| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
from collections import OrderedDict |
| 4 |
|
| 5 |
from calibre import browser |
| 6 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 7 |
|
| 8 |
|
| 9 |
class PhilosophyNow(BasicNewsRecipe): |
| 10 |
title = 'Philosophy Now' |
| 11 |
__author__ = 'unkn0wn' |
| 12 |
description = '''Philosophy Now is a lively magazine for everyone |
| 13 |
interested in ideas. It isn't afraid to tackle all the major questions of |
| 14 |
life, the universe and everything. Published every two months, it tries to |
| 15 |
corrupt innocent citizens by convincing them that philosophy can be |
| 16 |
exciting, worthwhile and comprehensible, and also to provide some enjoyable |
| 17 |
reading matter for those already ensnared by the muse, such as philosophy |
| 18 |
students and academics.''' |
| 19 |
language = 'en' |
| 20 |
use_embedded_content = False |
| 21 |
no_stylesheets = True |
| 22 |
remove_javascript = True |
| 23 |
remove_attributes = ['height', 'width', 'style'] |
| 24 |
encoding = 'utf-8' |
| 25 |
ignore_duplicate_articles = {'url'} |
| 26 |
masthead_url = 'https://philosophynow.org/media/images/regulars/logoStructuredData.png' |
| 27 |
|
| 28 |
keep_only_tags = [classes('article_page')] |
| 29 |
remove_tags = [dict(name='div', attrs={'id': 'welcome_box'})] |
| 30 |
extra_css = ''' |
| 31 |
img {display:block; margin:0 auto;} |
| 32 |
.articleImageCaption { font-size:small; text-align:center; } |
| 33 |
em, blockquote { color:#202020; } |
| 34 |
''' |
| 35 |
|
| 36 |
recipe_specific_options = {'issue': {'short': 'Enter the Issue Number you want to download ', 'long': 'For example, 136'}} |
| 37 |
|
| 38 |
def parse_index(self): |
| 39 |
soup = self.index_to_soup('https://philosophynow.org/') |
| 40 |
div = soup.find('div', attrs={'id': 'aside_issue_cover'}) |
| 41 |
url = 'https://philosophynow.org' + div.find('a', href=True)['href'] |
| 42 |
|
| 43 |
d = self.recipe_specific_options.get('issue') |
| 44 |
if d and isinstance(d, str): |
| 45 |
url = 'https://philosophynow.org/issues/' + d |
| 46 |
|
| 47 |
soup = self.index_to_soup(url) |
| 48 |
|
| 49 |
div = soup.find('div', attrs={'id': 'issue_contents_cover_div'}) |
| 50 |
cov_url = div.find('img', src=True)['src'] |
| 51 |
self.cover_url = 'https://philosophynow.org' + cov_url |
| 52 |
self.timefmt = ' [' + self.tag_to_string(soup.find('h1')) + ']' |
| 53 |
|
| 54 |
feeds = OrderedDict() |
| 55 |
|
| 56 |
for h2 in soup.findAll('h2', attrs={'class': 'article_list_title'}): |
| 57 |
articles = [] |
| 58 |
a = h2.find('a', href=True) |
| 59 |
url = a['href'] |
| 60 |
url = 'https://philosophynow.org' + url |
| 61 |
title = self.tag_to_string(a) |
| 62 |
des = h2.find_next_sibling('p') |
| 63 |
if des: |
| 64 |
desc = self.tag_to_string(des) |
| 65 |
h3 = h2.find_previous_sibling('h3') |
| 66 |
section_title = self.tag_to_string(h3).title() |
| 67 |
self.log('\t', title) |
| 68 |
self.log('\t', desc) |
| 69 |
self.log('\t\t', url) |
| 70 |
articles.append({'title': title, 'url': url, 'description': desc}) |
| 71 |
|
| 72 |
if articles: |
| 73 |
if section_title not in feeds: |
| 74 |
feeds[section_title] = [] |
| 75 |
feeds[section_title] += articles |
| 76 |
ans = list(feeds.items()) |
| 77 |
return ans |
| 78 |
|
| 79 |
# PN changes the content it delivers based on cookies, so the |
| 80 |
# following ensures that we send no cookies |
| 81 |
def get_browser(self, *args, **kwargs): |
| 82 |
return self |
| 83 |
|
| 84 |
def clone_browser(self, *args, **kwargs): |
| 85 |
return self.get_browser() |
| 86 |
|
| 87 |
def open_novisit(self, *args, **kwargs): |
| 88 |
br = browser(verify_ssl_certificates=False) |
| 89 |
return br.open_novisit(*args, **kwargs) |
| 90 |
|
| 91 |
open = open_novisit |