mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
889fc123e1
Fixes #1698646 [Failed: Fetch news from New York Times](https://bugs.launchpad.net/calibre/+bug/1698646)
120 lines
4.5 KiB
Python
120 lines
4.5 KiB
Python
#!/usr/bin/env python2
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
|
|
__docformat__ = 'restructuredtext en'
|
|
|
|
'''
|
|
espn.com
|
|
'''
|
|
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ptempfile import TemporaryFile
|
|
|
|
|
|
class ESPN(BasicNewsRecipe):
|
|
|
|
title = 'ESPN'
|
|
description = 'Sports news'
|
|
__author__ = 'Kovid Goyal and Sujata Raman'
|
|
language = 'en'
|
|
no_stylesheets = True
|
|
|
|
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')
|
|
]
|
|
|
|
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',
|
|
# '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'
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
for div in soup.findAll('div'):
|
|
if div.has_key('style') and 'px' in div['style']: # noqa
|
|
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 self.username and self.password:
|
|
br.set_handle_refresh(False)
|
|
url = ('https://r.espn.go.com/members/v3_1/login')
|
|
raw = br.open(url).read()
|
|
raw = re.sub(r'(?s)<form>.*?id="regsigninbtn".*?</form>', '', raw)
|
|
with TemporaryFile(suffix='.htm') as fname:
|
|
with open(fname, 'wb') as f:
|
|
f.write(raw)
|
|
br.open_local_file(fname)
|
|
|
|
br.form = list(br.forms())[0]
|
|
br.form.find_control(
|
|
name='username', type='text').value = self.username
|
|
br.form['password'] = self.password
|
|
br.submit().read()
|
|
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
|