diff --git a/resources/recipes/nspm.recipe b/resources/recipes/nspm.recipe index c00e472636..7514e0727d 100644 --- a/resources/recipes/nspm.recipe +++ b/resources/recipes/nspm.recipe @@ -14,33 +14,39 @@ class Nspm(BasicNewsRecipe): description = 'Casopis za politicku teoriju i drustvena istrazivanja' publisher = 'NSPM' category = 'news, politics, Serbia' - oldest_article = 2 + oldest_article = 7 max_articles_per_feed = 100 no_stylesheets = True use_embedded_content = False INDEX = 'http://www.nspm.rs/?alphabet=l' encoding = 'utf-8' language = 'sr' + delay = 2 publication_type = 'magazine' masthead_url = 'http://www.nspm.rs/templates/jsn_epic_pro/images/logol.jpg' - extra_css = ' @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: "Times New Roman", serif1, serif} .article_description{font-family: Arial, sans1, sans-serif} img{margin-top:0.5em; margin-bottom: 0.7em} .author{color: #990000; font-weight: bold} .author,.createdate{font-size: 0.9em} img{margin-top:0.5em; margin-bottom: 0.7em} ' + extra_css = """ @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} + @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} + body{font-family: "Times New Roman", serif1, serif} + .article_description{font-family: Arial, sans1, sans-serif} + img{margin-top:0.5em; margin-bottom: 0.7em} + .author{color: #990000; font-weight: bold} + .author,.createdate{font-size: 0.9em} """ conversion_options = { - 'comment' : description - , 'tags' : category - , 'publisher' : publisher - , 'language' : language + 'comment' : description + , 'tags' : category + , 'publisher' : publisher + , 'language' : language + , 'linearize_tables' : True } preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] + keep_only_tags = [dict(attrs={'id':'jsn-mainbody'})] remove_tags = [ - dict(name=['link','object','embed','script','meta']) - ,dict(name='td', attrs={'class':'buttonheading'}) + dict(name=['link','object','embed','script','meta','base','iframe']) + ,dict(attrs={'class':'buttonheading'}) ] - keep_only_tags = [ - dict(attrs={'class':['contentpagetitle','author','createdate']}) - ,dict(name='p') - ] + remove_tags_after = dict(attrs={'class':'article_separator'}) remove_attributes = ['width','height'] def get_browser(self): @@ -48,25 +54,18 @@ class Nspm(BasicNewsRecipe): br.open(self.INDEX) return br - feeds = [(u'Nova srpska politicka misao', u'http://www.nspm.rs/feed/rss.html')] - - def print_version(self, url): - return url.replace('.html','/stampa.html') + feeds = [ + (u'Rubrike' , u'http://www.nspm.rs/rubrike/feed/rss.html') + ,(u'Debate' , u'http://www.nspm.rs/debate/feed/rss.html') + ,(u'Reci i misli' , u'http://www.nspm.rs/reci-i-misli/feed/rss.html') + ,(u'Samo smeh srbina spasava', u'http://www.nspm.rs/samo-smeh-srbina-spasava/feed/rss.html') + ,(u'Polemike' , u'http://www.nspm.rs/polemike/feed/rss.html') + ,(u'Prikazi' , u'http://www.nspm.rs/prikazi/feed/rss.html') + ,(u'Prenosimo' , u'http://www.nspm.rs/prenosimo/feed/rss.html') + ,(u'Hronika' , u'http://www.nspm.rs/tabela/hronika/feed/rss.html') + ] def preprocess_html(self, soup): for item in soup.body.findAll(style=True): del item['style'] - att = soup.find('a',attrs={'class':'contentpagetitle'}) - if att: - att.name = 'h1'; - del att['href'] - att2 = soup.find('td') - if att2: - att2.name = 'p'; - del att['valign'] - for pt in soup.findAll('img'): - brtag = Tag(soup,'br') - brtag2 = Tag(soup,'br') - pt.append(brtag) - pt.append(brtag2) - return soup + return self.adeify_images(soup) \ No newline at end of file diff --git a/resources/recipes/nspm_int.recipe b/resources/recipes/nspm_int.recipe index 99c1707938..c6f94d904a 100644 --- a/resources/recipes/nspm_int.recipe +++ b/resources/recipes/nspm_int.recipe @@ -1,7 +1,5 @@ -#!/usr/bin/env python - __license__ = 'GPL v3' -__copyright__ = '2008, Darko Miletic ' +__copyright__ = '2008-2010, Darko Miletic ' ''' nspm.rs/nspm-in-english ''' @@ -11,29 +9,44 @@ from calibre.web.feeds.news import BasicNewsRecipe class Nspm_int(BasicNewsRecipe): title = 'NSPM in English' __author__ = 'Darko Miletic' - description = 'Magazine dedicated to political theory and sociological research' - oldest_article = 20 + description = 'Magazine dedicated to political theory and sociological research' + publisher = 'NSPM' + category = 'news, politics, Serbia' + oldest_article = 7 max_articles_per_feed = 100 - language = 'en' - no_stylesheets = True use_embedded_content = False - INDEX = 'http://www.nspm.rs/?alphabet=l' - cover_url = 'http://nspm.rs/templates/jsn_epic_pro/images/logol.jpg' - html2lrf_options = [ - '--comment', description - , '--base-font-size', '10' - , '--category', 'news, politics, Serbia, english' - , '--publisher', 'IIC NSPM' - ] + encoding = 'utf-8' + language = 'en' + delay = 2 + publication_type = 'magazine' + masthead_url = 'http://www.nspm.rs/templates/jsn_epic_pro/images/logol.jpg' + extra_css = """ + body{font-family: "Times New Roman", serif} + .article_description{font-family: Arial, sans-serif} + img{margin-top:0.5em; margin-bottom: 0.7em} + .author{color: #990000; font-weight: bold} + .author,.createdate{font-size: 0.9em} """ - def get_browser(self): - br = BasicNewsRecipe.get_browser() - br.open(self.INDEX) - return br + conversion_options = { + 'comment' : description + , 'tags' : category + , 'publisher' : publisher + , 'language' : language + , 'linearize_tables' : True + } + keep_only_tags = [dict(attrs={'id':'jsn-mainbody'})] + remove_tags = [ + dict(name=['link','object','embed','script','meta','base','iframe']) + ,dict(attrs={'class':'buttonheading'}) + ] + remove_tags_after = dict(attrs={'class':'article_separator'}) + remove_attributes = ['width','height'] - keep_only_tags = [dict(name='div', attrs={'id':'jsn-mainbody'})] - remove_tags = [dict(name='div', attrs={'id':'yvComment' })] + feeds = [(u'Articles', u'http://www.nspm.rs/nspm-in-english/feed/rss.html')] - feeds = [ (u'NSPM in English', u'http://nspm.rs/nspm-in-english/feed/rss.html')] + def preprocess_html(self, soup): + for item in soup.body.findAll(style=True): + del item['style'] + return self.adeify_images(soup) \ No newline at end of file