Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Popular Science

Browse Source
This commit is contained in:
Kovid Goyal 2021-06-02 09:24:25 +05:30
parent 27babe5ec8
commit d31874d94b
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 36 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

62
recipes/popscience.recipe
View File

@ -4,13 +4,15 @@
from __future__ import absolute_import, division, print_function, unicode_literals from __future__ import absolute_import, division, print_function, unicode_literals
import os
from collections import defaultdict
from calibre.ptempfile import PersistentTemporaryFile
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class AdvancedUserRecipe1282101454(BasicNewsRecipe): class AdvancedUserRecipe1282101454(BasicNewsRecipe):
title = 'Popular Science' title = 'Popular Science'
language = 'en' language = 'en'
@ -19,30 +21,38 @@ class AdvancedUserRecipe1282101454(BasicNewsRecipe):
publisher = 'Popular Science' publisher = 'Popular Science'
max_articles_per_feed = 100 max_articles_per_feed = 100
ignore_duplicate_articles = {'url'} ignore_duplicate_articles = {'url'}
no_stylesheets = True
keep_only_tags = [
classes('content-body article-header featured-img'),
]
def parse_section_index(self, slug):
soup = self.index_to_soup('https://www.popsci.com/{}/'.format(slug))
main = soup.find(**classes('main-module'))
for div in main.findAll(**classes('main-item')):
a = div.find('a', href=True, **classes('linkable'))
url = a['href']
title = self.tag_to_string(a.find(**classes('title')))
desc = ''
dek = a.find(**classes('dek'))
if dek is not None:
desc = self.tag_to_string(dek)
self.log(' ', title, url)
yield {'title': title, 'url': url, 'description': desc}
def parse_index(self): def parse_index(self):
from lxml import etree sections = []
raw = self.index_to_soup('https://www.popsci.com/arcio/rss/', raw=True) for slug, title in {
root = etree.fromstring(raw) 'science': 'Science',
ans = defaultdict(list) 'technology': 'Technology',
for item in root.iterdescendants('item'): 'diy': 'DIY',
title = item.find('title').text 'reviews': 'Reviews',
desc = item.find('description').text }.items():
author = item.find('dc:creator', {'dc': 'http://purl.org/dc/elements/1.1/'}).text self.log('Section:', title)
section = item.find('category').text articles = list(self.parse_section_index(slug))
content = item.find('content:encoded', {'content': 'http://purl.org/rss/1.0/modules/content/'}).text if articles:
content = '<html><body><h1>{title}</h1><h3>{desc}</h3><p>{author}</p><div>{content}</div></body></html>'.format( sections.append((title, articles))
title=title, author=author, desc=desc, content=content) return sections
if author:
desc += ' by ' + author
with PersistentTemporaryFile('popsci.html') as pt:
pt.write(content.encode('utf-8'))
ans[section].append({
'title': title,
'description': desc,
'url': 'file:///' + pt.name.replace(os.sep, '/'),
})
return [(sec, ans[sec]) for sec in sorted(ans)]
def preprocess_html(self, soup): def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-medsrc': True}): for img in soup.findAll('img', attrs={'data-medsrc': True}):