mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
112 lines
4.2 KiB
Python
112 lines
4.2 KiB
Python
#!/usr/bin/env python
|
||
from datetime import datetime, timedelta
|
||
|
||
from calibre.utils.date import parse_date
|
||
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
||
|
||
|
||
class ORF(BasicNewsRecipe):
|
||
title = 'Observer Research Foundation'
|
||
description = (
|
||
'Set up in 1990, ORF seeks to lead and aid policy thinking towards building a strong and prosperous India'
|
||
' in a fair and equitable world. It helps discover and inform India’s choices, and carries Indian voices '
|
||
'and ideas to forums shaping global debates.'
|
||
)
|
||
language = 'en_IN'
|
||
__author__ = 'unkn0wn'
|
||
encoding = 'utf-8'
|
||
no_stylesheets = True
|
||
remove_javascript = True
|
||
masthead_url = 'https://www.orfonline.org/wp-content/uploads/2015/09/Logo_ORF_JPEG.jpg'
|
||
remove_attributes = ['style', 'height', 'width']
|
||
ignore_duplicate_articles = {'url', 'title'}
|
||
remove_empty_feeds = True
|
||
oldest_article = 7
|
||
simultaneous_downloads = 1
|
||
|
||
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)
|
||
}
|
||
}
|
||
|
||
def __init__(self, *args, **kwargs):
|
||
BasicNewsRecipe.__init__(self, *args, **kwargs)
|
||
d = self.recipe_specific_options.get('days')
|
||
if d and isinstance(d, str):
|
||
self.oldest_article = float(d)
|
||
|
||
extra_css = '''
|
||
img {display:block; margin:0 auto;}
|
||
.report-slider, .author_panel {font-size:small; color:#404040;}
|
||
.report {font-size:small; font-weight:bold;}
|
||
.excert-italic, .recent-block-people {font-style:italic; color:#202020;}
|
||
blockquote, em {color:#202020;}
|
||
.espert_speak_panel {font-size:small;}
|
||
'''
|
||
|
||
def get_browser(self):
|
||
return BasicNewsRecipe.get_browser(self, user_agent='common_words/based')
|
||
|
||
resolve_internal_links = True
|
||
remove_empty_feeds = True
|
||
|
||
keep_only_tags = [
|
||
dict(name='h1'),
|
||
classes('author_panel espert_speak_panel expert_panel_content')
|
||
]
|
||
remove_tags = [
|
||
classes(
|
||
'social socialshare comment-area-section telegramhtml post-tag '
|
||
'research-prev research-next col-md-4 button_group sharethis-p tags'
|
||
)
|
||
]
|
||
|
||
def parse_index(self):
|
||
index = 'https://www.orfonline.org'
|
||
secs = [
|
||
('Expert Speak', '/expert-speak'),
|
||
('Young Voices', '/expert-speak-category/young-voices'),
|
||
('Commentary', '/content-type/commentary'),
|
||
('Issue Briefs', '/content-type/issue-briefs'),
|
||
('Books', '/content-type/books'),
|
||
('Special Reports', '/content-type/special-reports')
|
||
]
|
||
|
||
feeds = []
|
||
|
||
for x, y in secs:
|
||
section = x
|
||
self.log(section)
|
||
|
||
articles = []
|
||
|
||
soup = self.index_to_soup(index + y)
|
||
for a in soup.findAll('a', attrs={'href':True}):
|
||
if not a.find('h3'):
|
||
continue
|
||
div = a.find_previous_sibling(attrs={'class':'topic_story'})
|
||
if div:
|
||
if div.find(**classes('show_date')):
|
||
date = parse_date(self.tag_to_string(
|
||
div.find(**classes('show_date'))
|
||
)
|
||
).replace(tzinfo=None)
|
||
if (datetime.now() - date) > timedelta(self.oldest_article):
|
||
self.log(' Skipping ', self.tag_to_string(a))
|
||
continue
|
||
url = a['href']
|
||
title = self.tag_to_string(a)
|
||
desc = ''
|
||
if a.find_next_sibling('p'):
|
||
desc = self.tag_to_string(a.find_next_sibling('p'))
|
||
if a.find_next_sibling(attrs={'class':'author_name'}):
|
||
desc = self.tag_to_string(a.find_next_sibling(attrs={'class':'author_name'})) + ' | ' + desc
|
||
self.log('\t', title, '\n\t', desc, '\n\t\t', url)
|
||
articles.append({'title': title, 'url': url, 'description': desc})
|
||
if articles:
|
||
feeds.append((section, articles))
|
||
return feeds
|