mirror of
https://github.com/kovidgoyal/calibre.git
synced 2026-05-08 10:32:28 +00:00
Kovid Goyal
69 lines
2.9 KiB
Python
69 lines
2.9 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
sfgate.com
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
|
|
|
|
|
class SanFranciscoChronicle(BasicNewsRecipe):
|
|
title = u'San Francisco Chronicle'
|
|
__author__ = u'Kovid Goyal'
|
|
description = u'San Francisco news'
|
|
language = 'en_US'
|
|
|
|
oldest_article = 7
|
|
max_articles_per_feed = 20
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
delay = 1
|
|
|
|
extra_css = '''
|
|
h1{font-family :Arial,Helvetica,sans-serif; font-size:large;}
|
|
h2{font-family :Arial,Helvetica,sans-serif; font-size:medium; color:#666666;}
|
|
h3{font-family :Arial,Helvetica,sans-serif; font-size:medium; color:#000000;}
|
|
h4{font-family :Arial,Helvetica,sans-serif; font-size: x-small;}
|
|
p{font-family :Arial,Helvetica,sans-serif; font-size:x-small;}
|
|
.byline{font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
|
|
.date{font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
|
|
.dtlcomment{font-style:italic;}
|
|
.georgia h3{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#000000;}
|
|
'''
|
|
keep_only_tags = [
|
|
dict(name='h1'),
|
|
dict(**classes('package')),
|
|
]
|
|
remove_tags = [
|
|
dict(id=['badge-logo', 'everlit-auto-audio-widget']),
|
|
dict(name='svg'),
|
|
dict(attrs={'data-eid': lambda x: x and (
|
|
'news_alert_bar' in x or 'card' in x or 'mostPopular' in x or 'dynamic_thumbnail_list' in x)}),
|
|
dict(href=lambda x: x and 'california-mini-crossword' in x),
|
|
dict(attrs={'data-block-type': 'embed'}),
|
|
dict(name='img', width='1'),
|
|
]
|
|
|
|
feeds = [
|
|
(u'Bay Area News', u'https://www.sfgate.com/bayarea/feed/Bay-Area-News-429.php'),
|
|
(u'City Insider', u'https://www.sfgate.com/default/feed/City-Insider-Blog-573.php'),
|
|
(u'Crime Scene', u'https://www.sfgate.com/rss/feed/Crime-Scene-Blog-599.php'),
|
|
(u'Education News',
|
|
u'https://www.sfgate.com/education/feed/Education-News-from-SFGate-430.php'),
|
|
(u'National News', u'https://www.sfgate.com/rss/feed/National-News-RSS-Feed-435.php'),
|
|
(u'Weird News', u'https://www.sfgate.com/weird/feed/Weird-News-RSS-Feed-433.php'),
|
|
(u'World News', u'https://www.sfgate.com/rss/feed/World-News-From-SFGate-432.php'),
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
for picture in soup.find_all('picture'):
|
|
img = picture.find('img')
|
|
if img:
|
|
for i, source in enumerate(picture.find_all('source')):
|
|
if i == 0:
|
|
img['src'] = source['srcset'].split()[0]
|
|
source.extract()
|
|
return soup
|