Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

pep8

Browse Source
This commit is contained in:
Kovid Goyal 2014-03-19 09:40:29 +05:30
parent 0e36f48c19
commit 6e81aa8442
1 changed files with 33 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

56
recipes/guardian.recipe
View File

@ -48,14 +48,14 @@ class Guardian(BasicNewsRecipe):
# article history link
dict(name='a', attrs={'class':["rollover history-link"]}),
# "a version of this article ..." speil
dict(name='div' , attrs = { 'class' : ['section']}),
dict(name='div' , attrs={'class' : ['section']}),
# "about this article" js dialog
dict(name='div', attrs={'class':["share-top",]}),
# author picture
dict(name='img', attrs={'class':["contributor-pic-small"]}),
# embedded videos/captions
dict(name='span',attrs={'class' : ['inline embed embed-media']}),
#dict(name='img'),
# dict(name='img'),
]
use_embedded_content = False
@ -72,12 +72,12 @@ class Guardian(BasicNewsRecipe):
'''
def get_article_url(self, article):
url = article.get('guid', None)
if '/video/' in url or '/flyer/' in url or '/quiz/' in url or \
'/gallery/' in url or 'ivebeenthere' in url or \
'pickthescore' in url or 'audioslideshow' in url :
url = None
return url
url = article.get('guid', None)
if '/video/' in url or '/flyer/' in url or '/quiz/' in url or \
'/gallery/' in url or 'ivebeenthere' in url or \
'pickthescore' in url or 'audioslideshow' in url :
url = None
return url
def populate_article_metadata(self, article, soup, first):
if first and hasattr(self, 'add_toc_thumbnail'):
@ -87,39 +87,39 @@ class Guardian(BasicNewsRecipe):
def preprocess_html(self, soup):
# multiple html sections in soup, useful stuff in the first
html = soup.find('html')
soup2 = BeautifulSoup()
soup2.insert(0,html)
# multiple html sections in soup, useful stuff in the first
html = soup.find('html')
soup2 = BeautifulSoup()
soup2.insert(0,html)
soup = soup2
soup = soup2
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll(face=True):
del item['face']
for tag in soup.findAll(name=['ul','li']):
tag.name = 'div'
for item in soup.findAll(face=True):
del item['face']
for tag in soup.findAll(name=['ul','li']):
tag.name = 'div'
# removes number next to rating stars
items_to_remove = []
rating_container = soup.find('div', attrs = {'class': ['rating-container']})
if rating_container:
# removes number next to rating stars
items_to_remove = []
rating_container = soup.find('div', attrs={'class': ['rating-container']})
if rating_container:
for item in rating_container:
if isinstance(item, Tag) and str(item.name) == 'span':
items_to_remove.append(item)
for item in items_to_remove:
for item in items_to_remove:
item.extract()
return soup
return soup
def find_sections(self):
# soup = self.index_to_soup("http://www.guardian.co.uk/theobserver")
soup = self.index_to_soup(self.base_url)
# find cover pic
img = soup.find( 'img',attrs ={'alt':self.cover_pic})
img = soup.find('img',attrs={'alt':self.cover_pic})
if img is not None:
self.cover_url = img['src']
# end find cover pic
@ -149,7 +149,8 @@ class Guardian(BasicNewsRecipe):
continue
tt = li.find('div', attrs={'class':'trailtext'})
if tt is not None:
for da in tt.findAll('a'): da.extract()
for da in tt.findAll('a'):
da.extract()
desc = self.tag_to_string(tt).strip()
yield {
'title': title, 'url':url, 'description':desc,
@ -161,4 +162,3 @@ class Guardian(BasicNewsRecipe):
for title, href in self.find_sections():
feeds.append((title, list(self.find_articles(href))))
return feeds