diff --git a/recipes/wired.recipe b/recipes/wired.recipe index bb9a97f5c4..965d8a82ac 100644 --- a/recipes/wired.recipe +++ b/recipes/wired.recipe @@ -1,8 +1,9 @@ __license__ = 'GPL v3' -__copyright__ = '2010, Darko Miletic ' +__copyright__ = '2012, mkydgr' ''' www.wired.com +based on the (broken) built-in recipe by Darko Miletic ''' import re @@ -11,11 +12,11 @@ from calibre.web.feeds.news import BasicNewsRecipe class Wired(BasicNewsRecipe): title = 'Wired Magazine' - __author__ = 'Darko Miletic' - description = 'Gaming news' + __author__ = 'mkydgr' + description = 'Technology News' publisher = 'Conde Nast Digital' - category = 'news, games, IT, gadgets' - oldest_article = 32 + category = '' + oldest_article = 500 delay = 1 max_articles_per_feed = 100 no_stylesheets = True @@ -25,8 +26,9 @@ class Wired(BasicNewsRecipe): 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/' - + index = 'http://www.wired.com/magazine' + departments = ['features','start','test','play','found', 'reviews'] + preprocess_regexps = [(re.compile(r'', re.DOTALL|re.IGNORECASE),lambda match: '')] conversion_options = { 'comment' : description @@ -38,80 +40,53 @@ class Wired(BasicNewsRecipe): keep_only_tags = [dict(name='div', attrs={'class':'post'})] remove_tags_after = dict(name='div', attrs={'class':'tweetmeme_button'}) remove_tags = [ - dict(name=['object','embed','iframe','link','meta','base']) + dict(name=['object','embed','iframe','link']) ,dict(name='div', attrs={'class':['podcast_storyboard','tweetmeme_button']}) ,dict(attrs={'id':'ff_bottom_nav'}) ,dict(name='a',attrs={'href':'http://www.wired.com/app'}) ] - remove_attributes = ['height','width','lang','border','clear'] + remove_attributes = ['height','width'] def parse_index(self): totalfeeds = [] soup = self.index_to_soup(self.index) - majorf = soup.find('div',attrs={'class':'index'}) - if majorf: - pfarticles = [] - firsta = majorf.find(attrs={'class':'spread-header'}) - if firsta: - pfarticles.append({ - 'title' :self.tag_to_string(firsta.a) - ,'date' :strftime(self.timefmt) - ,'url' :'http://www.wired.com' + firsta.a['href'] - ,'description':'' - }) - for itt in majorf.findAll('li'): - itema = itt.find('a',href=True) - if itema: - pfarticles.append({ - 'title' :self.tag_to_string(itema) - ,'date' :strftime(self.timefmt) - ,'url' :'http://www.wired.com' + itema['href'] - ,'description':'' - }) - totalfeeds.append(('Cover', pfarticles)) - features = soup.find('div',attrs={'id':'my-glider'}) - if features: - farticles = [] - for item in features.findAll('div',attrs={'class':'section'}): - divurl = item.find('div',attrs={'class':'feature-header'}) - if divurl: - divdesc = item.find('div',attrs={'class':'feature-text'}) - url = divurl.a['href'] - if not divurl.a['href'].startswith('http://www.wired.com'): - url = 'http://www.wired.com' + divurl.a['href'] - title = self.tag_to_string(divurl.a) - description = self.tag_to_string(divdesc) - date = strftime(self.timefmt) - farticles.append({ - 'title' :title - ,'date' :date - ,'url' :url - ,'description':description - }) - totalfeeds.append(('Featured Articles', farticles)) - #department feeds - departments = ['rants','start','test','play','found'] - dept = soup.find('div',attrs={'id':'magazine-departments'}) - if dept: - for ditem in departments: + + #department feeds + depts = soup.find('div',attrs={'id':'department-posts'}) + + if depts: + for ditem in self.departments: darticles = [] - department = dept.find('div',attrs={'id':'department-'+ditem}) + department = depts.find('h3',attrs={'id':'department-'+ditem}) if department: - for item in department.findAll('div'): - description = '' - feed_link = item.find('a') - if feed_link and feed_link.has_key('href'): - url = feed_link['href'] - title = self.tag_to_string(feed_link) - date = strftime(self.timefmt) - darticles.append({ - 'title' :title - ,'date' :date - ,'url' :url - ,'description':description - }) + #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)) return totalfeeds @@ -120,7 +95,7 @@ class Wired(BasicNewsRecipe): soup = self.index_to_soup(self.index) cover_item = soup.find('div',attrs={'class':'spread-image'}) if cover_item: - cover_url = 'http://www.wired.com' + cover_item.a.img['src'] + cover_url = self.makeurl(cover_item.a.img['src']) return cover_url def print_version(self, url): @@ -129,17 +104,10 @@ 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' return soup + + def makeurl(self, addr): + if addr[:4] != 'http' : addr='http://www.wired.com' + addr + while addr[-2:] == '//' : addr=addr[:-1] + return addr