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

Fix ESPN download

Browse Source
This commit is contained in:
Kovid Goyal 2009-07-28 15:33:31 -06:00
parent 1f5a1fac4f
commit 9132c638a6
1 changed files with 11 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
src/calibre/web/feeds/recipes/recipe_espn.py
View File

@ -10,18 +10,17 @@ import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class ESPN(BasicNewsRecipe): class ESPN(BasicNewsRecipe):
title = 'ESPN' title = 'ESPN'
description = 'Sports news' description = 'Sports news'
__author__ = 'Kovid Goyal' __author__ = 'Kovid Goyal'
language = _('English') language = _('English')
needs_subscription = True needs_subscription = True
remove_tags = [dict(name='font', attrs={'class':'footer'}), dict(name='hr', noshade='noshade')] remove_tags = [dict(name='font', attrs={'class':'footer'}), dict(name='hr', noshade='noshade')]
remove_tags_before = dict(name='font', attrs={'class':'date'}) remove_tags_before = dict(name='font', attrs={'class':'date'})
center_navbar = False center_navbar = False
html2lrf_options = ['--base-font-size', '0']
feeds = [('Top Headlines', 'http://sports.espn.go.com/espn/rss/news'), 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/nfl/news',
'http://sports.espn.go.com/espn/rss/nba/news', 'http://sports.espn.go.com/espn/rss/nba/news',
@ -39,37 +38,37 @@ class ESPN(BasicNewsRecipe):
'http://sports.espn.go.com/espn/rss/bassmaster/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/oly/news',
'http://sports.espn.go.com/espn/rss/horse/news'] 'http://sports.espn.go.com/espn/rss/horse/news']
def get_browser(self): def get_browser(self):
br = BasicNewsRecipe.get_browser() br = BasicNewsRecipe.get_browser()
br.set_handle_refresh(False) br.set_handle_refresh(False)
if self.username is not None and self.password is not None: if self.username is not None and self.password is not None:
br.open('http://espn.com') br.open('http://espn.com')
br.select_form(nr=0) br.select_form(nr=1)
br.form.find_control(name='username', type='text').value = self.username br.form.find_control(name='username', type='text').value = self.username
br.form['password'] = self.password br.form['password'] = self.password
br.submit() br.submit()
br.set_handle_refresh(True) br.set_handle_refresh(True)
return br return br
def print_version(self, url): def print_version(self, url):
if 'eticket' in url: if 'eticket' in url:
return url.partition('&')[0].replace('story?', 'print?') return url.partition('&')[0].replace('story?', 'print?')
match = re.search(r'story\?(id=\d+)', url) match = re.search(r'story\?(id=\d+)', url)
if match: if match:
return 'http://sports.espn.go.com/espn/print?'+match.group(1)+'&type=story' return 'http://sports.espn.go.com/espn/print?'+match.group(1)+'&type=story'
return None return None
def preprocess_html(self, soup): def preprocess_html(self, soup):
for div in soup.findAll('div'): for div in soup.findAll('div'):
if div.has_key('style') and 'px' in div['style']: if div.has_key('style') and 'px' in div['style']:
div['style'] = '' div['style'] = ''
return soup return soup
def postprocess_html(self, soup, first_fetch): def postprocess_html(self, soup, first_fetch):
for div in soup.findAll('div', style=True): for div in soup.findAll('div', style=True):
div['style'] = div['style'].replace('center', 'left') div['style'] = div['style'].replace('center', 'left')
return soup return soup