| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
import re |
| 4 |
|
| 5 |
from calibre.ebooks.BeautifulSoup import Comment |
| 6 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 7 |
|
| 8 |
|
| 9 |
def build_absolute_url(url: str) -> str: |
| 10 |
# Ensure relative URLs are converted to absolute URLs for The Week site |
| 11 |
if url.startswith('/'): |
| 12 |
return 'https://www.theweek.in' + url |
| 13 |
return url |
| 14 |
|
| 15 |
|
| 16 |
class TheWeekRecipe(BasicNewsRecipe): |
| 17 |
title = 'The Week' |
| 18 |
description = ( |
| 19 |
'The Week is a best-selling general interest English news magazine. ' |
| 20 |
'It covers politics, entertainment, social issues, trends, technology, ' |
| 21 |
'lifestyle, and more. Best downloaded on Mondays.' |
| 22 |
) |
| 23 |
language = 'en_IN' |
| 24 |
__author__ = 'unkn0wn' |
| 25 |
encoding = 'utf-8' |
| 26 |
no_stylesheets = True |
| 27 |
use_embedded_content = False |
| 28 |
ignore_duplicate_articles = {'url', 'title'} |
| 29 |
remove_attributes = ['style', 'height', 'width'] |
| 30 |
masthead_url = 'https://www.theweek.in/content/dam/revamp-week/logo/THE-WEEK-LOGO.jpg' |
| 31 |
|
| 32 |
browser_type = 'webengine' |
| 33 |
|
| 34 |
keep_only_tags = [classes('articlecontent')] |
| 35 |
|
| 36 |
remove_tags = [ |
| 37 |
dict(name='source'), |
| 38 |
dict(attrs={'class': lambda cls: cls and 'ad_slot' in cls}), |
| 39 |
dict(attrs={'class': lambda cls: cls and 'article-header__action-block' in cls}), |
| 40 |
classes( |
| 41 |
'article-header__author-social cmp-social-media__nav advt-pos-wrap list-container-wrapper mmtagblock vuuklecomments article-header__author-image' |
| 42 |
), |
| 43 |
] |
| 44 |
|
| 45 |
extra_css = ''' |
| 46 |
em, blockquote { color: #202020; } |
| 47 |
.calibre-nuked-tag-figcaption, .mmtagblock { text-align:center; font-size:small; } |
| 48 |
.article-header__author-block { font-size:small; } |
| 49 |
img { display:block; margin:0 auto; } |
| 50 |
''' |
| 51 |
|
| 52 |
recipe_specific_options = { |
| 53 |
'date': { |
| 54 |
'short': 'Edition date to download (YYYY/MM/DD format)', |
| 55 |
'long': 'For example, 2026/06/21', |
| 56 |
} |
| 57 |
} |
| 58 |
|
| 59 |
def get_cover_url(self) -> str: |
| 60 |
# Fetch the cover image URL for the magazine issue |
| 61 |
edition_date = self.recipe_specific_options.get('date') |
| 62 |
if not (edition_date and isinstance(edition_date, str)): |
| 63 |
soup = self.index_to_soup('https://theweekmagazine.in/collections/weekly-magazine-subscription') |
| 64 |
cover_img = soup.find('img', attrs={'class': 'product-media__image'}) |
| 65 |
return 'https:' + cover_img['src'] |
| 66 |
|
| 67 |
def parse_index(self): |
| 68 |
# Parse the index page to collect article feeds |
| 69 |
edition_date = self.recipe_specific_options.get('date') |
| 70 |
if edition_date and isinstance(edition_date, str): |
| 71 |
issue_url = f'https://www.theweek.in/theweek/{edition_date}.html' |
| 72 |
else: |
| 73 |
archive_soup = self.index_to_soup('https://www.theweek.in/magazine-archives.html') |
| 74 |
arch = archive_soup.find('a', attrs={'class': 'cmp-story-list__image-link'}) |
| 75 |
issue_url = build_absolute_url(arch['href']) |
| 76 |
self.timefmt = ' [' + arch['title'] + ']' |
| 77 |
|
| 78 |
soup = self.index_to_soup(issue_url) |
| 79 |
feeds = [] |
| 80 |
|
| 81 |
for list_container in soup.findAll(**classes('listcontainer')): |
| 82 |
comment_node = list_container.find(string=lambda text: isinstance(text, Comment)) |
| 83 |
if comment_node: |
| 84 |
match = re.search(r'path:\s*(\S+),', comment_node) |
| 85 |
if match: |
| 86 |
list_url = match.group(1) |
| 87 |
feeds.append(self.parse_section_index(list_url)) |
| 88 |
|
| 89 |
return self.reorder_feeds(feeds) |
| 90 |
|
| 91 |
def parse_section_index(self, list_url: str): |
| 92 |
# Parse a section index page and extract articles |
| 93 |
soup = self.index_to_soup(list_url) |
| 94 |
for section in soup.findAll(**classes('story-list-block')): |
| 95 |
section_title = self.tag_to_string(section.find('h3', **classes('cmp-section-title'))) |
| 96 |
self.log(section_title) |
| 97 |
articles = [] |
| 98 |
|
| 99 |
for item in section.findAll(**classes('cmp-story-list__item')): |
| 100 |
title_tag = item.find(**classes('cmp-story-list__title-link')) |
| 101 |
title = self.tag_to_string(title_tag) |
| 102 |
link_tag = item.find('a', **classes('cmp-story-list__title-link')) |
| 103 |
url = build_absolute_url(link_tag['href']) |
| 104 |
|
| 105 |
description = '' |
| 106 |
if item.find(**classes('cmp-story-list__dispn')): |
| 107 |
description = self.tag_to_string(item.find(**classes('cmp-story-list__dispn'))) |
| 108 |
elif item.find(**classes('cmp-live-label')): |
| 109 |
description = self.tag_to_string(item.find(**classes('cmp-live-label'))) |
| 110 |
|
| 111 |
self.log('\t', title, '\n\t', description, '\n\t\t', url) |
| 112 |
articles.append({'title': title, 'description': description, 'url': url}) |
| 113 |
|
| 114 |
if articles: |
| 115 |
return (section_title, articles) |
| 116 |
|
| 117 |
def reorder_feeds(self, feeds): |
| 118 |
editor_articles = [] |
| 119 |
other_sections = [] |
| 120 |
|
| 121 |
for section_title, articles in feeds: |
| 122 |
# Split out articles with description "LETTER FROM THE EDITOR" |
| 123 |
editor = [a for a in articles if a.get('description', '').strip().upper() == 'LETTER FROM THE EDITOR'] |
| 124 |
non_editor = [a for a in articles if a not in editor] |
| 125 |
|
| 126 |
if editor: |
| 127 |
editor_articles.extend(editor) |
| 128 |
|
| 129 |
if non_editor: |
| 130 |
other_sections.append((section_title.strip(), non_editor)) |
| 131 |
|
| 132 |
# Build new feed list with editor section first |
| 133 |
if editor_articles: |
| 134 |
return [('Letter from the Editor', editor_articles)] + other_sections |
| 135 |
return other_sections |
| 136 |
|
| 137 |
def preprocess_html(self, soup): |
| 138 |
# Replace lazy-loaded image sources with actual URLs |
| 139 |
for img in soup.findAll('img', attrs={'data-websrc': True}): |
| 140 |
img['src'] = img['data-websrc'] |
| 141 |
return soup |