Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 02:34:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

quick fix for fronda - just populate article list and get the first page of article content

Browse Source
This commit is contained in:
Tomasz Długosz 2014-04-28 00:03:03 +02:00
parent 3ab8d26ac2
commit 73ed9f1268
1 changed files with 9 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
recipes/fronda.recipe
View File

@ -62,34 +62,25 @@ class Fronda(BasicNewsRecipe):
except:
continue
articles[genName] = []
for item in soup.findAll('li'):
article_h = item.find('h2')
if not article_h:
continue
article_date = self.tag_to_string(item.find('b'))
if self.date_cut(article_date):
continue
article_a = article_h.find('a')
for item in soup.findAll('article',attrs={'class':'article article-wide'}):
article_a = item.find('a')
article_url = 'http://www.fronda.pl' + article_a['href']
article_title = self.tag_to_string(article_a)
articles[genName].append( { 'title' : article_title, 'url' : article_url, 'date' : article_date })
articles[genName].append( { 'title' : article_title, 'url' : article_url })
if articles[genName]:
feeds.append((genName, articles[genName]))
return feeds
keep_only_tags = [
dict(name='div', attrs={'class':'yui-g'})
dict(name='div', attrs={'class':'content content-70 phone-100'})
]
remove_tags = [
dict(name='div', attrs={'class':['related-articles','button right','pagination','related-articles content']}),
dict(name='h3', attrs={'class':'block-header article comments'}),
dict(name='ul', attrs={'class':['comment-list','category','tag-list']}),
dict(name='p', attrs={'id':'comments-disclaimer'}),
dict(name='div', attrs={'style':'text-align: left; margin-bottom: 15px;'}),
dict(name='div', attrs={'style':'text-align: left; margin-top: 15px; margin-bottom: 30px;'}),
dict(name='div', attrs={'id':'comment-form'}),
dict(name='span', attrs={'class':'separator'})
dict(name='div', attrs={'class':['clearfix','last-articles clearfix','comments clearfix','related-articles','social-buttons clearfix']}),
dict(name='span', attrs={'class':'small-info'}),
dict(name='ul', attrs={'class':'nav nav-tags clearfix'}),
dict(name='h3', attrs={'class':'section-header'}),
dict(name='article', attrs={'class':['slided-article hidden-phone', 'article article-wide hidden-phone']})
]
preprocess_regexps = [