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 'ruff-pep8' of https://github.com/un-pogaz/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2024-12-15 19:07:08 +05:30
commit 5c9d3386ee
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
118 changed files with 657 additions and 594 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
manual/conf.py
View File

@ -23,8 +23,9 @@ from setup import __appname__, __version__
sys.path.append(base)
import calibre.utils.img as cimg
import custom
import calibre.utils.img as cimg
from calibre.utils.localization import localize_website_link
del sys.path[0]

2
manual/custom.py
View File

@ -299,7 +299,7 @@ def render_options(cmd, groups, options_header=True, add_program=True, header_le
def mark_options(raw):
raw = re.sub(r'(\s+)--(\s+)', u'\\1``--``\\2', raw)
raw = re.sub(r'(\s+)--(\s+)', r'\1``--``\2', raw)
def sub(m):
opt = m.group()

4
manual/epub.py
View File

@ -8,13 +8,13 @@ __docformat__ = 'restructuredtext en'
import os
from sphinx.builders.epub3 import Epub3Builder as EpubBuilder
from calibre.ebooks.oeb.base import OPF
from calibre.ebooks.oeb.polish.check.links import UnreferencedResource, check_links
from calibre.ebooks.oeb.polish.container import OEB_DOCS, get_container
from calibre.ebooks.oeb.polish.pretty import pretty_html_tree, pretty_opf
from calibre.utils.imghdr import identify
from sphinx.builders.epub3 import Epub3Builder as EpubBuilder
from polyglot.builtins import iteritems

5
manual/plugin_examples/editor_demo/main.py
View File

@ -7,14 +7,15 @@ __copyright__ = '2014, Kovid Goyal <kovid at kovidgoyal.net>'
import re
from css_parser.css import CSSRule
from qt.core import QAction, QInputDialog
from calibre import force_unicode
from calibre.ebooks.oeb.polish.container import OEB_DOCS, OEB_STYLES, serialize
from calibre.gui2 import error_dialog
# The base class that all tools must inherit from
from calibre.gui2.tweak_book.plugin import Tool
from css_parser.css import CSSRule
from qt.core import QAction, QInputDialog
class DemoTool(Tool):

3
manual/plugin_examples/interface_demo/config.py
View File

@ -6,9 +6,10 @@ __license__ = 'GPL v3'
__copyright__ = '2011, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
from calibre.utils.config import JSONConfig
from qt.core import QHBoxLayout, QLabel, QLineEdit, QWidget
from calibre.utils.config import JSONConfig
# This is where all preferences for this plugin will be stored
# Remember that this name (i.e. plugins/interface_demo) is also
# in a global namespace, so make it as unique as possible.

3
manual/plugin_examples/interface_demo/main.py
View File

@ -12,9 +12,10 @@ if False:
# You do not need this code in your plugins
get_icons = get_resources = None
from calibre_plugins.interface_demo.config import prefs
from qt.core import QDialog, QLabel, QMessageBox, QPushButton, QVBoxLayout
from calibre_plugins.interface_demo.config import prefs
class DemoDialog(QDialog):

35
pyproject.toml
View File

@ -4,24 +4,35 @@ requires-python = ">=3.8"
[tool.ruff]
line-length = 160
target-version = 'py38'
builtins = ['_']
[tool.ruff.lint]
ignore = ['E741', 'E402', 'E722', 'E401']
select = ['E', 'F', 'I']
[tool.ruff.lint.per-file-ignores]
"src/calibre/ebooks/unihandecode/unicodepoints.py" = ["E501"]
"src/qt/__init__.py" = ["E501"]
builtins = ['_', 'I', 'P']
include = ['*.py', '*.recipe']
exclude = [
"*_ui.py",
"bypy/*",
"setup/*",
"src/css_selectors/*",
"src/polyglot/*",
"src/templite/*",
"src/tinycss/*",
]
[tool.ruff.format]
quote-style = 'single'
[tool.ruff.lint]
ignore = ['E402', 'E722', 'E741', 'E401']
select = ['E', 'F', 'I', 'W']
[tool.ruff.lint.per-file-ignores]
"src/calibre/ebooks/unihandecode/*codepoints.py" = ['E501', 'W191']
"src/qt/*.py" = ['I']
"src/qt/*.pyi" = ['I']
[tool.ruff.lint.isort]
detect-same-package = true
extra-standard-library = ['aes', 'elementmaker', 'encodings']
known-first-party = ["calibre_extensions", 'polyglot']
known-third-party = ["qt"]
extra-standard-library = ["aes", "elementmaker", "encodings"]
known-first-party = ["calibre_extensions", "calibre_plugins", "polyglot"]
known-third-party = ["odf", "qt", "templite", "tinycss", "css_selectors"]
relative-imports-order = "closest-to-furthest"
split-on-trailing-comma = false
section-order = ['__python__', "future", "standard-library", "third-party", "first-party", "local-folder"]

5
recipes/1843.recipe
View File

@ -7,12 +7,13 @@ from collections import defaultdict
from datetime import datetime, timedelta
from urllib.parse import quote, urlencode
from html5_parser import parse
from lxml import etree
from calibre import replace_entities
from calibre.ebooks.BeautifulSoup import NavigableString, Tag
from calibre.ptempfile import PersistentTemporaryFile
from calibre.web.feeds.news import BasicNewsRecipe
from html5_parser import parse
from lxml import etree
use_archive = True

3
recipes/american_thinker.recipe
View File

@ -4,9 +4,10 @@ __copyright__ = '2010, Walt Anthony <workshop.northpole at gmail.com>'
www.americanthinker.com
'''
import html5lib
from lxml import etree
from calibre.utils.cleantext import clean_xml_chars
from calibre.web.feeds.news import BasicNewsRecipe
from lxml import etree
class AmericanThinker(BasicNewsRecipe):

3
recipes/amspec.recipe
View File

@ -4,9 +4,10 @@ __copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
spectator.org
'''
from calibre.web.feeds.news import BasicNewsRecipe
from css_selectors import Select
from calibre.web.feeds.news import BasicNewsRecipe
class TheAmericanSpectator(BasicNewsRecipe):
title = 'The American Spectator'

2
recipes/before_we_go.recipe
View File

@ -7,7 +7,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class BeforeWeGo(BasicNewsRecipe):
title = 'Before We Go'
title = 'Before We Go'
__author__ = 'bugmen00t'
description = 'Before We Go Blog is a collective of Fantasy, Sci-Fi and Graphic Novel fans from around the world, passionate about providing awesome, enjoyable reviews for anyone who loves a good book!' # noqa
publisher = 'BEFOREWEGOBLOG'

4
recipes/berfreunde_blog.recipe
View File

@ -14,7 +14,7 @@ class bergfreunde_blog(BasicNewsRecipe):
max_articles_per_feed = 100
# clean up the mess
auto_cleanup = True
# what's this?
# what's this?
description = 'Blog der Bergfreunde Seite (Online Händler für Bergsport)'
publisher = 'https://www.bergfreunde.de/ueber-die-bergfreunde/'
language = 'de'
@ -31,4 +31,4 @@ class bergfreunde_blog(BasicNewsRecipe):
feeds = [
('Bergfreunde', 'https://www.bergfreunde.de/blog/feed'),
]
]

7
recipes/business_standard.recipe
View File

@ -3,9 +3,10 @@
import json
from datetime import datetime
from calibre.web.feeds.news import BasicNewsRecipe
from html5_parser import parse
from calibre.web.feeds.news import BasicNewsRecipe
class BusinessStandard(BasicNewsRecipe):
title = 'Business Standard'
@ -97,9 +98,9 @@ class BusinessStandard(BasicNewsRecipe):
date = (datetime.fromtimestamp(int(data['publishDate']))).strftime('%b %d, %Y | %I:%M %p')
authors = []
if 'articleMappedMultipleAuthors' in data:
if 'articleMappedMultipleAuthors' in data:
for aut in data['articleMappedMultipleAuthors']:
authors.append(data['articleMappedMultipleAuthors'][str(aut)])
authors.append(data['articleMappedMultipleAuthors'][str(aut)])
auth = '<div><p class="auth">' + ', '.join(authors) + ' | ' + data['placeName'] + ' | ' + date + '</p></div>'
if 'featuredImageObj' in data:

3
recipes/caravan_magazine.recipe
View File

@ -3,9 +3,10 @@
import json
from urllib.parse import quote, urlparse
from calibre.web.feeds.news import BasicNewsRecipe
from mechanize import Request
from calibre.web.feeds.news import BasicNewsRecipe
def absurl(x):
if x.startswith('//'):

2
recipes/cato.recipe
View File

@ -5,7 +5,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class CATOInstitute(BasicNewsRecipe):
title = u'The CATO Institute'
description = "The Cato Institute is a public policy research organization — a think tank — \
description = "The Cato Institute is a public policy research organization — a think tank — \
dedicated to the principles of individual liberty, limited government, free markets and peace.\
Its scholars and analysts conduct independent, nonpartisan research on a wide range of policy issues."
__author__ = '_reader'

2
recipes/cherta.recipe
View File

@ -5,7 +5,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class Cherta(BasicNewsRecipe):
title = '\u0427\u0435\u0440\u0442\u0430'
title = '\u0427\u0435\u0440\u0442\u0430'
__author__ = 'bugmen00t'
description = ' \u0418\u043D\u0442\u0435\u0440\u0435\u0441\u043D\u044B\u0435, \u0432\u0430\u0436\u043D\u044B\u0435 \u0438 \u0433\u043B\u0443\u0431\u043E\u043A\u0438\u0435 \u0442\u0435\u043A\u0441\u0442\u044B \u043F\u0440\u043E \u043D\u0430\u0441\u0438\u043B\u0438\u0435 \u0438 \u043D\u0435\u0440\u0430\u0432\u0435\u043D\u0441\u0442\u0432\u043E \u0432 \u0420\u043E\u0441\u0441\u0438\u0438.' # noqa
publisher = 'cherta.media'

4
recipes/courrierinternational.recipe
View File

@ -58,14 +58,14 @@ class CourrierInternational(BasicNewsRecipe):
.info-date, .info-reserved {
font-style: italic;
font-size: 0.9em;
font-size: 0.9em;
display: block;
}
.strapline {
font-size: 1.17em;
font-weight: bold;
margin: 0.67em 0;
margin: 0.67em 0;
line-height: 1.2;
}
'''

1
recipes/deccan_herald.recipe
View File

@ -18,7 +18,6 @@ class herald(BasicNewsRecipe):
keep_only_tags = [
classes('article-title article-author__name'),
dict(name='div', attrs={'id':'main-content'})
]
remove_tags = [

4
recipes/deutsche_welle_bs.recipe
View File

@ -16,10 +16,10 @@ class DeutscheWelle_bs(BasicNewsRecipe):
remove_empty_feeds = True
remove_javascript = True
masthead_url = 'http://www.dw-world.de/skins/std/channel1/pics/dw_logo1024.gif'
ignore_duplicate_articles = {'title', 'url'}
remove_attributes = ['height', 'width', 'style']
keep_only_tags = [
dict(name='article')
]

4
recipes/deutsche_welle_de.recipe
View File

@ -40,7 +40,7 @@ class DeutscheWelle(BasicNewsRecipe):
dict(attrs={'data-tracking-name':'sharing-icons-inline'}),
classes('kicker advertisement vjs-wrapper')
]
# watch out https://www.dw.com/de/service/rss/s-9773 for description of possible rss feeds
feeds = [
('Nachrichten', 'http://rss.dw.com/xml/rss-de-news'),
@ -53,7 +53,7 @@ class DeutscheWelle(BasicNewsRecipe):
('Kultur und Leben', 'http://rss.dw.com/xml/rss-de-cul'),
('Thema des Tages', 'http://rss.dw.com/xml/rss-de-top'),
]
def preprocess_html(self, soup):
for img in soup.findAll('img', srcset=True):
img['src'] = img['srcset'].split()[6]

10
recipes/deutsche_welle_en.recipe
View File

@ -15,7 +15,7 @@ class DeutscheWelle_en(BasicNewsRecipe):
remove_empty_feeds = True
ignore_duplicate_articles = {'title', 'url'}
remove_attributes = ['height', 'width', 'style']
recipe_specific_options = {
'days': {
'short': 'Oldest article to download from this news source. In days ',
@ -29,17 +29,17 @@ class DeutscheWelle_en(BasicNewsRecipe):
d = self.recipe_specific_options.get('days')
if d and isinstance(d, str):
self.oldest_article = float(d)
keep_only_tags = [
dict(name='article')
]
remove_tags = [
dict(name=['footer', 'source']),
dict(attrs={'data-tracking-name':'sharing-icons-inline'}),
classes('kicker advertisement vjs-wrapper')
]
feeds = [
('World', 'http://rss.dw.de/rdf/rss-en-world'),
('Germany', 'http://rss.dw.de/rdf/rss-en-ger'),
@ -51,7 +51,7 @@ class DeutscheWelle_en(BasicNewsRecipe):
('Asia', 'http://rss.dw.de/rdf/rss-en-asia'),
('Top Stories', 'http://rss.dw-world.de/rdf/rss-en-top'),
]
def preprocess_html(self, soup):
for img in soup.findAll('img', srcset=True):
img['src'] = img['srcset'].split()[6]

2
recipes/deutsche_welle_pt.recipe
View File

@ -19,7 +19,7 @@ class DeutscheWelle_pt(BasicNewsRecipe):
remove_javascript = True
ignore_duplicate_articles = {'title', 'url'}
remove_attributes = ['height', 'width', 'style']
recipe_specific_options = {
'days': {
'short': 'Oldest article to download from this news source. In days ',

6
recipes/deutsche_welle_ru.recipe
View File

@ -16,7 +16,7 @@ class DeutscheWelle(BasicNewsRecipe):
remove_empty_feeds = True
ignore_duplicate_articles = {'title', 'url'}
remove_attributes = ['height', 'width', 'style']
recipe_specific_options = {
'days': {
'short': 'Oldest article to download from this news source. In days ',
@ -30,7 +30,7 @@ class DeutscheWelle(BasicNewsRecipe):
d = self.recipe_specific_options.get('days')
if d and isinstance(d, str):
self.oldest_article = float(d)
def preprocess_html(self, soup):
for img in soup.findAll('img', srcset=True):
img['src'] = img['srcset'].split()[6]
@ -39,7 +39,7 @@ class DeutscheWelle(BasicNewsRecipe):
keep_only_tags = [
dict(name='article')
]
remove_tags = [
dict(name=['footer', 'source']),
dict(attrs={'data-tracking-name':'sharing-icons-inline'}),

2
recipes/dev_ua.recipe
View File

@ -7,7 +7,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class WiComix(BasicNewsRecipe):
title = 'dev.ua'
title = 'dev.ua'
__author__ = 'bugmen00t'
publisher = '\u0422\u041E\u0412 \u00AB\u0414\u0435\u0432 \u0423\u043A\u0440\u0430\u0457\u043D\u0430\u00BB'
category = 'news'

1
recipes/discover_magazine_monthly.recipe
View File

@ -16,6 +16,7 @@ try:
except ImportError:
from cookielib import Cookie
import mechanize
from calibre.web.feeds.news import BasicNewsRecipe

4
recipes/dr_dk.recipe
View File

@ -39,7 +39,7 @@ class DRNyheder(BasicNewsRecipe):
publisher = 'DR Nyheder'
description = 'Her finder du nyheder fra DR.'
category = 'news, politics, money, culture, sport, science, Denmark'
publication_type = 'newspaper'
publication_type = 'newspaper'
encoding = 'utf8'
language = 'da'
oldest_article = 4 # 2 might be best
@ -47,7 +47,7 @@ class DRNyheder(BasicNewsRecipe):
no_stylesheets = True
use_embedded_content = False
auto_cleanup = False
remove_empty_feeds = True
remove_empty_feeds = True
ignore_duplicate_articles = {'title', 'url'}
simultaneous_downloads = 20
compress_news_images = True

2
recipes/echo_moskvy.recipe
View File

@ -4,7 +4,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class EchoMsk(BasicNewsRecipe):
title = '\u042D\u0425\u041E'
title = '\u042D\u0425\u041E'
__author__ = 'bugmen00t'
description = ('\u042D\u0425\u041E - \u043A\u0430\u043A \u043D\u0430 \u0441\u0442\u0430\u0440\u043E\u043C'
' \u0434\u043E\u0431\u0440\u043E\u043C \u0440\u0430\u0434\u0438\u043E')

2
recipes/economist_espresso.recipe
View File

@ -53,7 +53,7 @@ class JSONHasNoContent(ValueError):
def load_article_from_json(raw, root):
# open('/t/raw.json', 'w').write(raw)
# open('/t/raw.json', 'w').write(raw)
data = json.loads(raw)
body = root.xpath('//body')[0]
article = E(body, 'article')

2
recipes/epoch_times.recipe
View File

@ -42,7 +42,7 @@ class EpochTimes(BasicNewsRecipe):
dict(name='img', attrs={'src':lambda x: x and x.endswith('svg')})
]
# feeds can be found at https://www.theepochtimes.com/rssfeeds
# feeds can be found at https://www.theepochtimes.com/rssfeeds
feeds = [
('Special Series', 'https://feed.theepochtimes.com/health/special-series/feed'),
('US', 'https://feed.theepochtimes.com/us/feed'),

3
recipes/esquire.recipe
View File

@ -5,9 +5,10 @@ www.esquire.com
'''
from collections import defaultdict
from calibre.web.feeds.news import BasicNewsRecipe
from css_selectors import Select
from calibre.web.feeds.news import BasicNewsRecipe
def absolutize(url):
if url.startswith('/'):

3
recipes/financial_times.recipe
View File

@ -4,9 +4,10 @@ import json
import re
from urllib.parse import quote
from html5_parser import parse
from calibre import browser
from calibre.web.feeds.news import BasicNewsRecipe, classes
from html5_parser import parse
class ft(BasicNewsRecipe):

3
recipes/first_things.recipe
View File

@ -7,9 +7,10 @@ __copyright__ = '2017, John Hutson <jfhutson at gmail.com>'
firstthings.com
'''
import html5lib
from calibre.web.feeds.news import BasicNewsRecipe
from lxml import html
from calibre.web.feeds.news import BasicNewsRecipe
class FirstThings(BasicNewsRecipe):

3
recipes/foreignaffairs.recipe
View File

@ -4,9 +4,10 @@ import re
import html5lib
import mechanize
from calibre.web.feeds.news import BasicNewsRecipe, classes
from lxml import html
from calibre.web.feeds.news import BasicNewsRecipe, classes
def as_article(source, log):
url = source['url']

8
recipes/frontline.recipe
View File

@ -69,15 +69,15 @@ class Frontline(BasicNewsRecipe):
issue_url = 'https://frontline.thehindu.com/magazine/issue/vol' + d
soup = self.index_to_soup(issue_url)
if cover := soup.find('div', attrs={'class':'magazine'}):
self.cover_url = cover.find(**classes('sptar-image')).img['data-original'].replace('SQUARE_80', 'FREE_615')
self.log('Cover ', self.cover_url)
if desc := cover.find(**classes('sub-text')):
self.description = self.tag_to_string(desc)
feeds_dict = defaultdict(list)
mag = soup.find(**classes('section-magazine'))
for div in mag.findAll('div', attrs={'class':'content'}):
a = div.find(**classes('title')).find('a')
@ -87,7 +87,7 @@ class Frontline(BasicNewsRecipe):
if cat := div.find(**classes('label')):
section = self.tag_to_string(cat)
desc = ''
if art := div.find(**classes('sub-text')):
desc = self.tag_to_string(art)
if auth := div.find(**classes('author')):

10
recipes/google_news.recipe
View File

@ -20,9 +20,9 @@ class google_news_de(BasicNewsRecipe):
cover_url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/d/da/Google_News_icon.svg/500px-Google_News_icon.svg.png'
# Author
__author__ = 'Volker Heggemann, VoHe, unkn0wn'
# oldest article to download (in days) ---- can be edit by user
# oldest article to download (in days) ---- can be edit by user
oldest_article = 1.25
# describes itself, ---- can be edit by user
# describes itself, ---- can be edit by user
max_articles_per_feed = 200
# speed up the download on fast computers be careful (I test max.20)
# ---- can be edit by user
@ -31,7 +31,7 @@ class google_news_de(BasicNewsRecipe):
description = u'Google News filter by your own recipe. Please read it in calibre software!'
# What is the content of?
category = u'NEWS'
# describes itself, ---- can be edit by user
# describes itself, ---- can be edit by user
use_embedded_content = False
remove_javascript = True
# Removes empty feeds - why keep them!?
@ -39,7 +39,7 @@ class google_news_de(BasicNewsRecipe):
# remove the rubbish (in ebook)
auto_cleanup = True
articles_are_obfuscated = True
def get_obfuscated_article(self, url):
@ -65,7 +65,7 @@ class google_news_de(BasicNewsRecipe):
return pt.name
# now the content description and URL follows
# feel free to add, wipe out what you need ---- can be edit by user
# feel free to add, wipe out what you need ---- can be edit by user
#
def get_feeds(self):
url = "https://geolocation-db.com/json"

2
recipes/gorky.recipe
View File

@ -5,7 +5,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class Gorky(BasicNewsRecipe):
title = '\u0413\u043E\u0440\u044C\u043A\u0438\u0439'
title = '\u0413\u043E\u0440\u044C\u043A\u0438\u0439'
__author__ = 'bugmen00t'
description = '\u041D\u0435\u043A\u043E\u043C\u043C\u0435\u0440\u0447\u0435\u0441\u043A\u0438\u0439 \u043F\u0440\u043E\u0435\u043A\u0442 \u043E \u043A\u043D\u0438\u0433\u0430\u0445 \u0438 \u0447\u0442\u0435\u043D\u0438\u0438.' # noqa
publisher = '\u0410\u041D\u041E "\u0426\u0435\u043D\u0442\u0440 \u043F\u043E \u0441\u043E\u0434\u0435\u0439\u0441\u0442\u0432\u0438\u044E \u0440\u0430\u0437\u0432\u0438\u0442\u0438\u044F \u043A\u0443\u043B\u044C\u0442\u0443\u0440\u044B \u0447\u0442\u0435\u043D\u0438\u044F \u0438 \u043A\u043D\u0438\u0433\u043E\u0438\u0437\u0434\u0430\u043D\u0438\u044F \u00AB\u0413\u043E\u0440\u044C\u043A\u0438\u0439 \u041C\u0435\u0434\u0438\u0430\u00BB"' # noqa

3
recipes/gosc_full.recipe
View File

@ -8,9 +8,10 @@ __copyright__ = '2011, Piotr Kontek, piotr.kontek@gmail.com \
import re
import time
from calibre.web.feeds.news import BasicNewsRecipe
from lxml import html
from calibre.web.feeds.news import BasicNewsRecipe
class GN(BasicNewsRecipe):
__author__ = 'Piotr Kontek, Tomasz Długosz'

3
recipes/gosc_niedzielny.recipe
View File

@ -7,9 +7,10 @@ __copyright__ = '2011, Piotr Kontek, piotr.kontek@gmail.com \
import re
from calibre.web.feeds.news import BasicNewsRecipe
from lxml import html
from calibre.web.feeds.news import BasicNewsRecipe
class GN(BasicNewsRecipe):
__author__ = 'Piotr Kontek, Tomasz Długosz'

3
recipes/hbr.recipe
View File

@ -5,9 +5,10 @@ import re
from collections import OrderedDict
from urllib.parse import urlencode, urljoin
from mechanize import Request
from calibre import browser, random_user_agent
from calibre.web.feeds.news import BasicNewsRecipe, classes
from mechanize import Request
class HBR(BasicNewsRecipe):

3
recipes/himal_southasian.recipe
View File

@ -2,9 +2,10 @@
# vim:fileencoding=utf-8
import json
from calibre.web.feeds.news import BasicNewsRecipe
from html5_parser import parse
from calibre.web.feeds.news import BasicNewsRecipe
def get_story(story):
str_type = story.get('type', '')

6
recipes/hindutamil.recipe
View File

@ -15,10 +15,10 @@ class hindutamil(BasicNewsRecipe):
language = 'ta'
remove_attributes = ['style', 'height', 'width']
masthead_url = 'https://static.hindutamil.in/hindu/static/store/images/logo.png'
def get_browser(self):
return BasicNewsRecipe.get_browser(self, user_agent='common_words/based')
return BasicNewsRecipe.get_browser(self, user_agent='common_words/based')
keep_only_tags = [
classes('main-article')
]

2
recipes/horizons.recipe
View File

@ -37,7 +37,7 @@ class horizons(BasicNewsRecipe):
'long': 'For example, https://www.cirsd.org/en/horizons/horizons-winter-2024--issue-no-25',
}
}
def get_browser(self):
return BasicNewsRecipe.get_browser(self, verify_ssl_certificates=False)

2
recipes/hurriyet.recipe
View File

@ -41,7 +41,7 @@ class Hurriyet(BasicNewsRecipe):
keep_only_tags = [
# title
{'class': 'news-detail-title'},
# date
# date
{'class': 'news-detail-text'},
# media
{'class': 'news-media'},

8
recipes/hvg.recipe
View File

@ -1,7 +1,7 @@
##########################################################################
# Description: http://hvg.hu/ RSS channel
# Author: Bigpapa (bigpapabig@hotmail.com)
# Date: 2011.12.20. - V1.1
# Description: http://hvg.hu/ RSS channel
# Author: Bigpapa (bigpapabig@hotmail.com)
# Date: 2011.12.20. - V1.1
##########################################################################
from calibre.web.feeds.news import BasicNewsRecipe
@ -11,7 +11,7 @@ class hvg(BasicNewsRecipe):
title = u'HVG'
__author__ = 'Bigpapa'
language = 'hu'
oldest_article = 5 # Hany napos legyen a legregebbi cikk amit leszedjen.
oldest_article = 5 # Hany napos legyen a legregebbi cikk amit leszedjen.
# Az adott e-bookban tarolt cikkek feedenkenti maximalis szamat adja meg.
max_articles_per_feed = 5
no_stylesheets = True

6
recipes/inc42.recipe
View File

@ -12,18 +12,18 @@ class inc42(BasicNewsRecipe):
language = 'en_IN'
remove_attributes = ['style', 'height', 'width']
masthead_url = 'https://omcdn.inc42.com/users/d0ffd8ffa0d2/images/4477fc48bee71659696918-color-black-1-e1576150264134.png?width=224'
keep_only_tags = [
classes('entry-header entry-content'),
]
remove_tags = [
dict(name='button'),
classes('also-read slick-list slides-three common-card'),
]
ignore_duplicate_articles = {'title', 'url'}
remove_empty_feeds = True
remove_empty_feeds = True
def parse_index(self):
index = 'https://inc42.com/'

3
recipes/journalofaccountancy.recipe
View File

@ -8,9 +8,10 @@ import json
from contextlib import closing
from time import sleep
from calibre.web.feeds.news import BasicNewsRecipe
from mechanize import Request
from calibre.web.feeds.news import BasicNewsRecipe
def absolutize(url):
if url.startswith('/'):

2
recipes/kompiutierra.recipe
View File

@ -38,4 +38,4 @@ class Computerra(BasicNewsRecipe):
feeds = [(
u'\u041A\u043E\u043C\u043F\u044C\u044E\u0442\u0435\u0440\u0440\u0430',
'https://www.computerra.ru/feed/'
)]
)]

14
recipes/le_gorafi.recipe
View File

@ -26,7 +26,7 @@ class LeGorafi(BasicNewsRecipe):
height: auto !important;
}
'''
keep_only_tags = [
dict(name='h1'),
dict(name='img', attrs={'class': 'attachment- size- wp-post-image'}),
@ -36,16 +36,16 @@ class LeGorafi(BasicNewsRecipe):
dict(name='div', attrs={'class': 'heateor_sss_sharing_container'}),
]
feeds = ['http://www.legorafi.fr/feed/']
def preprocess_html(self, soup):
for img in soup.findAll('img'):
if 'svg' in img['src']:
img.decompose() # Removes the tag entirely
return soup
def is_cover(article):
return 'gorafi-magazine' in article.url
def get_cover_url(self):
feeds = BasicNewsRecipe.parse_feeds(self)
for feed in feeds:
@ -55,12 +55,12 @@ class LeGorafi(BasicNewsRecipe):
img = soup.select_one('#mvp-post-feat-img img')
return img['data-lazy-src']
print("No cover found")
return None
return None
def parse_feeds(self):
feeds = BasicNewsRecipe.parse_feeds(self)
for feed in feeds:
for article in feed.articles:
if LeGorafi.is_cover(article):
feed.articles.remove(article)
return feeds
return feeds

10
recipes/le_monde.recipe
View File

@ -129,11 +129,11 @@ class LeMonde(BasicNewsRecipe):
dict(name=['footer', 'link', 'meta', 'svg', 'button', 'source']),
dict(name='img', attrs={'class': ['article__author-picture']}),
dict(name='section', attrs={'class':
[
'inread js-services-inread', 'catcher catcher--inline', 'inread inread--NL js-services-inread',
'article__reactions', 'author', 'catcher', 'portfolio', 'services-inread'
]
})
[
'inread js-services-inread', 'catcher catcher--inline', 'inread inread--NL js-services-inread',
'article__reactions', 'author', 'catcher', 'portfolio', 'services-inread'
]
})
]
remove_attributes = [

2
recipes/linux_news_de.recipe
View File

@ -30,7 +30,7 @@ class AdvancedUserRecipe1591780224(BasicNewsRecipe):
# remove the rubbish (in ebook)
auto_cleanup = True
# now the content description and URL follows
# feel free to add, wipe out what you need ---- can be edit by user
# feel free to add, wipe out what you need ---- can be edit by user
#
# some of this are double
#

5
recipes/mediapart.recipe
View File

@ -111,16 +111,17 @@ class Mediapart(BasicNewsRecipe):
br['email'] = self.username
br['password'] = self.password
br.submit()
return br
def default_cover(self, cover_file):
'''
Create a generic cover for recipes that don't have a cover
'''
from calibre.gui2 import ensure_app, load_builtin_fonts, pixmap_to_data
from qt.core import QFont, QImage, QPainter, QPen, QRect, Qt
from calibre.gui2 import ensure_app, load_builtin_fonts, pixmap_to_data
def init_environment():
ensure_app()
load_builtin_fonts()

2
recipes/mit_technology_review.recipe
View File

@ -74,7 +74,7 @@ class MitTechnologyReview(BasicNewsRecipe):
}
def parse_index(self):
# for past editions, change the issue link below
# for past editions, change the issue link below
issue = 'http://www.technologyreview.com/magazine/'
d = self.recipe_specific_options.get('issue_url')
if d and isinstance(d, str):

2
recipes/moneycontrol.recipe
View File

@ -53,7 +53,7 @@ class MoneyControlRecipe(BasicNewsRecipe):
index = 'https://www.moneycontrol.com/'
business_sections = [
'markets', 'stocks', 'ipo', 'budget', 'banks', 'moneycontrol-research', 'economy', 'earnings', 'real-estate',
'markets', 'stocks', 'ipo', 'budget', 'banks', 'moneycontrol-research', 'economy', 'earnings', 'real-estate',
'personal-finance', 'commodities', 'trade', 'companies'
]

2
recipes/moscowtimes_en.recipe
View File

@ -5,7 +5,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class MoscowTimes(BasicNewsRecipe):
title = 'The Moscow Times'
title = 'The Moscow Times'
__author__ = 'bugmen00t'
description = 'The Moscow Times is Russia’s leading, independent English-language media outlet. Our team of Russian and English journalists provide readers across the world with breaking news, engaging stories and balanced reporting about the largest country on Earth.' # noqa
publisher = 'Tiamti LLC'

10
recipes/my_dealz_de.recipe
View File

@ -9,9 +9,9 @@ class MyDealzDE(BasicNewsRecipe):
title = 'MyDealz'
# Author
__author__ = 'Volker Heggemann, VoHe'
# oldest article to download (in days) ---- can be edit by user
# oldest article to download (in days) ---- can be edit by user
oldest_article = 5
# describes itself, ---- can be edit by user
# describes itself, ---- can be edit by user
max_articles_per_feed = 100
# Cover Picture
cover_url = 'https://pbs.twimg.com/profile_images/817053687545741313/0wFqvfqC_400x400.jpg'
@ -24,9 +24,9 @@ class MyDealzDE(BasicNewsRecipe):
publisher = u'https://www.mydealz.de'
# What is the content of?
category = u'Shopping'
# describes itself, ---- can be edit by user
# describes itself, ---- can be edit by user
use_embedded_content = False
# describes itself, ---- can be edit by user
# describes itself, ---- can be edit by user
language = 'de'
# encoding of content. e.g. utf-8, None, ...
# ---- can be edit by user
@ -39,7 +39,7 @@ class MyDealzDE(BasicNewsRecipe):
# remove the rubbish (in ebook)
auto_cleanup = True
# now the content description and URL follows
# feel free to add, wipe out what you need ---- can be edit by user
# feel free to add, wipe out what you need ---- can be edit by user
#
# some of this are double
#

2
recipes/new_scientist_mag.recipe
View File

@ -84,7 +84,7 @@ class NewScientist(BasicNewsRecipe):
d = self.recipe_specific_options.get('issue')
if d and isinstance(d, str):
issue_url = 'https://www.newscientist.com/issue/' + d
soup = self.index_to_soup(issue_url)
div = soup.find('div', attrs={'class':'ThisWeeksMagazineHero__CoverInfo'})
tme = div.find(**classes('ThisWeeksMagazineHero__MagInfoHeading'))

6
recipes/nol.recipe
View File

@ -1,7 +1,7 @@
##########################################################################
# Description: http://nol.hu/ RSS channel
# Author: Bigpapa (bigpapabig@hotmail.com)
# Date: 2011.12.18. - V1.1
# Description: http://nol.hu/ RSS channel
# Author: Bigpapa (bigpapabig@hotmail.com)
# Date: 2011.12.18. - V1.1
##########################################################################
from calibre.web.feeds.recipes import BasicNewsRecipe

3
recipes/nrc.nl.recipe
View File

@ -4,9 +4,10 @@ import json
import re
from contextlib import closing
from calibre.web.feeds.recipes import BasicNewsRecipe
from mechanize import Request
from calibre.web.feeds.recipes import BasicNewsRecipe
class NRC(BasicNewsRecipe):
title = 'NRC'

3
recipes/nzz_ger.recipe
View File

@ -1,9 +1,10 @@
import json
from datetime import datetime
from calibre.web.feeds.recipes import BasicNewsRecipe
from mechanize import Request
from calibre.web.feeds.recipes import BasicNewsRecipe
class Nzz(BasicNewsRecipe):
title = 'NZZ'

3
recipes/ourdailybread.recipe
View File

@ -7,9 +7,10 @@ odb.org
import uuid
from calibre.web.feeds.news import BasicNewsRecipe
from lxml import html
from calibre.web.feeds.news import BasicNewsRecipe
class OurDailyBread(BasicNewsRecipe):
title = 'Our Daily Bread'

2
recipes/paperpaper.recipe
View File

@ -7,7 +7,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class PaperPaper(BasicNewsRecipe):
title = '\u0411\u0443\u043C\u0430\u0433\u0430'
title = '\u0411\u0443\u043C\u0430\u0433\u0430'
__author__ = 'bugmen00t'
description = '\u0418\u0437\u0434\u0430\u043D\u0438\u0435 \u043E \u043F\u0440\u0435\u043A\u0440\u0430\u0441\u043D\u043E\u043C \u0433\u043E\u0440\u043E\u0434\u0435 \u0421\u0430\u043D\u043A\u0442-\u041F\u0435\u0442\u0435\u0440\u0431\u0443\u0440\u0433\u0435, \u0432 \u043A\u043E\u0442\u043E\u0440\u043E\u043C, \u043A\u043E\u043D\u0435\u0447\u043D\u043E, \u0434\u0430\u043B\u0435\u043A\u043E \u043D\u0435 \u0432\u0441\u0451 \u0438\u0434\u0435\u0430\u043B\u044C\u043D\u043E, \u2014 \u0438 \u043F\u043E\u044D\u0442\u043E\u043C\u0443 \u043C\u044B \u0437\u0430\u043D\u0438\u043C\u0430\u0435\u043C\u0441\u044F \u0436\u0443\u0440\u043D\u0430\u043B\u0438\u0441\u0442\u0438\u043A\u043E\u0439, \u0447\u0442\u043E\u0431\u044B \u043F\u0440\u0438\u0432\u043B\u0435\u043A\u0430\u0442\u044C \u0432\u043D\u0438\u043C\u0430\u043D\u0438\u0435 \u043A \u0432\u0430\u0436\u043D\u044B\u043C \u0434\u043B\u044F \u0432\u0441\u0435\u0445 \u043F\u0440\u043E\u0431\u043B\u0435\u043C\u0430\u043C \u0438 \u0432\u043B\u0438\u044F\u0442\u044C \u043D\u0430 \u0438\u0445 \u0440\u0435\u0448\u0435\u043D\u0438\u0435.' # noqa
publisher = '\u041A\u0438\u0440\u0438\u043B\u043B \u0410\u0440\u0442\u0451\u043C\u0435\u043D\u043A\u043E, \u0422\u0430\u0442\u044C\u044F\u043D\u0430 \u0418\u0432\u0430\u043D\u043E\u0432\u0430' # noqa

3
recipes/parool.recipe
View File

@ -3,9 +3,10 @@ import json
import uuid
from contextlib import closing
from calibre.web.feeds.recipes import BasicNewsRecipe
from mechanize import Request
from calibre.web.feeds.recipes import BasicNewsRecipe
class Parool(BasicNewsRecipe):
title = 'Het Parool'

2
recipes/phillosophy_now.recipe
View File

@ -33,7 +33,7 @@ class PhilosophyNow(BasicNewsRecipe):
.articleImageCaption { font-size:small; text-align:center; }
em, blockquote { color:#202020; }
'''
recipe_specific_options = {
'issue': {
'short': 'Enter the Issue Number you want to download ',

2
recipes/poligon.recipe
View File

@ -7,7 +7,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class Poligon(BasicNewsRecipe):
title = '\u041F\u043E\u043B\u0438\u0433\u043E\u043D'
title = '\u041F\u043E\u043B\u0438\u0433\u043E\u043D'
__author__ = 'bugmen00t'
description = '\u041D\u0435\u0437\u0430\u0432\u0438\u0441\u0438\u043C\u043E\u0435 \u0438\u043D\u0442\u0435\u0440\u043D\u0435\u0442-\u0438\u0437\u0434\u0430\u043D\u0438\u0435, \u0432\u044B\u043F\u0443\u0441\u043A\u0430\u0435\u043C\u043E\u0435 \u0436\u0443\u0440\u043D\u0430\u043B\u0438\u0441\u0442\u0430\u043C\u0438 \u043D\u0435\u0441\u043A\u043E\u043B\u044C\u043A\u0438\u0445 \u0440\u043E\u0441\u0441\u0438\u0439\u0441\u043A\u0438\u0445 \u0438\u0437\u0434\u0430\u043D\u0438\u0439, \u043F\u043E\u0434\u0432\u0435\u0440\u0433\u0448\u0438\u0445\u0441\u044F \u0434\u0430\u0432\u043B\u0435\u043D\u0438\u044E \u0441\u043E \u0441\u0442\u043E\u0440\u043E\u043D\u044B \u0433\u043E\u0441\u0443\u0434\u0430\u0440\u0441\u0442\u0432\u0430. \u041F\u0438\u0448\u0435\u043C \u043E \u0420\u043E\u0441\u0441\u0438\u0438 \u0438 \u043D\u0435 \u0442\u043E\u043B\u044C\u043A\u043E.' # noqa
publisher = 'poligon.media'

10
recipes/presse_portal.recipe
View File

@ -12,9 +12,9 @@ class PressePortalDE(BasicNewsRecipe):
title = 'Presseportal DE'
# Author
__author__ = 'Volker Heggemann, VoHe'
# oldest article to download (in days) ---- can be edit by user
# oldest article to download (in days) ---- can be edit by user
oldest_article = 1
# describes itself, ---- can be edit by user
# describes itself, ---- can be edit by user
max_articles_per_feed = 100
# speed up the download on fast computers be careful (I test max.20)
# ---- can be edit by user
@ -29,9 +29,9 @@ class PressePortalDE(BasicNewsRecipe):
publisher = u'Presseportal.de'
# What is the content of?
category = u'latest news, national Police, Germany'
# describes itself, ---- can be edit by user
# describes itself, ---- can be edit by user
use_embedded_content = False
# describes itself, ---- can be edit by user
# describes itself, ---- can be edit by user
language = 'de'
# encoding of content. e.g. utf-8, None, ...
# ---- can be edit by user
@ -44,7 +44,7 @@ class PressePortalDE(BasicNewsRecipe):
# remove the rubbish (in ebook)
auto_cleanup = True
# now the content description and URL follows
# feel free to add, wipe out what you need ---- can be edit by user
# feel free to add, wipe out what you need ---- can be edit by user
#
# some of this are double
# so if you load "Alle Ressort" you don't need "Wirtschaft, Finanzen, Politik, Vermischtes..." at all.

16
recipes/pro_physik.recipe
View File

@ -10,27 +10,27 @@ from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1303841067(BasicNewsRecipe):
title = u'Pro Physik'
__author__ = 'schuster, Armin Geller'
__author__ = 'schuster, Armin Geller'
# AGE Upd. 2012-11-28, 2019-02-09,
# 2019-02-18, 2024-02-11
# https://www.mobileread.com/forums/showthread.php?t=133184
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
remove_empty_feeds = True
language = 'de_DE'
language = 'de_DE'
# In case you want to assign a cover picture to this recipe.
# Copy the file Pro_Physik.png to:
# c:/Users/YOUR_USERNAME/AppData/Roaming/calibre/resources/images/news_covers/
# where YOUR_USERNAME needs to be replaced with your username.
# Then remove # in front of cover_url and replace YOUR_USERNAME with your username as well
# cover_url = file:///c:/Users/YOUR_USERNAME/AppData/Roaming/calibre/resources/images/news_covers/Pro_Physik.png
extra_css = '''
h1 {font-size: 1.6em; text-align: left}
h2, h3 {font-size: 1.3em;text-align: left}
@ -43,7 +43,7 @@ class AdvancedUserRecipe1303841067(BasicNewsRecipe):
dict(name='article', attrs={'id':['story']}),
dict(name='div', attrs={'class':['event-item view-mode-default']})
]
remove_tags = [
dict(name='ul', attrs={'class':["wj-share-buttons"]}), #Block social media
]
@ -51,4 +51,4 @@ class AdvancedUserRecipe1303841067(BasicNewsRecipe):
feeds = [
(u'Nachrichten', u'https://pro-physik.de/rss/news/'),
# (u'Veranstaltungen', u'https://pro-physik.de/rss/events/'), # AGe 2024-02-11
]
]

2
recipes/prosleduet.recipe
View File

@ -7,7 +7,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class ProSleduet(BasicNewsRecipe):
title = '\u041F\u0440\u043E\u0434\u043E\u043B\u0436\u0435\u043D\u0438\u0435 \u0441\u043B\u0435\u0434\u0443\u0435\u0442'
title = '\u041F\u0440\u043E\u0434\u043E\u043B\u0436\u0435\u043D\u0438\u0435 \u0441\u043B\u0435\u0434\u0443\u0435\u0442'
__author__ = 'bugmen00t'
description = ('\u0414\u0438\u0434\u0436\u0438\u0442\u0430\u043B-\u043F\u0440\u043E\u0435\u043A\u0442'
' \u0436\u0443\u0440\u043D\u0430\u043B\u0438\u0441\u0442\u043E\u0432'

1
recipes/publico.recipe
View File

@ -9,7 +9,6 @@ publico.pt
'''
from calibre.web.feeds.news import BasicNewsRecipe
from polyglot.urllib import urlencode

2
recipes/queueacmorg.recipe
View File

@ -35,4 +35,4 @@ class QueueAcmOrg(BasicNewsRecipe):
)
if len(imgs) > 0:
self.cover_url = 'https://queue.acm.org/' + imgs[0]['src']
return getattr(self, 'cover_url', self.cover_url)
return getattr(self, 'cover_url', self.cover_url)

102
recipes/radio_canada.recipe
View File

@ -82,70 +82,70 @@ class RadioCanada(BasicNewsRecipe):
# From the list situated at https://ici.radio-canada.ca/rss
feeds = [
# Information
('Grands titres', 'https://ici.radio-canada.ca/rss/4159'),
('En continu', 'https://ici.radio-canada.ca/rss/1000524'),
('Grands titres', 'https://ici.radio-canada.ca/rss/4159'),
('En continu', 'https://ici.radio-canada.ca/rss/1000524'),
# Thématiques
('Alimentation', 'https://ici.radio-canada.ca/rss/7239'),
('Art de vivre', 'https://ici.radio-canada.ca/rss/4163'),
('Économie', 'https://ici.radio-canada.ca/rss/5717'),
('Environnement', 'https://ici.radio-canada.ca/rss/92408'),
('International', 'https://ici.radio-canada.ca/rss/96'),
('Alimentation', 'https://ici.radio-canada.ca/rss/7239'),
('Art de vivre', 'https://ici.radio-canada.ca/rss/4163'),
('Économie', 'https://ici.radio-canada.ca/rss/5717'),
('Environnement', 'https://ici.radio-canada.ca/rss/92408'),
('International', 'https://ici.radio-canada.ca/rss/96'),
('Justice et faits divers', 'https://ici.radio-canada.ca/rss/92411'),
('Politique', 'https://ici.radio-canada.ca/rss/4175'),
('Santé', 'https://ici.radio-canada.ca/rss/4171'),
('Science', 'https://ici.radio-canada.ca/rss/4165'),
('Société', 'https://ici.radio-canada.ca/rss/7110'),
('Techno', 'https://ici.radio-canada.ca/rss/4169'),
('Politique', 'https://ici.radio-canada.ca/rss/4175'),
('Santé', 'https://ici.radio-canada.ca/rss/4171'),
('Science', 'https://ici.radio-canada.ca/rss/4165'),
('Société', 'https://ici.radio-canada.ca/rss/7110'),
('Techno', 'https://ici.radio-canada.ca/rss/4169'),
# Sports
('Grands titres', 'https://ici.radio-canada.ca/rss/771'),
('Football', 'https://ici.radio-canada.ca/rss/1000057'),
('Hockey', 'https://ici.radio-canada.ca/rss/1000056'),
('Olympiques', 'https://ici.radio-canada.ca/rss/64852'),
('Podium', 'https://ici.radio-canada.ca/rss/555082'),
('Soccer', 'https://ici.radio-canada.ca/rss/1000058'),
('Tennis', 'https://ici.radio-canada.ca/rss/1000059'),
('Grands titres', 'https://ici.radio-canada.ca/rss/771'),
('Football', 'https://ici.radio-canada.ca/rss/1000057'),
('Hockey', 'https://ici.radio-canada.ca/rss/1000056'),
('Olympiques', 'https://ici.radio-canada.ca/rss/64852'),
('Podium', 'https://ici.radio-canada.ca/rss/555082'),
('Soccer', 'https://ici.radio-canada.ca/rss/1000058'),
('Tennis', 'https://ici.radio-canada.ca/rss/1000059'),
# Arts
('Grands Titres', 'https://ici.radio-canada.ca/rss/4167'),
('Célébrités', 'https://ici.radio-canada.ca/rss/1000232'),
('Cinéma', 'https://ici.radio-canada.ca/rss/1000229'),
('Humour', 'https://ici.radio-canada.ca/rss/1000231'),
('Livres', 'https://ici.radio-canada.ca/rss/1000083'),
('Musique', 'https://ici.radio-canada.ca/rss/1000230'),
('Télé', 'https://ici.radio-canada.ca/rss/1000233'),
('Grands Titres', 'https://ici.radio-canada.ca/rss/4167'),
('Célébrités', 'https://ici.radio-canada.ca/rss/1000232'),
('Cinéma', 'https://ici.radio-canada.ca/rss/1000229'),
('Humour', 'https://ici.radio-canada.ca/rss/1000231'),
('Livres', 'https://ici.radio-canada.ca/rss/1000083'),
('Musique', 'https://ici.radio-canada.ca/rss/1000230'),
('Télé', 'https://ici.radio-canada.ca/rss/1000233'),
# Régions
('Abitibi-Témiscamingue', 'https://ici.radio-canada.ca/rss/5763'),
('Alberta', 'https://ici.radio-canada.ca/rss/5767'),
('Bas-Saint-Laurent', 'https://ici.radio-canada.ca/rss/35004'),
('Colombie-Brittanique', 'https://ici.radio-canada.ca/rss/5769'),
('Côte-Nord', 'https://ici.radio-canada.ca/rss/35019'),
('Estrie', 'https://ici.radio-canada.ca/rss/5773'),
('Gaspésie-Îles-de-la-Madeleine', 'https://ici.radio-canada.ca/rss/35015'),
('Grand Montréal', 'https://ici.radio-canada.ca/rss/4201'),
('Grand Nord', 'https://ici.radio-canada.ca/rss/1001049'),
('Île-du-Prince-Édouard', 'https://ici.radio-canada.ca/rss/1000814'),
('Manitoba', 'https://ici.radio-canada.ca/rss/5775'),
('Mauricie–Centre-du-Québec', 'https://ici.radio-canada.ca/rss/5777'),
('Nord de l’Ontario', 'https://ici.radio-canada.ca/rss/36518'),
('Nouveau-Brunswick', 'https://ici.radio-canada.ca/rss/5765'),
('Nouvelle-Écosse', 'https://ici.radio-canada.ca/rss/1000813'),
('Ottawa-Gatineau', 'https://ici.radio-canada.ca/rss/6102'),
('Québec', 'https://ici.radio-canada.ca/rss/6104'),
('Saguenay-Lac-St-Jean', 'https://ici.radio-canada.ca/rss/6106'),
('Saskatchewan', 'https://ici.radio-canada.ca/rss/6108'),
('Terre-Neuve-et-Labrador', 'https://ici.radio-canada.ca/rss/1000815'),
('Toronto', 'https://ici.radio-canada.ca/rss/5779'),
('Windsor', 'https://ici.radio-canada.ca/rss/475289'),
('Abitibi-Témiscamingue', 'https://ici.radio-canada.ca/rss/5763'),
('Alberta', 'https://ici.radio-canada.ca/rss/5767'),
('Bas-Saint-Laurent', 'https://ici.radio-canada.ca/rss/35004'),
('Colombie-Brittanique', 'https://ici.radio-canada.ca/rss/5769'),
('Côte-Nord', 'https://ici.radio-canada.ca/rss/35019'),
('Estrie', 'https://ici.radio-canada.ca/rss/5773'),
('Gaspésie-Îles-de-la-Madeleine', 'https://ici.radio-canada.ca/rss/35015'),
('Grand Montréal', 'https://ici.radio-canada.ca/rss/4201'),
('Grand Nord', 'https://ici.radio-canada.ca/rss/1001049'),
('Île-du-Prince-Édouard', 'https://ici.radio-canada.ca/rss/1000814'),
('Manitoba', 'https://ici.radio-canada.ca/rss/5775'),
('Mauricie–Centre-du-Québec', 'https://ici.radio-canada.ca/rss/5777'),
('Nord de l’Ontario', 'https://ici.radio-canada.ca/rss/36518'),
('Nouveau-Brunswick', 'https://ici.radio-canada.ca/rss/5765'),
('Nouvelle-Écosse', 'https://ici.radio-canada.ca/rss/1000813'),
('Ottawa-Gatineau', 'https://ici.radio-canada.ca/rss/6102'),
('Québec', 'https://ici.radio-canada.ca/rss/6104'),
('Saguenay-Lac-St-Jean', 'https://ici.radio-canada.ca/rss/6106'),
('Saskatchewan', 'https://ici.radio-canada.ca/rss/6108'),
('Terre-Neuve-et-Labrador', 'https://ici.radio-canada.ca/rss/1000815'),
('Toronto', 'https://ici.radio-canada.ca/rss/5779'),
('Windsor', 'https://ici.radio-canada.ca/rss/475289'),
# Autres
('Archives', 'https://ici.radio-canada.ca/rss/1000548'),
('Dossiers', 'https://ici.radio-canada.ca/rss/6735'),
('Archives', 'https://ici.radio-canada.ca/rss/1000548'),
('Dossiers', 'https://ici.radio-canada.ca/rss/6735'),
('Espaces autochtones', 'https://ici.radio-canada.ca/rss/116435'),
('RCI', 'http://www.rcinet.ca/fr/feed/rss/')
('RCI', 'http://www.rcinet.ca/fr/feed/rss/')
]
# The following was copied and adapted as per the following post:

3
recipes/respekt_magazine.recipe
View File

@ -10,9 +10,10 @@ import re
# This imports the version bundled with Calibre
import lxml
from lxml.builder import E
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.web.feeds.recipes import BasicNewsRecipe
from lxml.builder import E
respekt_url = 'https://www.respekt.cz'

2
recipes/sobaka.recipe
View File

@ -5,7 +5,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class Sobaka(BasicNewsRecipe):
title = '\u0421\u043E\u0431\u0430\u043A\u0430.ru'
title = '\u0421\u043E\u0431\u0430\u043A\u0430.ru'
__author__ = 'bugmen00t'
description = '\u0416\u0443\u0440\u043D\u0430\u043B \u043E \u043B\u044E\u0434\u044F\u0445 \u0432 \u041F\u0435\u0442\u0435\u0440\u0431\u0443\u0440\u0433\u0435' # noqa
publisher = '\u041E\u041E\u041E \u00AB\u0416\u0443\u0440\u043D\u0430\u043B\u044B \u0438 \u0441\u0430\u0439\u0442\u044B "\u0424\u0430\u0431\u0440\u0438\u043A\u0430 \u043A\u043E\u043D\u0442\u0435\u043D\u0442\u0430 "\u0422\u043E\u0447\u043A\u0430 \u0420\u0443"\u00BB' # noqa

4
recipes/spectator_magazine.recipe
View File

@ -40,7 +40,7 @@ class spectator(BasicNewsRecipe):
dict(name = ['svg', 'button']),
classes(
'entry-meta audio-read-block insert--most-popular ad-slot ad-slot--in-content ad-content '
'subscription-banner '
'subscription-banner '
)
]
@ -48,7 +48,7 @@ class spectator(BasicNewsRecipe):
for fc in soup.findAll('figcaption'):
fc['id'] = 'fig-c'
return soup
def get_browser(self, *args, **kwargs):
kwargs['user_agent'] = 'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)'
br = BasicNewsRecipe.get_browser(self, *args, **kwargs)

10
recipes/spiegelde.recipe
View File

@ -19,10 +19,10 @@ class Spiegel_DE_all(BasicNewsRecipe):
title = u'Spiegel Online RSS - German alle Themen'
# Author
__author__ = u'Volker Heggemann, VoHe'
# oldest article to download (in days) ---- can be edit by user
# oldest article to download (in days) ---- can be edit by user
# be careful, if there is a lot of news, the file size exceeds!
oldest_article = 7
# describes itself, ---- can be edit by user
# describes itself, ---- can be edit by user
max_articles_per_feed = 100
# speed up the download on fast computers be careful (I test max.20)
# ---- can be edit by user
@ -40,11 +40,11 @@ class Spiegel_DE_all(BasicNewsRecipe):
cover_url = 'https://de.m.wikipedia.org/wiki/Datei:Spiegel_Online_logo.svg'
# What is the content of?
category = 'SPIEGEL ONLINE RSS'
# describes itself, ---- can be edit by user
# describes itself, ---- can be edit by user
language = 'de'
lang = 'de-DE'
no_stylesheets = True
# describes itself, ---- can be edit by user
# describes itself, ---- can be edit by user
use_embedded_content = False
# encoding of content. e.g. utf-8, None, ...
# ---- can be edit by user
@ -57,7 +57,7 @@ class Spiegel_DE_all(BasicNewsRecipe):
# remove the rubbish (in ebook)
auto_cleanup = True
# now the content description and URL follows
# feel free to add, wipe out what you need ---- can be edit by user
# feel free to add, wipe out what you need ---- can be edit by user
#
# Make some tests, may you first comment all of them out, and step by step you add what you'll need?
#

2
recipes/st_louis_post_dispatch.recipe
View File

@ -66,4 +66,4 @@ class StLouisPostDispatch(BasicNewsRecipe):
(u'Opinion - Editorial', u'http://www.stltoday.com/search/?c=opinion%2feditorial&d1=&d2=&s=start_time&sd=desc&f=rss&l=25&t=article'),
(u'Opinion - Letters to the Editor', u'https://www.stltoday.com/search/?c=opinion%2Fletters&d1=&d2=&s=start_time&sd=desc&f=rss&l=25&t=article'),
(u'Opinion - Local Columns', u'https://www.stltoday.com/search/?c=opinion%2fcolumn*&d1=&d2=&s=start_time&sd=desc&nfl=ap&nk=%23noshow,dcc&f=rss&l=25&t=article')
]
]

2
recipes/straitstimes.recipe
View File

@ -46,7 +46,7 @@ class StraitsTimes(BasicNewsRecipe):
,(u'Opinion' , u'https://www.straitstimes.com/news/opinion/rss.xml')
,(u'Life' , u'https://www.straitstimes.com/news/life/rss.xml')
,(u'Singapore' , u'https://www.straitstimes.com/news/singapore/rss.xml')
,(u'Asia' , u'https://www.straitstimes.com/news/asia/rss.xml')
,(u'Asia' , u'https://www.straitstimes.com/news/asia/rss.xml')
,(u'Multimedia' , u'https://www.straitstimes.com/news/multimedia/rss.xml')
,(u'Sport' , u'https://www.straitstimes.com/news/sport/rss.xml')
]

2
recipes/t3n_de.recipe
View File

@ -22,7 +22,7 @@ class germant3n(BasicNewsRecipe):
# remove the rubbish (in ebook)
auto_cleanup = True
# now the content description and URL follows
# feel free to add, wipe out what you need ---- can be edit by user
# feel free to add, wipe out what you need ---- can be edit by user
#
# some of this are double
#

2
recipes/t_invariant_en.recipe
View File

@ -7,7 +7,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class TInvariant(BasicNewsRecipe):
title = 'T-Invariant'
title = 'T-Invariant'
__author__ = 'bugmen00t'
description = 'T-Invariant is a multimedia project of scientists and science journalists. Our task is to be a bridge between the academic community in Russia and outside Russia. Let’s keep in touch!' # noqa
publisher = '\u0422-\u0438\u043D\u0432\u0430\u0440\u0438\u0430\u043D\u0442 / T-invariant'

2
recipes/t_invariant_ru.recipe
View File

@ -7,7 +7,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class TInvariant(BasicNewsRecipe):
title = 'T-Invariant'
title = 'T-Invariant'
__author__ = 'bugmen00t'
description = '\u041C\u0443\u043B\u044C\u0442\u0438\u043C\u0435\u0434\u0438\u0439\u043D\u044B\u0439 \u043F\u0440\u043E\u0435\u043A\u0442 \u0443\u0447\u0435\u043D\u044B\u0445 \u0438 \u043D\u0430\u0443\u0447\u043D\u044B\u0445 \u0436\u0443\u0440\u043D\u0430\u043B\u0438\u0441\u0442\u043E\u0432.' # noqa
publisher = '\u0422-\u0438\u043D\u0432\u0430\u0440\u0438\u0430\u043D\u0442 / T-invariant'

2
recipes/t_invariant_ua.recipe
View File

@ -7,7 +7,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class TInvariant(BasicNewsRecipe):
title = 'T-Invariant'
title = 'T-Invariant'
__author__ = 'bugmen00t'
description = 'T-Invariant is a multimedia project of scientists and science journalists. Our task is to be a bridge between the academic community in Russia and outside Russia. Let’s keep in touch!' # noqa
publisher = '\u0422-\u0438\u043D\u0432\u0430\u0440\u0438\u0430\u043D\u0442 / T-invariant'

2
recipes/tagesspiegel.recipe
View File

@ -48,7 +48,7 @@ class TagesspiegelRss(BasicNewsRecipe):
from datetime import date
cover = 'https://img.kiosko.net/' + date.today().strftime('%Y/%m/%d') + '/de/tagesspiegel.750.jpg'
return cover
keep_only_tags = [
dict(name = 'header', attrs={'class':'Bo'}),
dict(name = 'div', attrs={'id':'story-elements'})

104
recipes/the_philippine_daily_inquirer.recipe
View File

@ -51,73 +51,73 @@ class PhilippineDailyInquirer(BasicNewsRecipe):
feeds = [
('Headlines' , 'http://newsinfo.inquirer.net/category/inquirer-headlines/feed'),
('Latest Stories' , 'http://newsinfo.inquirer.net/category/latest-stories/feed'),
('Nation' , 'http://newsinfo.inquirer.net/category/nation/feed'),
('Nation - Latest Stories' , 'http://newsinfo.inquirer.net/category/latest-stories/nation-latest-stories/feed'),
('Metro' , 'http://newsinfo.inquirer.net/category/metro/feed'),
('Metro - Latest Stories' , 'http://newsinfo.inquirer.net/category/latest-stories/metro-latest-stories/feed'),
('Regions' , 'http://newsinfo.inquirer.net/category/regions/feed'),
('Regions - Latest Stories' , 'http://newsinfo.inquirer.net/category/latest-stories/regions-latest-stories/feed'),
('News' , 'http://www.inquirer.net/fullfeed'),
('More News' , 'http://newsinfo.inquirer.net/feed')
('Headlines', 'http://newsinfo.inquirer.net/category/inquirer-headlines/feed'),
('Latest Stories' , 'http://newsinfo.inquirer.net/category/latest-stories/feed'),
('Nation' , 'http://newsinfo.inquirer.net/category/nation/feed'),
('Nation - Latest Stories' , 'http://newsinfo.inquirer.net/category/latest-stories/nation-latest-stories/feed'),
('Metro' , 'http://newsinfo.inquirer.net/category/metro/feed'),
('Metro - Latest Stories' , 'http://newsinfo.inquirer.net/category/latest-stories/metro-latest-stories/feed'),
('Regions' , 'http://newsinfo.inquirer.net/category/regions/feed'),
('Regions - Latest Stories' , 'http://newsinfo.inquirer.net/category/latest-stories/regions-latest-stories/feed'),
('News' , 'http://www.inquirer.net/fullfeed'),
('More News' , 'http://newsinfo.inquirer.net/feed')
,
('Global Nation' , 'http://globalnation.inquirer.net/feed'),
('Global Nation' , 'http://globalnation.inquirer.net/feed'),
('Global Nation - Latest Stories', 'http://globalnation.inquirer.net/category/latest-stories/feed'),
('Global Nation - Philippines', 'http://globalnation.inquirer.net/category/news/philippines/feed'),
('Global Nation - Asia & Pacific', 'http://globalnation.inquirer.net/category/news/asiaaustralia/feed'),
('Global Nation - Americas', 'http://globalnation.inquirer.net/category/news/uscanada/feed'),
('Global Nation - Middle East & Africa', 'http://globalnation.inquirer.net/category/news/middle-eastafrica/feed'),
('Global Nation - Europe' , 'http://globalnation.inquirer.net/category/news/europe/feed'),
('Global Nation - Europe' , 'http://globalnation.inquirer.net/category/news/europe/feed'),
('Global Nation - Global Pinoy', 'http://globalnation.inquirer.net/category/global-pinoy/feed'),
('Global Nation - Events' , 'http://globalnation.inquirer.net/category/events/feed'),
('Business' , 'http://business.inquirer.net/feed'),
('Business - Latest Stories' , 'http://business.inquirer.net/category/latest-stories/feed'),
('Business - Money' , 'http://business.inquirer.net/category/money/feed'),
('Global Nation - Events' , 'http://globalnation.inquirer.net/category/events/feed'),
('Business' , 'http://business.inquirer.net/feed'),
('Business - Latest Stories' , 'http://business.inquirer.net/category/latest-stories/feed'),
('Business - Money' , 'http://business.inquirer.net/category/money/feed'),
('Business - Science & Health', 'http://business.inquirer.net/category/science-and-health/feed'),
('Business - Motoring' , 'http://business.inquirer.net/category/motoring/feed'),
('Business - Property Guide' , 'http://business.inquirer.net/category/property-guide/feed'),
('Business - Columnists' , 'http://business.inquirer.net/category/columnists/feed'),
('Sports' , 'http://sports.inquirer.net/feed'),
('Sports - Latest Stories' , 'http://sports.inquirer.net/category/latest-stories/feed'),
('Sports - Basketball' , 'http://sports.inquirer.net/category/section/basketball/feed'),
('Business - Motoring' , 'http://business.inquirer.net/category/motoring/feed'),
('Business - Property Guide' , 'http://business.inquirer.net/category/property-guide/feed'),
('Business - Columnists' , 'http://business.inquirer.net/category/columnists/feed'),
('Sports' , 'http://sports.inquirer.net/feed'),
('Sports - Latest Stories' , 'http://sports.inquirer.net/category/latest-stories/feed'),
('Sports - Basketball' , 'http://sports.inquirer.net/category/section/basketball/feed'),
('Sports - Boxing & MMA', 'http://sports.inquirer.net/category/section/boxing-mma/feed'),
('Sports - Golf' , 'http://sports.inquirer.net/category/section/golf/feed'),
('Sports - Football' , 'http://sports.inquirer.net/category/section/other-sports/football/feed'),
('Sports - Other Sports' , 'http://sports.inquirer.net/category/section/other-sports/feed'),
('Technology' , 'http://technology.inquirer.net/feed'),
('Sports - Golf' , 'http://sports.inquirer.net/category/section/golf/feed'),
('Sports - Football' , 'http://sports.inquirer.net/category/section/other-sports/football/feed'),
('Sports - Other Sports' , 'http://sports.inquirer.net/category/section/other-sports/feed'),
('Technology' , 'http://technology.inquirer.net/feed'),
('Technology Latest Stories', 'http://technology.inquirer.net/category/latest-stories/feed'),
('Entertainment' , 'http://entertainment.inquirer.net/feed'),
('Entertainment' , 'http://entertainment.inquirer.net/feed'),
('Entertainment - Headlines', 'http://entertainment.inquirer.net/category/headlines/feed'),
('Entertainment - Latest Stories', 'http://entertainment.inquirer.net/category/latest-stories/feed'),
('Entertainment - Movies' , 'http://movies.inquirer.net/feed'),
('Lifestyle' , 'http://lifestyle.inquirer.net/feed'),
('Entertainment - Movies' , 'http://movies.inquirer.net/feed'),
('Lifestyle' , 'http://lifestyle.inquirer.net/feed'),
('Lifestyle - Latest Stories', 'http://lifestyle.inquirer.net/category/latest-stories/feed'),
('Lifestyle - Arts & Books' , 'http://lifestyle.inquirer.net/category/arts-and-books/feed'),
('Lifestyle - Wellness' , 'http://lifestyle.inquirer.net/category/wellness/feed'),
('Lifestyle - Arts & Books' , 'http://lifestyle.inquirer.net/category/arts-and-books/feed'),
('Lifestyle - Wellness' , 'http://lifestyle.inquirer.net/category/wellness/feed'),
('Lifestyle - Home & Entertaining', 'http://lifestyle.inquirer.net/category/home-and-entertaining/feed'),
('Lifestyle - Parenting' , 'http://lifestyle.inquirer.net/category/parenting/feed'),
('Lifestyle - Food' , 'http://lifestyle.inquirer.net/category/food/feed'),
('Lifestyle - Parenting' , 'http://lifestyle.inquirer.net/category/parenting/feed'),
('Lifestyle - Food' , 'http://lifestyle.inquirer.net/category/food/feed'),
('Lifestyle - Fashion & Beauty', 'http://lifestyle.inquirer.net/category/fashion-and-beauty/feed'),
('Lifestyle - Super' , 'http://lifestyle.inquirer.net/category/super/feed'),
('Lifestyle - 2BU' , 'http://lifestyle.inquirer.net/category/2bu/feed'),
('Lifestyle - Super' , 'http://lifestyle.inquirer.net/category/super/feed'),
('Lifestyle - 2BU' , 'http://lifestyle.inquirer.net/category/2bu/feed'),
('Lifestyle - Sunday Lifestyle', 'http://lifestyle.inquirer.net/category/sunday-lifestyle/feed'),
('Lifestyle - Wedding' , 'http://lifestyle.inquirer.net/category/sunday-lifestyle/wedding/feed'),
('Lifestyle - Travel' , 'http://lifestyle.inquirer.net/category/sunday-lifestyle/travel/feed'),
('Lifestyle - Relationship' , 'http://lifestyle.inquirer.net/category/sunday-lifestyle/relationship/feed'),
('Opinion' , 'http://opinion.inquirer.net/feed'),
('Opinion - Viewpoints' , 'http://opinion.inquirer.net/category/viewpoints/feed'),
('Lifestyle - Wedding' , 'http://lifestyle.inquirer.net/category/sunday-lifestyle/wedding/feed'),
('Lifestyle - Travel' , 'http://lifestyle.inquirer.net/category/sunday-lifestyle/travel/feed'),
('Lifestyle - Relationship' , 'http://lifestyle.inquirer.net/category/sunday-lifestyle/relationship/feed'),
('Opinion' , 'http://opinion.inquirer.net/feed'),
('Opinion - Viewpoints' , 'http://opinion.inquirer.net/category/viewpoints/feed'),
('Opinion - Talk of the Town', 'http://opinion.inquirer.net/category/inquirer-opinion/talk-of-the-town/feed'),
('Editorial' , 'http://opinion.inquirer.net/category/editorial/feed'),
('Letters to the Editor' , 'http://opinion.inquirer.net/category/letters-to-the-editor/feed'),
('Columns' , 'http://opinion.inquirer.net/category/columns/feed'),
('Citizens Journalism' , 'http://newsinfo.inquirer.net/category/citizens-journalism/feed'),
('Cebu - Daily News' , 'http://newsinfo.inquirer.net/category/cdn/feed'),
('Cebu - More News' , 'http://newsinfo.inquirer.net/category/cdn/cdn-news/feed'),
('Cebu - Community' , 'http://newsinfo.inquirer.net/category/cdn/cdn-community/feed'),
('Cebu - Metro' , 'http://newsinfo.inquirer.net/category/cdn/cdn-metro/feed'),
('Cebu - Business' , 'http://newsinfo.inquirer.net/category/cdn/cdn-enterprise/feed'),
('Cebu - Sports' , 'http://newsinfo.inquirer.net/category/cdn/cdn-sports/feed'),
('Cebu - Visayas' , 'http://newsinfo.inquirer.net/category/cdn/cdn-visayas/feed'),
('Cebu - Opinion' , 'http://newsinfo.inquirer.net/category/cdn/cdn-opinion/feed')
('Editorial' , 'http://opinion.inquirer.net/category/editorial/feed'),
('Letters to the Editor' , 'http://opinion.inquirer.net/category/letters-to-the-editor/feed'),
('Columns' , 'http://opinion.inquirer.net/category/columns/feed'),
('Citizens Journalism' , 'http://newsinfo.inquirer.net/category/citizens-journalism/feed'),
('Cebu - Daily News' , 'http://newsinfo.inquirer.net/category/cdn/feed'),
('Cebu - More News' , 'http://newsinfo.inquirer.net/category/cdn/cdn-news/feed'),
('Cebu - Community' , 'http://newsinfo.inquirer.net/category/cdn/cdn-community/feed'),
('Cebu - Metro' , 'http://newsinfo.inquirer.net/category/cdn/cdn-metro/feed'),
('Cebu - Business' , 'http://newsinfo.inquirer.net/category/cdn/cdn-enterprise/feed'),
('Cebu - Sports' , 'http://newsinfo.inquirer.net/category/cdn/cdn-sports/feed'),
('Cebu - Visayas' , 'http://newsinfo.inquirer.net/category/cdn/cdn-visayas/feed'),
('Cebu - Opinion' , 'http://newsinfo.inquirer.net/category/cdn/cdn-opinion/feed')
]

3
recipes/thenewcriterion.recipe
View File

@ -15,10 +15,11 @@ except ImportError:
from urllib import urlencode
import re
from mechanize import Request
from calibre import strftime
from calibre.ptempfile import PersistentTemporaryFile
from calibre.web.feeds.news import BasicNewsRecipe
from mechanize import Request
class TheNewCriterion(BasicNewsRecipe):

6
recipes/theoldie.recipe
View File

@ -69,7 +69,7 @@ class PrivateEyeRecipe(BasicNewsRecipe):
article['author'] = author
return article
edition_re = re.compile('(?:-front-cover-)(\d+)-')
edition_re = re.compile(r'(?:-front-cover-)(\d+)-')
# Identify the cover image and extract the edition# from the url
def get_cover_url(self):
@ -242,8 +242,8 @@ class PrivateEyeRecipe(BasicNewsRecipe):
{'name': 'a', 'class': "view-full-screen"},
{'name': 'div', 'class': "image-counter"},
{'name': 'h2', 'string': "Find out more about The Oldie"},
{'name': 'a', 'href': re.compile("^https?:\/\/issuu.com\/")},
{'name': 'img', 'src': re.compile("\/assets\/images\/icons\/icon-")},
{'name': 'a', 'href': re.compile(r"^https?:\/\/issuu.com\/")},
{'name': 'img', 'src': re.compile(r"\/assets\/images\/icons\/icon-")},
]
# The following extra css is to tweak the formatting of various elements of various article pages.

2
recipes/tls_mag.recipe
View File

@ -16,7 +16,7 @@ def re_html(y):
def get_id(url):
rq = browser().open(url)
return re.search('\?p=(\S+)>', str(rq.info())).group(1)
return re.search(r'\?p=(\S+)>', str(rq.info())).group(1)
class TLS(BasicNewsRecipe):

3
recipes/ugeskriftet.recipe
View File

@ -29,9 +29,8 @@ class Ugeskriftet(BasicNewsRecipe):
h2{font-weight: bold; font-size: large;}
h3{font-weight: bold; font-size: large;}
h4{font-weight: bold; font-size: large;}
"""
"""
feeds = [
('Ugeskriftet for læger', 'https://ugeskriftet.dk/rss/forside'),
]

2
recipes/ukrinform_es.recipe
View File

@ -5,7 +5,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class UkrInform(BasicNewsRecipe):
title = 'UkrInform (Espa\u00F1ol)'
title = 'UkrInform (Espa\u00F1ol)'
__author__ = 'bugmen00t'
description = 'Agencia de noticias nacional de Ucrania, fuente de informaci\u00F3n sobre la vida pol\u00EDtica, econ\u00F3mica, social, cient\u00EDfica, cultural y p\u00FAblica en Ucrania y en el extranjero.' # noqa
publisher = 'Ministerio de Cultura y Pol\u00EDtica de Informaci\u00F3n de Ucrania'

3
recipes/usatoday.recipe
View File

@ -69,7 +69,7 @@ class USAToday(BasicNewsRecipe):
def parse_index(self):
index = 'https://www.usatoday.com/'
sections = [
'news', 'opinion', 'tech', 'entertainment', 'money', 'sports', 'travel', 'life', 'investigations',
'news', 'opinion', 'tech', 'entertainment', 'money', 'sports', 'travel', 'life', 'investigations',
]
feeds = []
soup = self.index_to_soup(index)
@ -87,7 +87,6 @@ class USAToday(BasicNewsRecipe):
if articles:
feeds.append((section, articles))
return feeds
def preprocess_html(self, soup):
for img in soup.findAll('img', src=True):

3
recipes/volksrant.recipe
View File

@ -3,9 +3,10 @@ import json
import uuid
from contextlib import closing
from calibre.web.feeds.recipes import BasicNewsRecipe
from mechanize import Request
from calibre.web.feeds.recipes import BasicNewsRecipe
class Volkskrant(BasicNewsRecipe):
title = 'Volkskrant'

2
recipes/wicomix.recipe
View File

@ -7,7 +7,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class WiComix(BasicNewsRecipe):
title = 'Wicomix'
title = 'Wicomix'
__author__ = 'bugmen00t'
description = '\u0418\u043D\u0442\u0435\u0440\u0435\u0441\u043D\u043E \u043F\u0438\u0448\u0435\u043C \u043F\u0440\u043E \u043A\u043E\u043C\u0438\u043A\u0441\u044B \u0438 \u043C\u0430\u043D\u0433\u0443 \u0432 \u0420\u043E\u0441\u0441\u0438\u0438.' # noqa
publisher = '\u0421\u0435\u0440\u0433\u0435\u0439 \u041E\u0440\u0435\u0448\u043A\u0438\u043D'

5
recipes/wsj_free.recipe
View File

@ -10,11 +10,12 @@ import time
from base64 import standard_b64encode
from datetime import date, timedelta
from calibre.ptempfile import PersistentTemporaryFile
from calibre.web.feeds.news import BasicNewsRecipe
from css_selectors import Select
from mechanize import Request
from calibre.ptempfile import PersistentTemporaryFile
from calibre.web.feeds.news import BasicNewsRecipe
try:
import urllib.parse as urlparse
except ImportError:

32
resources/default_tweaks.py
View File

@ -216,14 +216,14 @@ save_template_title_series_sorting = 'library_order'
# (present only for legacy reasons).
per_language_title_sort_articles = {
# English
'eng' : (r'A\s+', r'The\s+', r'An\s+'),
'eng': (r'A\s+', r'The\s+', r'An\s+'),
# Esperanto
'epo': (r'La\s+', r"L'", 'L´'),
# Spanish
'spa' : (r'El\s+', r'La\s+', r'Lo\s+', r'Los\s+', r'Las\s+', r'Un\s+',
'spa': (r'El\s+', r'La\s+', r'Lo\s+', r'Los\s+', r'Las\s+', r'Un\s+',
r'Una\s+', r'Unos\s+', r'Unas\s+'),
# French
'fra' : (r'Le\s+', r'La\s+', r"L'", u'L´', u'L’', r'Les\s+', r'Un\s+', r'Une\s+',
'fra': (r'Le\s+', r'La\s+', r"L'", r'L´', r'L’', r'Les\s+', r'Un\s+', r'Une\s+',
r'Des\s+', r'De\s+La\s+', r'De\s+', r"D'", r'D´', r'D’'),
# Polish
'pol': (),
@ -233,32 +233,32 @@ per_language_title_sort_articles = {
'Un´', 'Dei\\s+', 'Degli\\s+', 'Delle\\s+', 'Del\\s+',
'Della\\s+', 'Dello\\s+', "Dell'", 'Dell´'),
# Portuguese
'por' : (r'A\s+', r'O\s+', r'Os\s+', r'As\s+', r'Um\s+', r'Uns\s+',
'por': (r'A\s+', r'O\s+', r'Os\s+', r'As\s+', r'Um\s+', r'Uns\s+',
r'Uma\s+', r'Umas\s+', ),
# Romanian
'ron' : (r'Un\s+', r'O\s+', r'Nişte\s+', ),
'ron': (r'Un\s+', r'O\s+', r'Nişte\s+', ),
# German
'deu' : (r'Der\s+', r'Die\s+', r'Das\s+', r'Den\s+', r'Ein\s+',
'deu': (r'Der\s+', r'Die\s+', r'Das\s+', r'Den\s+', r'Ein\s+',
r'Eine\s+', r'Einen\s+', r'Dem\s+', r'Des\s+', r'Einem\s+',
r'Eines\s+'),
# Dutch
'nld' : (r'De\s+', r'Het\s+', r'Een\s+', r"'n\s+", r"'s\s+", r'Ene\s+',
'nld': (r'De\s+', r'Het\s+', r'Een\s+', r"'n\s+", r"'s\s+", r'Ene\s+',
r'Ener\s+', r'Enes\s+', r'Den\s+', r'Der\s+', r'Des\s+',
r"'t\s+"),
# Swedish
'swe' : (r'En\s+', r'Ett\s+', r'Det\s+', r'Den\s+', r'De\s+', ),
'swe': (r'En\s+', r'Ett\s+', r'Det\s+', r'Den\s+', r'De\s+', ),
# Turkish
'tur' : (r'Bir\s+', ),
'tur': (r'Bir\s+', ),
# Afrikaans
'afr' : (r"'n\s+", r'Die\s+', ),
'afr': (r"'n\s+", r'Die\s+', ),
# Greek
'ell' : (r'O\s+', r'I\s+', r'To\s+', r'Ta\s+', r'Tus\s+', r'Tis\s+',
'ell': (r'O\s+', r'I\s+', r'To\s+', r'Ta\s+', r'Tus\s+', r'Tis\s+',
r"'Enas\s+", r"'Mia\s+", r"'Ena\s+", r"'Enan\s+", ),
# Hungarian
'hun' : (r'A\s+', r'Az\s+', r'Egy\s+',),
'hun': (r'A\s+', r'Az\s+', r'Egy\s+',),
}
default_language_for_title_sort = None
title_sort_articles=r'^(A|The|An)\s+'
title_sort_articles = r'^(A|The|An)\s+'
#: Specify a folder calibre should connect to at startup
# Specify a folder that calibre should connect to at startup using
@ -331,8 +331,8 @@ auto_connect_to_folder = ''
# The resulting two tweaks are:
# sony_collection_renaming_rules={'series':'Series', 'tags':'Tag'}
# sony_collection_name_template='{category:||: }{value}'
sony_collection_renaming_rules={}
sony_collection_name_template='{value}{category:| (|)}'
sony_collection_renaming_rules = {}
sony_collection_name_template = '{value}{category:| (|)}'
#: Specify how SONY collections are sorted
# Specify how SONY collections are sorted. This tweak is only applicable if
@ -402,7 +402,7 @@ vertical_scrolling_per_row = False
# Default: locale_for_sorting = '' -- use the language calibre displays in
# Example: locale_for_sorting = 'fr' -- sort using French rules.
# Example: locale_for_sorting = 'nb' -- sort using Norwegian rules.
locale_for_sorting = ''
locale_for_sorting = ''
#: The number of seconds to wait before sending emails
# The number of seconds to wait before sending emails when using a

17
setup/check.py
View File

@ -41,6 +41,10 @@ class Check(Command):
CACHE = 'check.json'
def add_options(self, parser):
parser.add_option('--fix', '--auto-fix', default=False, action='store_true',
help='Try to automatically fix some of the smallest errors')
def get_files(self):
yield from checkable_python_files(self.SRC)
@ -91,6 +95,10 @@ class Check(Command):
p = subprocess.Popen(['python', self.j(self.wn_path, 'whats_new.py'), f])
return p.wait() != 0
def perform_auto_fix(self):
p = subprocess.Popen(['ruff', 'check', '--fix-only'], text=True, stdout=subprocess.PIPE)
return p.stdout.read()
def run(self, opts):
self.fhash_cache = {}
cache = {}
@ -102,13 +110,20 @@ class Check(Command):
except OSError as err:
if err.errno != errno.ENOENT:
raise
if opts.fix:
self.info('\tAuto-fixing')
msg = self.perform_auto_fix()
self.info(msg)
dirty_files = tuple(f for f in self.get_files() if not self.is_cache_valid(f, cache))
try:
for i, f in enumerate(dirty_files):
self.info('\tChecking', f)
if self.file_has_errors(f):
self.info('%d files left to check' % (len(dirty_files) - i - 1))
edit_file(f)
try:
edit_file(f)
except FileNotFoundError:
pass # continue if the configured editor fail to be open
if self.file_has_errors(f):
raise SystemExit(1)
cache[f] = self.file_hash(f)

42
src/calibre/devices/boeye/driver.py
View File

@ -10,49 +10,49 @@ from calibre.devices.usbms.driver import USBMS
class BOEYE_BEX(USBMS):
name = 'BOEYE BEX reader driver'
gui_name = 'BOEYE BEX'
description = _('Communicate with BOEYE BEX Serial e-book readers.')
author = 'szboeye'
name = 'BOEYE BEX reader driver'
gui_name = 'BOEYE BEX'
description = _('Communicate with BOEYE BEX Serial e-book readers.')
author = 'szboeye'
supported_platforms = ['windows', 'osx', 'linux']
FORMATS = ['epub', 'mobi', 'fb2', 'lit', 'prc', 'pdf', 'rtf', 'txt', 'djvu', 'doc', 'chm', 'html', 'zip', 'pdb']
FORMATS = ['epub', 'mobi', 'fb2', 'lit', 'prc', 'pdf', 'rtf', 'txt', 'djvu', 'doc', 'chm', 'html', 'zip', 'pdb']
VENDOR_ID = [0x0085]
PRODUCT_ID = [0x600]
VENDOR_ID = [0x0085]
PRODUCT_ID = [0x600]
VENDOR_NAME = 'LINUX'
VENDOR_NAME = 'LINUX'
WINDOWS_MAIN_MEM = 'FILE-STOR_GADGET'
OSX_MAIN_MEM = 'Linux File-Stor Gadget Media'
OSX_MAIN_MEM = 'Linux File-Stor Gadget Media'
MAIN_MEMORY_VOLUME_LABEL = 'BOEYE BEX Storage Card'
EBOOK_DIR_MAIN = 'Documents'
EBOOK_DIR_MAIN = 'Documents'
SUPPORTS_SUB_DIRS = True
class BOEYE_BDX(USBMS):
name = 'BOEYE BDX reader driver'
gui_name = 'BOEYE BDX'
description = _('Communicate with BOEYE BDX serial e-book readers.')
author = 'szboeye'
name = 'BOEYE BDX reader driver'
gui_name = 'BOEYE BDX'
description = _('Communicate with BOEYE BDX serial e-book readers.')
author = 'szboeye'
supported_platforms = ['windows', 'osx', 'linux']
FORMATS = ['epub', 'mobi', 'fb2', 'lit', 'prc', 'pdf', 'rtf', 'txt', 'djvu', 'doc', 'chm', 'html', 'zip', 'pdb']
FORMATS = ['epub', 'mobi', 'fb2', 'lit', 'prc', 'pdf', 'rtf', 'txt', 'djvu', 'doc', 'chm', 'html', 'zip', 'pdb']
VENDOR_ID = [0x0085]
PRODUCT_ID = [0x800]
VENDOR_ID = [0x0085]
PRODUCT_ID = [0x800]
VENDOR_NAME = 'LINUX'
VENDOR_NAME = 'LINUX'
WINDOWS_MAIN_MEM = 'FILE-STOR_GADGET'
WINDOWS_CARD_A_MEM = 'FILE-STOR_GADGET'
OSX_MAIN_MEM = 'Linux File-Stor Gadget Media'
OSX_CARD_A_MEM = 'Linux File-Stor Gadget Media'
OSX_MAIN_MEM = 'Linux File-Stor Gadget Media'
OSX_CARD_A_MEM = 'Linux File-Stor Gadget Media'
MAIN_MEMORY_VOLUME_LABEL = 'BOEYE BDX Internal Memory'
STORAGE_CARD_VOLUME_LABEL = 'BOEYE BDX Storage Card'
EBOOK_DIR_MAIN = 'Documents'
EBOOK_DIR_MAIN = 'Documents'
EBOOK_DIR_CARD_A = 'Documents'
SUPPORTS_SUB_DIRS = True

4
src/calibre/devices/hanlin/driver.py
View File

@ -97,8 +97,8 @@ class HANLINV5(HANLINV3):
gui_name = 'Hanlin V5'
description = _('Communicate with Hanlin V5 e-book readers.')
VENDOR_ID = [0x0492]
PRODUCT_ID = [0x8813]
VENDOR_ID = [0x0492]
PRODUCT_ID = [0x8813]
BCD = [0x319]
OSX_MAIN_MEM = 'Hanlin V5 Internal Memory'

6
src/calibre/devices/kindle/apnx_page_generator/page_group.py
View File

@ -11,7 +11,7 @@ class PageGroup:
"""Simulate constructor overloading"""
def __init__(self, page_locations: Union[int, List[int]], page_number_type: PageNumberTypes, first_value: int,
page_labels: Union[str, List[str], None] = None):
if page_locations.__class__ == int:
if page_locations.__class__ is int:
self.page_locations: List[int] = [page_locations]
else:
self.page_locations: List[int] = page_locations
@ -19,7 +19,7 @@ class PageGroup:
self.__first_value = first_value
if page_number_type == PageNumberTypes.Custom:
assert page_labels is not None
if page_labels.__class__ == str:
if page_labels.__class__ is str:
assert 1 == len(self.page_locations) and len(page_labels) > 0
self.__page_number_labels: List[str] = [page_labels]
else:
@ -28,7 +28,7 @@ class PageGroup:
self.__page_number_labels: List[str] = page_labels
def append(self, page_location: Union[int, Tuple[int, str]]) -> None:
if page_location.__class__ == int:
if page_location.__class__ is int:
assert self.__page_number_type != PageNumberTypes.Custom
self.page_locations.append(page_location)
else:

2
src/calibre/devices/kindle/apnx_page_generator/pages.py
View File

@ -11,7 +11,7 @@ from calibre.devices.kindle.apnx_page_generator.page_number_type import PageNumb
class Pages:
def __init__(self, page_locations: Optional[List[int]] = None):
if page_locations.__class__ == list:
if page_locations.__class__ is list:
self.__pages_groups: List[PageGroup] = [PageGroup(page_locations, PageNumberTypes.Arabic, 1)]
else:
self.__pages_groups: List[PageGroup] = []

2
src/calibre/devices/usbms/device.py
View File

@ -673,7 +673,7 @@ class Device(DeviceConfig, DevicePlugin):
hal = get_hal()
vols = hal.get_volumes(d)
if verbose:
print("FBSD: ", vols)
print("FBSD:\t", vols)
ok, mv = hal.mount_volumes(vols)
if not ok:

8
src/calibre/devices/usbms/hal.py
View File

@ -106,19 +106,19 @@ class HAL:
# Mount Point becomes Mount Path
mp += '/'
if DEBUG:
print("FBSD: mounted", vol['label'], "on", mp)
print("FBSD:\tmounted", vol['label'], "on", mp)
if mtd == 0:
ans['_main_prefix'], ans['_main_vol'] = mp, vol['vol']
if DEBUG:
print("FBSD: main = ", mp)
print("FBSD:\tmain = ", mp)
elif mtd == 1:
ans['_card_a_prefix'], ans['_card_a_vol'] = mp, vol['vol']
if DEBUG:
print("FBSD: card a = ", mp)
print("FBSD:\tcard a = ", mp)
elif mtd == 2:
ans['_card_b_prefix'], ans['_card_b_vol'] = mp, vol['vol']
if DEBUG:
print("FBSD: card b = ", mp)
print("FBSD:\tcard b = ", mp)
break
mtd += 1

10
src/calibre/devices/winusb.py
View File

@ -307,27 +307,27 @@ SPDRP_LOCATION_PATHS = DWORD(0x00000023)
CR_CODES, CR_CODE_NAMES = {}, {}
for line in '''\
#define CR_SUCCESS 0x00000000
#define CR_SUCCESS 0x00000000
#define CR_DEFAULT 0x00000001
#define CR_OUT_OF_MEMORY 0x00000002
#define CR_INVALID_POINTER 0x00000003
#define CR_INVALID_FLAG 0x00000004
#define CR_INVALID_DEVNODE 0x00000005
#define CR_INVALID_DEVINST CR_INVALID_DEVNODE
#define CR_INVALID_DEVINST CR_INVALID_DEVNODE
#define CR_INVALID_RES_DES 0x00000006
#define CR_INVALID_LOG_CONF 0x00000007
#define CR_INVALID_ARBITRATOR 0x00000008
#define CR_INVALID_NODELIST 0x00000009
#define CR_DEVNODE_HAS_REQS 0x0000000A
#define CR_DEVINST_HAS_REQS CR_DEVNODE_HAS_REQS
#define CR_DEVINST_HAS_REQS CR_DEVNODE_HAS_REQS
#define CR_INVALID_RESOURCEID 0x0000000B
#define CR_DLVXD_NOT_FOUND 0x0000000C
#define CR_NO_SUCH_DEVNODE 0x0000000D
#define CR_NO_SUCH_DEVINST CR_NO_SUCH_DEVNODE
#define CR_NO_SUCH_DEVINST CR_NO_SUCH_DEVNODE
#define CR_NO_MORE_LOG_CONF 0x0000000E
#define CR_NO_MORE_RES_DES 0x0000000F
#define CR_ALREADY_SUCH_DEVNODE 0x00000010
#define CR_ALREADY_SUCH_DEVINST CR_ALREADY_SUCH_DEVNODE
#define CR_ALREADY_SUCH_DEVINST CR_ALREADY_SUCH_DEVNODE
#define CR_INVALID_RANGE_LIST 0x00000011
#define CR_INVALID_RANGE 0x00000012
#define CR_FAILURE 0x00000013

Some files were not shown because too many files have changed in this diff Show More