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

Merge branch 'kovidgoyal:master' into tolino

Browse Source
This commit is contained in:
beedaddy 2024-07-19 12:22:37 +00:00 committed by GitHub
commit f1932f1bc2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 63 additions and 38 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
recipes/atlantic.recipe
View File

@ -199,7 +199,7 @@ class TheAtlantic(BasicNewsRecipe):
self.cover_url = img['src']
current_section, current_articles = 'Cover Story', []
feeds = []
for x in soup.findAll(**prefix_classes('TocFeaturedSection_heading__ TocSection_heading__ TocHeroGridItem_hedLink___ TocGridItem_hedLink__')):
for x in soup.findAll(**prefix_classes('TocFeaturedSection_heading__ TocSection_heading__ TocHeroGridItem_hedLink__ TocGridItem_hedLink__')):
cls = x['class']
if not isinstance(cls, str):
cls = ' '.join(cls)

53
recipes/hindu.recipe
View File

@ -11,23 +11,6 @@ def absurl(url):
url = 'https://www.thehindu.com' + url
return url
# Chennai is default edition, for other editions use 'th_hyderabad', 'th_bangalore', 'th_delhi', 'th_kolkata' etc
local_edition = None
# For past editions, set date to, for example, '2023-01-28'
past_edition = None
is_monday = date.today().weekday() == 0
is_friday = date.today().weekday() == 4
is_saturday = date.today().weekday() == 5
is_sunday = date.today().weekday() == 6
if past_edition:
year, month, day = (int(x) for x in past_edition.split('-'))
dt = date(year, month, day)
is_monday = dt.weekday() == 0
is_saturday = dt.weekday() == 5
is_sunday = dt.weekday() == 6
class TheHindu(BasicNewsRecipe):
title = 'The Hindu'
@ -46,6 +29,17 @@ class TheHindu(BasicNewsRecipe):
.italic, .sub-title {font-style:italic; color:#202020;}
'''
recipe_specific_options = {
'location': {
'short': 'The name of the local edition',
'long': 'If The Hindu is available in your local town/city,\nset this to your location, for example, hyderabad'
},
'date': {
'short': 'The date of the edition to download (YYYY-MM-DD format)',
'long': 'For example, 2023-01-28'
}
}
ignore_duplicate_articles = {'url'}
keep_only_tags = [
@ -65,17 +59,24 @@ class TheHindu(BasicNewsRecipe):
h3.name = 'p'
return soup
def __init__(self, *args, **kwargs):
BasicNewsRecipe.__init__(self, *args, **kwargs)
if self.output_profile.short_name.startswith('kindle'):
if not past_edition:
self.title = 'The Hindu ' + date.today().strftime('%b %d, %Y')
else:
self.title = 'The Hindu ' + dt.strftime('%b %d, %Y')
def parse_index(self):
mag_url = None
global local_edition
local_edition = self.recipe_specific_options.get('location')
if local_edition:
local_edition = 'th_' + local_edition
past_edition = self.recipe_specific_options.get('date')
dt = date.today()
if past_edition:
year, month, day = (int(x) for x in past_edition.split('-'))
dt = date(year, month, day)
is_monday = dt.weekday() == 0
is_friday = dt.weekday() == 4
is_saturday = dt.weekday() == 5
is_sunday = dt.weekday() == 6
if local_edition or past_edition:
if local_edition is None:
local_edition = 'th_chennai'

27
recipes/psych.recipe
View File

@ -31,6 +31,19 @@ class PsychologyToday(BasicNewsRecipe):
encoding = 'UTF-8'
no_stylesheets = True
publication_type = 'magazine'
remove_attributes = ['style', 'height', 'width']
extra_css = '''
.image-article_inline_full, .image-article-inline-half { text-align:center; font-size:small; }
em, blockquote { color:#202020; }
.blog-entry__date--full { font-size:small; }
'''
recipe_specific_options = {
'date': {
'short': 'The date of the Past Edition to download (YYYY/MM format)',
'long': 'For example, 2024/07'
}
}
keep_only_tags = [dict(attrs={'id': 'block-pt-content'})]
remove_tags = [classes('pt-social-media')]
@ -38,9 +51,15 @@ class PsychologyToday(BasicNewsRecipe):
def parse_index(self):
soup = self.index_to_soup('https://www.psychologytoday.com/us/magazine/archive')
a = soup.find(**classes('magazine-thumbnail')).a
self.timefmt = ' [%s]' % a['title']
self.cover_url = absurl(a.img['src'])
soup = self.index_to_soup(absurl(a['href']))
url = a['href']
past_edition = self.recipe_specific_options.get('date')
if past_edition:
url = '/us/magazine/archive/' + past_edition
soup = self.index_to_soup(absurl(url))
cov = soup.find(**classes('content-header--cover-image'))
if cov:
self.cover_url = cov.img['src']
self.timefmt = ' [%s]' % cov.img['alt'].replace(' magazine cover', '')
articles = []
for article in soup.findAll('div', attrs={'class':'article-text'}):
title = self.tag_to_string(article.find(attrs={'class':['h2','h3']})).strip()
@ -53,4 +72,4 @@ class PsychologyToday(BasicNewsRecipe):
else:
desc = ''
articles.append({'title': title, 'url': url, 'description': desc, 'author': author})
return [('Current Issue', articles)]
return [('Articles', articles)]

19
recipes/wsj.recipe
View File

@ -6,11 +6,6 @@ from itertools import zip_longest
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.web.feeds.news import BasicNewsRecipe, classes
# Past 6 editions are available for download.
# For available past editions see log and set date to, for example, '20240513'.
past_edition = None
def media_bucket(x):
if x.get('type', '') == 'image':
if x.get('subtype', '') == 'graphic' or 'images.wsj.net' not in x['manifest-url']:
@ -41,6 +36,13 @@ class WSJ(BasicNewsRecipe):
remove_attributes = ['style', 'height', 'width']
resolve_internal_links = True
recipe_specific_options = {
'date': {
'short': 'The date of the edition to download (YYYYMMDD format)\nOnly the past 6 editions will be available ',
'long': 'For example, 20240513'
}
}
extra_css = '''
#subhed, em { font-style:italic; color:#202020; }
#byline, #time-to-read, #orig-pubdate-string, .article-byline, time, #flashline { font-size:small; }
@ -103,8 +105,8 @@ class WSJ(BasicNewsRecipe):
pan.name = 'div'
return soup
if not past_edition:
def _download_cover(self):
def _download_cover(self):
if not self.recipe_specific_options.get('date'):
import os
from contextlib import closing
@ -136,6 +138,9 @@ class WSJ(BasicNewsRecipe):
catalog = json.loads(self.index_to_soup(index + '/catalogs/v1/wsj/us/catalog.json', raw=True))
edit = [itm['key'][10:] for itm in catalog['items'] if itm['type'] == 'ITPNEXTGEN'][1:]
self.log('**Past Editions available :', ', '.join(edit))
past_edition = self.recipe_specific_options.get('date')
for itm in catalog['items']:
if past_edition:
if itm['key'] == 'ITPNEXTGEN' + past_edition: