| 1 |
# -*- mode: python -*- |
| 2 |
# -*- coding: utf-8 -*- |
| 3 |
# vi: set fenc=utf-8 ft=python : |
| 4 |
# kate: encoding utf-8; syntax python; |
| 5 |
|
| 6 |
__license__ = 'GPL v3' |
| 7 |
__copyright__ = '2019, Darko Miletic <darko.miletic at gmail.com>' |
| 8 |
''' |
| 9 |
www.newcriterion.com |
| 10 |
''' |
| 11 |
|
| 12 |
from calibre import strftime |
| 13 |
from calibre.ptempfile import PersistentTemporaryFile |
| 14 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 15 |
|
| 16 |
|
| 17 |
class TheNewCriterion(BasicNewsRecipe): |
| 18 |
title = 'The New Criterion' |
| 19 |
__author__ = 'Darko Miletic' |
| 20 |
description = 'On the front lines of the battle for culture' |
| 21 |
publisher = 'The Foundation for Cultural Review' |
| 22 |
category = 'art, politics, USA, world' |
| 23 |
oldest_article = 40 |
| 24 |
no_stylesheets = True |
| 25 |
encoding = 'utf8' |
| 26 |
use_embedded_content = False |
| 27 |
language = 'en' |
| 28 |
remove_empty_feeds = True |
| 29 |
publication_type = 'magazine' |
| 30 |
needs_subscription = 'optional' |
| 31 |
delay = 1 |
| 32 |
simultaneous_downloads = 1 |
| 33 |
timeout = 8 |
| 34 |
ignore_duplicate_articles = {'url'} |
| 35 |
articles_are_obfuscated = True |
| 36 |
temp_files = [] |
| 37 |
fetch_retries = 10 |
| 38 |
auto_cleanup = True |
| 39 |
masthead_url = 'https://www.newcriterion.com/themes/thenewcriterion/assets/img/horizontal-logo.svg' |
| 40 |
extra_css = ''' |
| 41 |
body{font-family: Galliard, serif} |
| 42 |
''' |
| 43 |
|
| 44 |
conversion_options = {'comment': description, 'tags': category, 'publisher': publisher, 'language': language} |
| 45 |
|
| 46 |
def get_browser(self): |
| 47 |
br = BasicNewsRecipe.get_browser(self) |
| 48 |
if self.username is not None and self.password is not None: |
| 49 |
br.set_cookie('wordpress_test_cookie', 'WP+Cookie+check', '.newcriterion.com') |
| 50 |
br.open('https://newcriterion.com/wp-login.php') |
| 51 |
br.select_form(name='loginform') |
| 52 |
br['log'] = self.username |
| 53 |
br['pwd'] = self.password |
| 54 |
br.submit() |
| 55 |
return br |
| 56 |
|
| 57 |
def parse_index(self): |
| 58 |
months = ('january', 'february', 'march', 'april', 'may', 'june', 'july', 'august', 'september', 'october', 'november', 'december') |
| 59 |
slug = months[int(strftime('%m')) - 1] + '-' + strftime('%Y') |
| 60 |
currentIssue_url = 'https://newcriterion.com/issues/' + slug + '/' |
| 61 |
self.log(currentIssue_url) |
| 62 |
soup1 = self.index_to_soup(currentIssue_url) |
| 63 |
date = strftime(' %B %Y') |
| 64 |
articles = [] |
| 65 |
subset = soup1.find('div', attrs={'class': 'issue-layout'}) |
| 66 |
if subset is None: |
| 67 |
return [] |
| 68 |
for art in subset.findAll('article', attrs={'class': 'article-display'}): |
| 69 |
h2 = art.find('h2') |
| 70 |
if h2 is None: |
| 71 |
continue |
| 72 |
a = h2.find('a', href=True) |
| 73 |
if a is None or '/article/' not in a['href']: |
| 74 |
continue |
| 75 |
title = self.tag_to_string(a).strip() |
| 76 |
excerpt = art.find('p', attrs={'class': 'post-excerpt'}) |
| 77 |
description = self.tag_to_string(excerpt).strip() if excerpt else '' |
| 78 |
articles.append({ |
| 79 |
'title': title, |
| 80 |
'date': date, |
| 81 |
'url': a['href'], |
| 82 |
'description': description, |
| 83 |
}) |
| 84 |
return [(self.title, articles)] |
| 85 |
|
| 86 |
def get_obfuscated_article(self, url): |
| 87 |
result = None |
| 88 |
count = 0 |
| 89 |
while count < self.fetch_retries: |
| 90 |
try: |
| 91 |
response = self.browser.open(url, timeout=self.timeout) |
| 92 |
html = response.read() |
| 93 |
count = self.fetch_retries |
| 94 |
tfile = PersistentTemporaryFile('_fa.html') |
| 95 |
tfile.write(html) |
| 96 |
tfile.close() |
| 97 |
self.temp_files.append(tfile) |
| 98 |
result = tfile.name |
| 99 |
except Exception: |
| 100 |
print('Retrying download...') |
| 101 |
count += 1 |
| 102 |
return result |