Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update ESPN

Browse Source
This commit is contained in:
Kovid Goyal 2020-08-08 16:03:12 +05:30
parent 5c23956001
commit c88b4b091a
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 28 additions and 68 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

96
recipes/espn.recipe
View File

@ -11,6 +11,12 @@ from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ptempfile import TemporaryFile
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class ESPN(BasicNewsRecipe):
title = 'ESPN'
@ -22,58 +28,35 @@ class ESPN(BasicNewsRecipe):
use_embedded_content = False
remove_javascript = True
needs_subscription = 'optional'
encoding = 'ISO-8859-1'
remove_tags_before = dict(name='font', attrs={'class': 'date'})
center_navbar = False
remove_tags = [
dict(name='font', attrs={'class': 'footer'}), dict(
name='hr', noshade='noshade'),
dict(name='img', src='/winnercomm/horseracing/DRF.jpg')
keep_only_tags = [
classes('article-header article-body'),
]
remove_tags = [
classes('ad-slot article-social'),
]
extra_css = '''
body{font-family:Verdana,Arial,Helvetica,sans-serif; font-size:x-small; font-weight:normal;}
.subhead{color:#666666;font-family:Verdana,sans-serif; font-size:x-small; font-weight:bold;}
.clearfix{font-family:Verdana,sans-serif; font-size:xx-small; }
.date{ font-family:Verdana,Arial,Helvetica,sans-serif ; font-size:xx-small;color:#7A7A7A;}
.byline{ font-family:Verdana,Arial,Helvetica,sans-serif ; font-size:xx-small;color:#666666;}
.headline{font-family:Verdana,Arial,Helvetica,sans-serif ; font-size:large; font-weight:bold;}
'''
feeds = [
('Top Headlines', 'http://sports.espn.go.com/espn/rss/news'),
'http://sports.espn.go.com/espn/rss/nfl/news',
'http://sports.espn.go.com/espn/rss/nba/news',
'http://sports.espn.go.com/espn/rss/mlb/news',
'http://sports.espn.go.com/espn/rss/nhl/news',
'http://sports.espn.go.com/espn/rss/golf/news',
'http://sports.espn.go.com/espn/rss/rpm/news',
'http://sports.espn.go.com/espn/rss/tennis/news',
'http://sports.espn.go.com/espn/rss/boxing/news',
'http://soccernet.espn.go.com/rss/news',
'http://sports.espn.go.com/espn/rss/ncb/news',
'http://sports.espn.go.com/espn/rss/ncf/news',
'http://sports.espn.go.com/espn/rss/ncaa/news',
'http://sports.espn.go.com/espn/rss/outdoors/news',
('Top Headlines', 'https://www.espn.com/espn/rss/news'),
'https://www.espn.com/espn/rss/nfl/news',
'https://www.espn.com/espn/rss/nba/news',
'https://www.espn.com/espn/rss/mlb/news',
'https://www.espn.com/espn/rss/nhl/news',
'https://www.espn.com/espn/rss/golf/news',
'https://www.espn.com/espn/rss/rpm/news',
'https://www.espn.com/espn/rss/tennis/news',
'https://www.espn.com/espn/rss/boxing/news',
'https://www.espn.com/espn/rss/soccer/news',
# 'http://soccernet.espn.go.com/rss/news',
'https://www.espn.com/espn/rss/ncb/news',
'https://www.espn.com/espn/rss/ncf/news',
'https://www.espn.com/espn/rss/ncaa/news',
# 'https://www.espn.com/espn/rss/outdoors/news',
# 'http://sports.espn.go.com/espn/rss/bassmaster/news',
'http://sports.espn.go.com/espn/rss/oly/news',
'http://sports.espn.go.com/espn/rss/horse/news'
'https://www.espn.com/espn/rss/oly/news',
'https://www.espn.com/espn/rss/horse/news'
]
def preprocess_html(self, soup):
for div in soup.findAll('div', style=True):
if 'px' in div['style']:
div['style'] = ''
return soup
def postprocess_html(self, soup, first_fetch):
for div in soup.findAll('div', style=True):
div['style'] = div['style'].replace('center', 'left')
return soup
def get_browser(self):
br = BasicNewsRecipe.get_browser(self)
if False and self.username and self.password:
@ -96,26 +79,3 @@ class ESPN(BasicNewsRecipe):
br.open('http://espn.go.com').read()
br.set_handle_refresh(True)
return br
def get_article_url(self, article):
return article.get('guid', None)
def print_version(self, url):
if 'eticket' in url:
return url.partition('&')[0].replace('story?', 'print?')
match = re.search(r'story\?(id=\d+)', url)
if match and 'soccernet' not in url and 'bassmaster' not in url:
return 'http://sports.espn.go.com/espn/print?' + match.group(1) + '&type=story'
else:
if 'soccernet' in url:
match = re.search(r'/id/(\d+)/', url)
if match:
return \
'http://soccernet.espn.go.com/print?id=%s&type=story' % match.group(
1)
# else:
# if 'bassmaster' in url:
# return url
return None