasicNewsRecipe): (u'Wyborcza.biz', u'http://wyborcza.biz/pub/rss/wyborcza_biz_wiadomosci.htm'), (u'Komentarze', u'http://rss.feedsportal.com/c/32739/f/530312/index.rss'), (u'Kultura', u'http://rss.gazeta.pl/pub/rss/gazetawyborcza_kultura.xml'), - (u'Nauka', u'http://rss.feedsportal.com/c/32739/f/530269/index.rss'), (u'Opinie', u'http://rss.gazeta.pl/pub/rss/opinie.xml'), (u'Gazeta \u015awi\u0105teczna', u'http://rss.feedsportal.com/c/32739/f/530431/index.rss'), (u'Du\u017cy Format', u'http://rss.feedsportal.com/c/32739/f/530265/index.rss'), (u'Witamy w Polsce', u'http://rss.feedsportal.com/c/32739/f/530476/index.rss'), (u'M\u0119ska Muzyka', u'http://rss.feedsportal.com/c/32739/f/530337/index.rss'), (u'Lata Lec\u0105', u'http://rss.feedsportal.com/c/32739/f/530326/index.rss'), (u'Solidarni z Tybetem', u'http://rss.feedsportal.com/c/32739/f/530461/index.rss'), (u'W pon. - \u017bakowski', u'http://rss.feedsportal.com/c/32739/f/530491/index.rss'), (u'We wt. - Kolenda-Zalewska', u'http://rss.feedsportal.com/c/32739/f/530310/index.rss'), (u'\u015aroda w \u015brod\u0119', u'http://rss.feedsportal.com/c/32739/f/530428/index.rss'), (u'W pi\u0105tek - Olejnik', u'http://rss.feedsportal.com/c/32739/f/530364/index.rss'), (u'Nekrologi', u'http://rss.feedsportal.com/c/32739/f/530358/index.rss') + (u'Nauka', u'http://rss.feedsportal.com/c/32739/f/530269/index.rss'), + (u'Opinie', u'http://rss.gazeta.pl/pub/rss/opinie.xml'), + (u'Gazeta \u015awi\u0105teczna', u'http://rss.feedsportal.com/c/32739/f/530431/index.rss'), + (u'Du\u017cy Format', u'http://rss.feedsportal.com/c/32739/f/530265/index.rss'), + (u'Witamy w Polsce', u'http://rss.feedsportal.com/c/32739/f/530476/index.rss'), + (u'M\u0119ska Muzyka', u'http://rss.feedsportal.com/c/32739/f/530337/index.rss'), + (u'Lata Lec\u0105', u'http://rss.feedsportal.com/c/32739/f/530326/index.rss'), + (u'Solidarni z Tybetem', u'http://rss.feedsportal.com/c/32739/f/530461/index.rss'), + (u'W pon. - \u017bakowski', u'http://rss.feedsportal.com/c/32739/f/530491/index.rss'), + (u'We wt. - Kolenda-Zalewska', u'http://rss.feedsportal.com/c/32739/f/530310/index.rss'), + (u'\u015aroda w \u015brod\u0119', u'http://rss.feedsportal.com/c/32739/f/530428/index.rss'), + (u'W pi\u0105tek - Olejnik', u'http://rss.feedsportal.com/c/32739/f/530364/index.rss'), + (u'Nekrologi', u'http://rss.feedsportal.com/c/32739/f/530358/index.rss') ] def skip_ad_pages(self, soup): diff --git a/recipes/gildia_pl.recipe b/recipes/gildia_pl.recipe index 6d3528b0bc..37c129aaa1 100644 --- a/recipes/gildia_pl.recipe +++ b/recipes/gildia_pl.recipe @@ -31,6 +31,14 @@ class Gildia(BasicNewsRecipe): for link in content.findAll(name='a'): if 'fragment' in link['href']: return self.index_to_soup(link['href'], raw=True) + if 'relacj' in soup.title.string.lower(): + for link in content.findAll(name='a'): + if 'relacj' in link['href']: + return self.index_to_soup(link['href'], raw=True) + if 'wywiad' in soup.title.string.lower(): + for link in content.findAll(name='a'): + if 'wywiad' in link['href']: + return self.index_to_soup(link['href'], raw=True) def preprocess_html(self, soup): diff --git a/recipes/glos_wielkopolski.recipe b/recipes/glos_wielkopolski.recipe index d7706c4173..1b7f3f7817 100644 --- a/recipes/glos_wielkopolski.recipe +++ b/recipes/glos_wielkopolski.recipe @@ -16,7 +16,7 @@ class GlosWielkopolski(BasicNewsRecipe): ignore_duplicate_articles = {'title', 'url'} #preprocess_regexps = [(re.compile(ur'Czytaj także:.*?', re.DOTALL), lambda match: ''), (re.compile(ur',Czytaj też:.*?', re.DOTALL), lambda match: ''), (re.compile(ur'Zobacz także:.*?', re.DOTALL), lambda match: ''), (re.compile(ur'

', re.DOTALL), lambda match: ''), (re.compile(ur'CZYTAJ TEŻ:.*?', re.DOTALL), lambda match: ''), (re.compile(ur'CZYTAJ WIĘCEJ:.*?', re.DOTALL), lambda match: ''), (re.compile(ur'CZYTAJ TAKŻE:.*?', re.DOTALL), lambda match: ''), (re.compile(ur'\* CZYTAJ KONIECZNIE:.*', re.DOTALL), lambda match: ''), (re.compile(ur'Nasze serwisy:.*', re.DOTALL), lambda match: '') ] remove_tags_after= dict(attrs={'src':'http://nm.dz.com.pl/dz.png'}) - remove_tags=[dict(id='mat-podobne'), dict(name='a', attrs={'class':'czytajDalej'}), dict(attrs={'src':'http://nm.dz.com.pl/dz.png'})] + remove_tags=[dict(id='mat-podobne'), dict(name='a', attrs={'class':'czytajDalej'}), dict(attrs={'src':'http://nm.dz.com.pl/dz.png'}), dict(name='a', attrs={'href', 'http://www.gloswielkopolski.pl/newsletter/'})] feeds = [(u'Wszystkie', u'http://gloswielkopolski.feedsportal.com/c/32980/f/533779/index.rss?201302'), (u'Wiadomo\u015bci', u'http://gloswielkopolski.feedsportal.com/c/32980/f/533780/index.rss?201302'), (u'Sport', u'http://gloswielkopolski.feedsportal.com/c/32980/f/533781/index.rss?201302'), (u'Kultura', u'http://gloswielkopolski.feedsportal.com/c/32980/f/533782/index.rss?201302'), (u'Porady', u'http://www.gloswielkopolski.pl/rss/gloswielkopolski_porady.xml?201302'), (u'Blogi', u'http://www.gloswielkopolski.pl/rss/gloswielkopolski_blogi.xml?201302'), (u'Nasze akcje', u'http://www.gloswielkopolski.pl/rss/gloswielkopolski_naszeakcje.xml?201302'), (u'Opinie', u'http://www.gloswielkopolski.pl/rss/gloswielkopolski_opinie.xml?201302'), (u'Magazyn', u'http://www.gloswielkopolski.pl/rss/gloswielkopolski_magazyn.xml?201302')] diff --git a/recipes/kdefamily_pl.recipe b/recipes/kdefamily_pl.recipe index df0aacc2df..0e03ea75aa 100644 --- a/recipes/kdefamily_pl.recipe +++ b/recipes/kdefamily_pl.recipe @@ -12,5 +12,6 @@ class KDEFamilyPl(BasicNewsRecipe): max_articles_per_feed = 100 preprocess_regexps = [(re.compile(r"Podobne wpisy.*", re.IGNORECASE|re.DOTALL), lambda m: '')] no_stylesheets = True + remove_empty_feeds = True use_embedded_content = True feeds = [(u'Wszystko', u'http://kdefamily.pl/feed/')] \ No newline at end of file diff --git a/recipes/legeartis.recipe b/recipes/legeartis.recipe index 1b882c26d7..b2e1b0e782 100644 --- a/recipes/legeartis.recipe +++ b/recipes/legeartis.recipe @@ -21,7 +21,7 @@ class LegeArtisRecipe(BasicNewsRecipe): no_stylesheets = True remove_javascript = True - + remove_empty_feeds = True extra_css = ''' img{clear: both;} ''' diff --git a/recipes/lomza.recipe b/recipes/lomza.recipe index 2c31271624..ed5c513430 100644 --- a/recipes/lomza.recipe +++ b/recipes/lomza.recipe @@ -8,6 +8,7 @@ class Lomza(BasicNewsRecipe): language = 'pl' oldest_article = 15 no_stylesheets = True + extra_css = '#foto {float: right; max-width: 200px; margin-left: 10px;} #fotogaleria > div {float:left;} .br {clear: both;}' max_articles_per_feed = 100 remove_tags=[dict(name='div', attrs={'class':['bxbanner', 'drukuj', 'wyslijznajomemu']})] keep_only_tags=[dict(name='div', attrs={'class':'wiadomosc'})] diff --git a/recipes/pc_lab.recipe b/recipes/pc_lab.recipe index 7a6038bd65..e7c6bcb654 100644 --- a/recipes/pc_lab.recipe +++ b/recipes/pc_lab.recipe @@ -1,6 +1,6 @@ #!/usr/bin/env python from calibre.web.feeds.recipes import BasicNewsRecipe - +from calibre.ebooks.BeautifulSoup import Comment class PCLab(BasicNewsRecipe): cover_url = 'http://pclab.pl/img/logo.png' title = u"PC Lab" @@ -52,6 +52,9 @@ class PCLab(BasicNewsRecipe): pager = soup2.find('div', attrs={'class':'next'}) pagetext = soup2.find('div', attrs={'class':'substance'}) pagetext = pagetext.find('div', attrs={'class':'data'}) + comments = pagetext.findAll(text=lambda text:isinstance(text, Comment)) + for comment in comments: + comment.extract() pos = len(appendtag.contents) appendtag.insert(pos, pagetext) diff --git a/recipes/swiatkindle.recipe b/recipes/swiatkindle.recipe index c589d1b6e1..d5774898aa 100644 --- a/recipes/swiatkindle.recipe +++ b/recipes/swiatkindle.recipe @@ -10,7 +10,7 @@ import re from calibre.web.feeds.news import BasicNewsRecipe class swiatczytnikow(BasicNewsRecipe): - title = u'Swiat Czytnikow' + title = u'Świat Czytników' description = u'Czytniki e-książek w Polsce. Jak wybrać, kupić i korzystać z Amazon Kindle i innych' language = 'pl' __author__ = u'Tomasz D\u0142ugosz'