diff --git a/recipes/wired.recipe b/recipes/wired.recipe index 965d8a82ac..aacbd903d9 100644 --- a/recipes/wired.recipe +++ b/recipes/wired.recipe @@ -1,9 +1,8 @@ __license__ = 'GPL v3' -__copyright__ = '2012, mkydgr' +__copyright__ = '2010-2013, Darko Miletic ' ''' www.wired.com -based on the (broken) built-in recipe by Darko Miletic ''' import re @@ -12,12 +11,11 @@ from calibre.web.feeds.news import BasicNewsRecipe class Wired(BasicNewsRecipe): title = 'Wired Magazine' - __author__ = 'mkydgr' - description = 'Technology News' + __author__ = 'Darko Miletic' + description = 'Gaming news' publisher = 'Conde Nast Digital' - category = '' - oldest_article = 500 - delay = 1 + category = 'news, games, IT, gadgets' + oldest_article = 32 max_articles_per_feed = 100 no_stylesheets = True encoding = 'utf-8' @@ -25,10 +23,16 @@ class Wired(BasicNewsRecipe): masthead_url = 'http://www.wired.com/images/home/wired_logo.gif' language = 'en' publication_type = 'magazine' - extra_css = ' body{font-family: Arial,Verdana,sans-serif} .entryDescription li {display: inline; list-style-type: none} ' - index = 'http://www.wired.com/magazine' - departments = ['features','start','test','play','found', 'reviews'] - + extra_css = """ + h1, .entry-header{font-family: brandon-grotesque,anchor-web,Helvetica,Arial,sans-serif} + .entry-header{display: block;} + .entry-header ul{ list-style-type:disc;} + .author, .entryDate, .entryTime, .entryEdit, .entryCategories{display: inline} + .entry-header li{text-transform: uppercase;} + div#container{font-family: 'Exchange SSm 4r', Georgia, serif} + """ + index = 'http://www.wired.com/magazine/' + preprocess_regexps = [(re.compile(r'', re.DOTALL|re.IGNORECASE),lambda match: '')] conversion_options = { 'comment' : description @@ -38,56 +42,37 @@ class Wired(BasicNewsRecipe): } keep_only_tags = [dict(name='div', attrs={'class':'post'})] - remove_tags_after = dict(name='div', attrs={'class':'tweetmeme_button'}) + remove_tags_after = dict(name='div', attrs={'id':'container'}) remove_tags = [ - dict(name=['object','embed','iframe','link']) - ,dict(name='div', attrs={'class':['podcast_storyboard','tweetmeme_button']}) + dict(name=['object','embed','iframe','link','meta','base']) + ,dict(name='div', attrs={'class':['social-top','podcast_storyboard','tweetmeme_button']}) ,dict(attrs={'id':'ff_bottom_nav'}) ,dict(name='a',attrs={'href':'http://www.wired.com/app'}) + ,dict(name='div', attrs={'id':'mag-bug'}) ] - remove_attributes = ['height','width'] + remove_attributes = ['height','width','lang','border','clear'] def parse_index(self): totalfeeds = [] - soup = self.index_to_soup(self.index) - - #department feeds - depts = soup.find('div',attrs={'id':'department-posts'}) - - if depts: - for ditem in self.departments: - darticles = [] - department = depts.find('h3',attrs={'id':'department-'+ditem}) - if department: - #print '\n###### Found department %s ########'%(ditem) - - el = department.next - while el and (el.__class__.__name__ == 'NavigableString' or el.name != 'h3'): - if el.__class__.__name__ != 'NavigableString': - #print '\t ... element',el.name - if el.name == 'ul': - for artitem in el.findAll('li'): - #print '\t\t ... article',repr(artitem) - feed_link = artitem.find('a') - #print '\t\t\t ... link',repr(feed_link) - if feed_link and feed_link.has_key('href'): - url = self.makeurl(feed_link['href']) - title = self.tag_to_string(feed_link) - date = strftime(self.timefmt) - #print '\t\t ... found "%s" %s'%(title,url) - darticles.append({ - 'title' :title - ,'date' :date - ,'url' :url - ,'description':'' - }) - el = None - else: - el = el.next - - totalfeeds.append((ditem.capitalize(), darticles)) + majorf = soup.find('div',attrs={'class':'entry'}) + if majorf: + articles = [] + checker = [] + for a in majorf.findAll('a', href=True): + if a['href'].startswith('http://www.wired.com/') and a['href'].endswith('/'): + title = self.tag_to_string(a) + url = a['href'] + if title.lower() != 'read more' and url not in checker: + checker.append(url) + articles.append({ + 'title' :title + ,'date' :strftime(self.timefmt) + ,'url' :a['href'] + ,'description':'' + }) + totalfeeds.append(('Articles', articles)) return totalfeeds def get_cover_url(self): @@ -95,7 +80,7 @@ class Wired(BasicNewsRecipe): soup = self.index_to_soup(self.index) cover_item = soup.find('div',attrs={'class':'spread-image'}) if cover_item: - cover_url = self.makeurl(cover_item.a.img['src']) + cover_url = 'http://www.wired.com' + cover_item.a.img['src'] return cover_url def print_version(self, url): @@ -104,10 +89,19 @@ class Wired(BasicNewsRecipe): def preprocess_html(self, soup): for item in soup.findAll(style=True): del item['style'] + for item in soup.findAll('a'): + if item.string is not None: + tstr = item.string + item.replaceWith(tstr) + else: + item.name='span' + for atrs in ['href','target','alt','title','name','id']: + if item.has_key(atrs): + del item[atrs] + for item in soup.findAll('img'): + if not item.has_key('alt'): + item['alt'] = 'image' + if item.has_key('data-lazy-src'): + item['src'] = item['data-lazy-src'] + del item['data-lazy-src'] return soup - - def makeurl(self, addr): - if addr[:4] != 'http' : addr='http://www.wired.com' + addr - while addr[-2:] == '//' : addr=addr[:-1] - return addr -