mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
67 lines
2.5 KiB
Plaintext
67 lines
2.5 KiB
Plaintext
import re
|
|
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
|
|
|
|
class TNR(BasicNewsRecipe):
|
|
|
|
title = 'The New Republic'
|
|
__author__ = 'Krittika Goyal'
|
|
|
|
description = '''The New Republic is a journal of opinion with an emphasis
|
|
on politics and domestic and international affairs. It carries feature
|
|
articles by staff and contributing editors. The second half of each issue
|
|
is devoted to book and the arts, theater, motion pictures, music and art.'''
|
|
|
|
language = 'en'
|
|
encoding = 'UTF-8'
|
|
needs_subscription = True
|
|
|
|
preprocess_regexps = [
|
|
(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: ''),
|
|
(re.compile(r'<script.*?</script>', re.DOTALL), lambda m: ''),
|
|
]
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser(self)
|
|
br.open('http://www.newrepublic.com/user')
|
|
br.select_form(nr=1)
|
|
try:
|
|
br['user'] = self.username
|
|
except:
|
|
br['name'] = self.username
|
|
br['pass'] = self.password
|
|
self.log('Logging in...')
|
|
raw = br.submit().read()
|
|
if b'SIGN OUT' not in raw:
|
|
raise ValueError(
|
|
'Failed to log in to tnr.com, check your username and password')
|
|
self.log('Logged in successfully')
|
|
return br
|
|
|
|
def parse_index(self):
|
|
raw = self.index_to_soup(
|
|
'http://www.newrepublic.com/current-issue', raw=True)
|
|
# raw = self.index_to_soup(open('/t/raw.html').read().decode('utf-8'), raw=True)
|
|
for pat, sub in self.preprocess_regexps:
|
|
raw = pat.sub(sub, raw)
|
|
soup = self.index_to_soup(raw)
|
|
feed_title = 'The New Republic Magazine Articles'
|
|
|
|
articles = []
|
|
for div in soup.findAll('div', attrs={'class': lambda x: x and 'field-item' in x.split()}):
|
|
a = div.find('a', href=True, attrs={
|
|
'class': lambda x: x != 'author'})
|
|
if a is not None:
|
|
art_title = self.tag_to_string(a)
|
|
url = a.get('href')
|
|
num = re.search(r'/(\d+)/', url)
|
|
if num is not None:
|
|
art = num.group(1)
|
|
url = 'http://www.newrepublic.com/node/%s/print' % art
|
|
self.log.info('\tFound article:', art_title, 'at', url)
|
|
article = {'title': art_title, 'url': url,
|
|
'description': '', 'date': ''}
|
|
articles.append(article)
|
|
|
|
return [(feed_title, articles)]
|