mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
113 lines
4.1 KiB
Python
113 lines
4.1 KiB
Python
#!/usr/bin/env python
|
|
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
use_wayback_machine = False
|
|
|
|
|
|
class NYTimesTechnology(BasicNewsRecipe):
|
|
title = 'New York Times Technology Beat'
|
|
language = 'en_US'
|
|
description = 'The latest in technology - Gadgetwise'
|
|
__author__ = 'unkn0wn'
|
|
oldest_article = 14 # days
|
|
no_stylesheets = True
|
|
no_javascript = True
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
encoding = 'utf-8'
|
|
|
|
extra_css = '''
|
|
.byl, .time { font-size:small; color:#202020; }
|
|
.cap { font-size:small; text-align:center; }
|
|
.cred { font-style:italic; font-size:small; }
|
|
em, blockquote { color: #202020; }
|
|
.sc { font-variant: small-caps; }
|
|
.lbl { font-size:small; color:#404040; }
|
|
img { display:block; margin:0 auto; }
|
|
'''
|
|
|
|
articles_are_obfuscated = use_wayback_machine
|
|
|
|
if use_wayback_machine:
|
|
def get_obfuscated_article(self, url):
|
|
from calibre.ptempfile import PersistentTemporaryFile
|
|
with PersistentTemporaryFile() as tf:
|
|
tf.write(self.get_nyt_page(url))
|
|
return tf.name
|
|
|
|
@property
|
|
def nyt_parser(self):
|
|
ans = getattr(self, '_nyt_parser', None)
|
|
if ans is None:
|
|
from calibre.live import load_module
|
|
self._nyt_parser = ans = load_module('calibre.web.site_parsers.nytimes')
|
|
return ans
|
|
|
|
def get_nyt_page(self, url, skip_wayback=False):
|
|
if use_wayback_machine and not skip_wayback:
|
|
from calibre import browser
|
|
return self.nyt_parser.download_url(url, browser())
|
|
return self.index_to_soup(url, raw=True)
|
|
|
|
def preprocess_raw_html(self, raw_html, url):
|
|
if '/interactive/' in url:
|
|
return '<html><body><p><em>'\
|
|
+ 'This is an interactive article, which is supposed to be read in a browser.'\
|
|
+ '</p></em></body></html>'
|
|
html = self.nyt_parser.extract_html(self.index_to_soup(raw_html))
|
|
return html
|
|
|
|
recipe_specific_options = {
|
|
'days': {
|
|
'short': 'Oldest article to download from this news source. In days ',
|
|
'long': 'For example, 0.5, gives you articles from the past 12 hours',
|
|
'default': str(oldest_article)
|
|
},
|
|
'res': {
|
|
'short': 'For hi-res images, select a resolution from the following\noptions: popup, jumbo, mobileMasterAt3x, superJumbo',
|
|
'long': 'This is useful for non e-ink devices, and for a lower file size\nthan the default, use articleInline.',
|
|
},
|
|
'comp': {
|
|
'short': 'Compress News Images?',
|
|
'long': 'enter yes',
|
|
'default': 'no'
|
|
}
|
|
}
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
BasicNewsRecipe.__init__(self, *args, **kwargs)
|
|
c = self.recipe_specific_options.get('comp')
|
|
if c and isinstance(c, str):
|
|
if c.lower() == 'yes':
|
|
self.compress_news_images = True
|
|
d = self.recipe_specific_options.get('days')
|
|
if d and isinstance(d, str):
|
|
self.oldest_article = float(d)
|
|
|
|
feeds = [
|
|
(u'Gadgetwise', u'http://gadgetwise.blogs.nytimes.com/feed/'),
|
|
]
|
|
|
|
def get_browser(self, *args, **kwargs):
|
|
kwargs['user_agent'] = 'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)'
|
|
br = BasicNewsRecipe.get_browser(self, *args, **kwargs)
|
|
br.addheaders += [
|
|
('Referer', 'https://www.google.com/'),
|
|
('X-Forwarded-For', '66.249.66.1')
|
|
]
|
|
return br
|
|
|
|
def preprocess_html(self, soup):
|
|
w = self.recipe_specific_options.get('res')
|
|
if w and isinstance(w, str):
|
|
res = '-' + w
|
|
for img in soup.findAll('img', attrs={'src':True}):
|
|
if '-article' in img['src']:
|
|
ext = img['src'].split('?')[0].split('.')[-1]
|
|
img['src'] = img['src'].rsplit('-article', 1)[0] + res + '.' + ext
|
|
for c in soup.findAll('div', attrs={'class':'cap'}):
|
|
for p in c.findAll(['p', 'div']):
|
|
p.name = 'span'
|
|
return soup
|