| 1 |
#!/usr/bin/env python |
| 2 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 3 |
|
| 4 |
|
| 5 |
class firstpost(BasicNewsRecipe): |
| 6 |
title = 'Firstpost' |
| 7 |
__author__ = 'unkn0wn' |
| 8 |
description = ( |
| 9 |
'Firstpost.com will serve as a trusted guide to the crush of news and ideas around you.' |
| 10 |
' With thoughtful analysis and fearless views our team of editors and writers will track' |
| 11 |
' news in India and the world and provide a perspective that is reflective of a changing dynamic.' |
| 12 |
) |
| 13 |
no_stylesheets = True |
| 14 |
use_embedded_content = False |
| 15 |
encoding = 'utf-8' |
| 16 |
language = 'en_IN' |
| 17 |
remove_attributes = ['height', 'width', 'style'] |
| 18 |
masthead_url = 'https://images.firstpost.com/wp-content/uploads/2016/03/FP-Logo.png?impolicy=website&width=600&height=60' |
| 19 |
max_articles_per_feed = 25 |
| 20 |
remove_empty_feeds = True |
| 21 |
ignore_duplicate_articles = {'title', 'url'} |
| 22 |
extra_css = ''' |
| 23 |
.category-name, .author-info { font-size:small; color:#202020; } |
| 24 |
.wp-caption-text { font-size:small; text-align:center; } |
| 25 |
''' |
| 26 |
|
| 27 |
keep_only_tags = [classes('article-sect')] |
| 28 |
|
| 29 |
remove_tags = [ |
| 30 |
classes('art-rel-articles tags-wrap'), |
| 31 |
dict(name='svg'), |
| 32 |
] |
| 33 |
|
| 34 |
feeds = [] |
| 35 |
|
| 36 |
sections = [ |
| 37 |
'india', |
| 38 |
'politics', |
| 39 |
'opinion', |
| 40 |
'explainers', |
| 41 |
'business', |
| 42 |
'world', |
| 43 |
'web-stories', |
| 44 |
'tech', |
| 45 |
'artandculture', |
| 46 |
'health', |
| 47 |
'health-supplement', |
| 48 |
# 'photos', 'entertainment', 'living', 'education', 'sports', 'firstcricket', |
| 49 |
] |
| 50 |
|
| 51 |
oldest_article = 1.2 # days |
| 52 |
for sec in sections: |
| 53 |
a = 'https://www.firstpost.com/rss/{}.xml' |
| 54 |
feeds.append((sec.capitalize(), a.format(sec))) |
| 55 |
|
| 56 |
def preprocess_html(self, soup): |
| 57 |
if h2 := soup.find('h2', attrs={'class': 'category-name'}): |
| 58 |
h2.name = 'p' |
| 59 |
if h := soup.find('h2', attrs={'class': 'inner-copy'}): |
| 60 |
h.name = 'p' |
| 61 |
for img in soup.findAll('img', attrs={'data-src': True}): |
| 62 |
img['src'] = img['data-src'] |
| 63 |
return soup |