| 1 |
#!/usr/bin/env python |
| 2 |
from datetime import datetime, timedelta |
| 3 |
|
| 4 |
from calibre.utils.date import parse_date |
| 5 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 6 |
|
| 7 |
|
| 8 |
class ORF(BasicNewsRecipe): |
| 9 |
title = 'Observer Research Foundation' |
| 10 |
description = ( |
| 11 |
'Set up in 1990, ORF seeks to lead and aid policy thinking towards building a strong and prosperous India' |
| 12 |
' in a fair and equitable world. It helps discover and inform India’s choices, and carries Indian voices ' |
| 13 |
'and ideas to forums shaping global debates.' |
| 14 |
) |
| 15 |
language = 'en_IN' |
| 16 |
__author__ = 'unkn0wn' |
| 17 |
encoding = 'utf-8' |
| 18 |
no_stylesheets = True |
| 19 |
remove_javascript = True |
| 20 |
masthead_url = 'https://www.orfonline.org/wp-content/uploads/2015/09/Logo_ORF_JPEG.jpg' |
| 21 |
remove_attributes = ['style', 'height', 'width'] |
| 22 |
ignore_duplicate_articles = {'url', 'title'} |
| 23 |
oldest_article = 7 |
| 24 |
simultaneous_downloads = 1 |
| 25 |
|
| 26 |
recipe_specific_options = { |
| 27 |
'days': { |
| 28 |
'short': 'Oldest article to download from this news source. In days ', |
| 29 |
'long': 'For example, 0.5, gives you articles from the past 12 hours', |
| 30 |
'default': str(oldest_article), |
| 31 |
} |
| 32 |
} |
| 33 |
|
| 34 |
def __init__(self, *args, **kwargs): |
| 35 |
BasicNewsRecipe.__init__(self, *args, **kwargs) |
| 36 |
d = self.recipe_specific_options.get('days') |
| 37 |
if d and isinstance(d, str): |
| 38 |
self.oldest_article = float(d) |
| 39 |
|
| 40 |
extra_css = ''' |
| 41 |
img {display:block; margin:0 auto;} |
| 42 |
.report-slider, .author_panel {font-size:small; color:#404040;} |
| 43 |
.report {font-size:small; font-weight:bold;} |
| 44 |
.excert-italic, .recent-block-people {font-style:italic; color:#202020;} |
| 45 |
blockquote, em {color:#202020;} |
| 46 |
.espert_speak_panel {font-size:small;} |
| 47 |
''' |
| 48 |
|
| 49 |
def get_browser(self): |
| 50 |
return BasicNewsRecipe.get_browser(self, user_agent='common_words/based') |
| 51 |
|
| 52 |
resolve_internal_links = True |
| 53 |
remove_empty_feeds = True |
| 54 |
|
| 55 |
keep_only_tags = [dict(name='h1'), classes('author_panel espert_speak_panel expert_panel_content')] |
| 56 |
remove_tags = [classes('social socialshare comment-area-section telegramhtml post-tag research-prev research-next col-md-4 button_group sharethis-p tags')] |
| 57 |
|
| 58 |
def parse_index(self): |
| 59 |
index = 'https://www.orfonline.org' |
| 60 |
secs = [ |
| 61 |
('Expert Speak', '/expert-speak'), |
| 62 |
('Young Voices', '/expert-speak-category/young-voices'), |
| 63 |
('Commentary', '/content-type/commentary'), |
| 64 |
('Issue Briefs', '/content-type/issue-briefs'), |
| 65 |
('Books', '/content-type/books'), |
| 66 |
('Special Reports', '/content-type/special-reports'), |
| 67 |
] |
| 68 |
|
| 69 |
feeds = [] |
| 70 |
|
| 71 |
for x, y in secs: |
| 72 |
section = x |
| 73 |
self.log(section) |
| 74 |
|
| 75 |
articles = [] |
| 76 |
|
| 77 |
soup = self.index_to_soup(index + y) |
| 78 |
for a in soup.findAll('a', attrs={'href': True}): |
| 79 |
if not a.find('h3'): |
| 80 |
continue |
| 81 |
div = a.find_previous_sibling(attrs={'class': 'topic_story'}) |
| 82 |
if div: |
| 83 |
if div.find(**classes('show_date')): |
| 84 |
date = parse_date(self.tag_to_string(div.find(**classes('show_date')))).replace(tzinfo=None) |
| 85 |
if (datetime.now() - date) > timedelta(self.oldest_article): |
| 86 |
self.log(' Skipping ', self.tag_to_string(a)) |
| 87 |
continue |
| 88 |
url = a['href'] |
| 89 |
title = self.tag_to_string(a) |
| 90 |
desc = '' |
| 91 |
if a.find_next_sibling('p'): |
| 92 |
desc = self.tag_to_string(a.find_next_sibling('p')) |
| 93 |
if a.find_next_sibling(attrs={'class': 'author_name'}): |
| 94 |
desc = self.tag_to_string(a.find_next_sibling(attrs={'class': 'author_name'})) + ' | ' + desc |
| 95 |
self.log('\t', title, '\n\t', desc, '\n\t\t', url) |
| 96 |
articles.append({'title': title, 'url': url, 'description': desc}) |
| 97 |
if articles: |
| 98 |
feeds.append((section, articles)) |
| 99 |
return feeds |