mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Fix typos in recipes/
This commit is contained in:
parent
f0308f23a9
commit
6eb95a700c
@ -47,7 +47,7 @@ class AdvancedUserRecipe1282101454(BasicNewsRecipe):
|
|||||||
masthead_url = 'http://gawand.org/wp-content/uploads/2010/06/ajc-logo.gif'
|
masthead_url = 'http://gawand.org/wp-content/uploads/2010/06/ajc-logo.gif'
|
||||||
|
|
||||||
# Pick your poison. Business seems to be mostly cross-linked articles. Premium and cross-linked
|
# Pick your poison. Business seems to be mostly cross-linked articles. Premium and cross-linked
|
||||||
# articels will be dropped.
|
# articles will be dropped.
|
||||||
feeds = [
|
feeds = [
|
||||||
('Breaking News', 'http://www.ajc.com/list/rss/online/ajc-auto-list-iphone-topnews/aFKq/'),
|
('Breaking News', 'http://www.ajc.com/list/rss/online/ajc-auto-list-iphone-topnews/aFKq/'),
|
||||||
('Metro and Georgia',
|
('Metro and Georgia',
|
||||||
|
@ -234,8 +234,8 @@ class BBCNews(BasicNewsRecipe):
|
|||||||
#
|
#
|
||||||
oldest_article = 1.5
|
oldest_article = 1.5
|
||||||
|
|
||||||
# Number of simultaneous downloads. 20 is consistantly working fine on the
|
# Number of simultaneous downloads. 20 is consistently working fine on the
|
||||||
# BBC News feeds with no problems. Speeds things up from the defualt of 5.
|
# BBC News feeds with no problems. Speeds things up from the default of 5.
|
||||||
# If you have a lot of feeds and/or have increased oldest_article above 2
|
# If you have a lot of feeds and/or have increased oldest_article above 2
|
||||||
# then you may wish to try increasing simultaneous_downloads to 25-30,
|
# then you may wish to try increasing simultaneous_downloads to 25-30,
|
||||||
# Or, of course, if you are in a hurry. [I've not tried beyond 20.]
|
# Or, of course, if you are in a hurry. [I've not tried beyond 20.]
|
||||||
|
@ -42,7 +42,7 @@ class BBCBrasilRecipe(BasicNewsRecipe):
|
|||||||
#
|
#
|
||||||
# There are 68 feeds below which constitute the bulk of the available rss
|
# There are 68 feeds below which constitute the bulk of the available rss
|
||||||
# feeds on the BBC web site. These include 5 blogs by editors and
|
# feeds on the BBC web site. These include 5 blogs by editors and
|
||||||
# correspondants, 16 sports feeds, 15 'sub' regional feeds (Eg. North West
|
# correspondents, 16 sports feeds, 15 'sub' regional feeds (Eg. North West
|
||||||
# Wales, Scotland Business), and 7 Welsh language feeds.
|
# Wales, Scotland Business), and 7 Welsh language feeds.
|
||||||
#
|
#
|
||||||
# Some of the feeds are low volume (Eg. blogs), or very low volume (Eg. Click)
|
# Some of the feeds are low volume (Eg. blogs), or very low volume (Eg. Click)
|
||||||
@ -108,8 +108,8 @@ class BBCBrasilRecipe(BasicNewsRecipe):
|
|||||||
#
|
#
|
||||||
oldest_article = 1.5
|
oldest_article = 1.5
|
||||||
|
|
||||||
# Number of simultaneous downloads. 20 is consistantly working fine on the
|
# Number of simultaneous downloads. 20 is consistently working fine on the
|
||||||
# BBC News feeds with no problems. Speeds things up from the defualt of 5.
|
# BBC News feeds with no problems. Speeds things up from the default of 5.
|
||||||
# If you have a lot of feeds and/or have increased oldest_article above 2
|
# If you have a lot of feeds and/or have increased oldest_article above 2
|
||||||
# then you may wish to try increasing simultaneous_downloads to 25-30,
|
# then you may wish to try increasing simultaneous_downloads to 25-30,
|
||||||
# Or, of course, if you are in a hurry. [I've not tried beyond 20.]
|
# Or, of course, if you are in a hurry. [I've not tried beyond 20.]
|
||||||
@ -383,7 +383,7 @@ class BBCBrasilRecipe(BasicNewsRecipe):
|
|||||||
skip_reg_exp = '^.*skip.*$'
|
skip_reg_exp = '^.*skip.*$'
|
||||||
|
|
||||||
# Extra things to remove due to the addition of 'storycontent' in keep_only_tags,
|
# Extra things to remove due to the addition of 'storycontent' in keep_only_tags,
|
||||||
# which are the alterative table design based pages. The purpose of some of these
|
# which are the alternative table design based pages. The purpose of some of these
|
||||||
# is not entirely clear from the pages (which are a total mess!).
|
# is not entirely clear from the pages (which are a total mess!).
|
||||||
|
|
||||||
# Remove mapping based tags, Eg. <map id="world_map">
|
# Remove mapping based tags, Eg. <map id="world_map">
|
||||||
|
@ -7,17 +7,17 @@ from calibre.web.feeds.news import BasicNewsRecipe
|
|||||||
|
|
||||||
|
|
||||||
class germanyBSI(BasicNewsRecipe):
|
class germanyBSI(BasicNewsRecipe):
|
||||||
# Titel of the Recipe
|
# Title of the Recipe
|
||||||
# title = 'News des Bundesamt für Sicherheit in der Informationstechnik'
|
# title = 'News des Bundesamt für Sicherheit in der Informationstechnik'
|
||||||
title = 'BSI News - DE'
|
title = 'BSI News - DE'
|
||||||
cover_url = 'https://www.bsi.bund.de/SiteGlobals/Frontend/Images/BSI/logo.png'
|
cover_url = 'https://www.bsi.bund.de/SiteGlobals/Frontend/Images/BSI/logo.png'
|
||||||
# Author
|
# Author
|
||||||
__author__ = 'Volker Heggemann, VoHe'
|
__author__ = 'Volker Heggemann, VoHe'
|
||||||
# oldes article to download (in days) ---- can be edit by user
|
# oldest article to download (in days) ---- can be edit by user
|
||||||
oldest_article = 7
|
oldest_article = 7
|
||||||
# describes itself, ---- can be edit by user
|
# describes itself, ---- can be edit by user
|
||||||
max_articles_per_feed = 100
|
max_articles_per_feed = 100
|
||||||
# speed up the download on fast computers be carefull (I test max.20)
|
# speed up the download on fast computers be careful (I test max.20)
|
||||||
# ---- can be edit by user
|
# ---- can be edit by user
|
||||||
simultaneous_downloads = 10
|
simultaneous_downloads = 10
|
||||||
# description, some Reader show this in titlepage
|
# description, some Reader show this in titlepage
|
||||||
|
@ -63,7 +63,7 @@ class CaravanMagazine(BasicNewsRecipe):
|
|||||||
raise ValueError('Login failed, check your username and password')
|
raise ValueError('Login failed, check your username and password')
|
||||||
return br
|
return br
|
||||||
|
|
||||||
# To parse artice toc
|
# To parse article toc
|
||||||
def parse_index(self):
|
def parse_index(self):
|
||||||
base_url = 'https://www.caravanmagazine.in/'
|
base_url = 'https://www.caravanmagazine.in/'
|
||||||
soup = self.index_to_soup('{0}magazine'.format(base_url))
|
soup = self.index_to_soup('{0}magazine'.format(base_url))
|
||||||
|
@ -68,7 +68,7 @@ class CaravanMagazineHindi(BasicNewsRecipe):
|
|||||||
raise ValueError('Login failed, check your username and password')
|
raise ValueError('Login failed, check your username and password')
|
||||||
return br
|
return br
|
||||||
|
|
||||||
# To parse artice toc
|
# To parse article toc
|
||||||
def parse_index(self):
|
def parse_index(self):
|
||||||
base_url = 'https://www.caravanmagazine.in/'
|
base_url = 'https://www.caravanmagazine.in/'
|
||||||
soup = self.index_to_soup('{0}magazine'.format(base_url))
|
soup = self.index_to_soup('{0}magazine'.format(base_url))
|
||||||
|
@ -7,7 +7,7 @@ class AdvancedUserRecipe1278162597(BasicNewsRecipe):
|
|||||||
oldest_article = 7
|
oldest_article = 7
|
||||||
max_articles_per_feed = 100
|
max_articles_per_feed = 100
|
||||||
|
|
||||||
pubisher = 'www.ce.cn - China Economic net - Beijing'
|
publisher = 'www.ce.cn - China Economic net - Beijing'
|
||||||
description = 'China Economic Net Magazine'
|
description = 'China Economic Net Magazine'
|
||||||
category = 'Economic News Magazine, Chinese, China'
|
category = 'Economic News Magazine, Chinese, China'
|
||||||
feeds = [
|
feeds = [
|
||||||
|
@ -17,7 +17,7 @@ class AdvancedUserRecipe1294946868(BasicNewsRecipe):
|
|||||||
publisher = u'Grupo Prisa'
|
publisher = u'Grupo Prisa'
|
||||||
|
|
||||||
__author__ = 'Luis Hernandez'
|
__author__ = 'Luis Hernandez'
|
||||||
description = 'spanish web about money and bussiness, free edition'
|
description = 'spanish web about money and business, free edition'
|
||||||
|
|
||||||
cover_url = 'http://www.prisa.com/images/logos/logo_cinco_dias.gif'
|
cover_url = 'http://www.prisa.com/images/logos/logo_cinco_dias.gif'
|
||||||
oldest_article = 2
|
oldest_article = 2
|
||||||
|
@ -90,7 +90,7 @@ class Clarin(BasicNewsRecipe):
|
|||||||
|
|
||||||
remove_attributes = ['lang']
|
remove_attributes = ['lang']
|
||||||
|
|
||||||
# Images on hightlights view
|
# Images on highlights view
|
||||||
def populate_article_metadata(self, article, soup, first):
|
def populate_article_metadata(self, article, soup, first):
|
||||||
if first and hasattr(self, 'add_toc_thumbnail'):
|
if first and hasattr(self, 'add_toc_thumbnail'):
|
||||||
picdiv = soup.find('img')
|
picdiv = soup.find('img')
|
||||||
|
@ -4,7 +4,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
|
|||||||
class DaytonBeachNewsJournal(BasicNewsRecipe):
|
class DaytonBeachNewsJournal(BasicNewsRecipe):
|
||||||
title = 'Daytona Beach News Journal'
|
title = 'Daytona Beach News Journal'
|
||||||
__author__ = 'BRGriff'
|
__author__ = 'BRGriff'
|
||||||
pubisher = 'News-JournalOnline.com'
|
publisher = 'News-JournalOnline.com'
|
||||||
description = 'Daytona Beach, Florida, Newspaper'
|
description = 'Daytona Beach, Florida, Newspaper'
|
||||||
category = 'News, Daytona Beach, Florida'
|
category = 'News, Daytona Beach, Florida'
|
||||||
oldest_article = 1
|
oldest_article = 1
|
||||||
|
@ -3,7 +3,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
|
|||||||
# 1: Base Version
|
# 1: Base Version
|
||||||
# 2: Added rules for wdr.de, ndr.de, br-online.de
|
# 2: Added rules for wdr.de, ndr.de, br-online.de
|
||||||
# 3: Added rules for rbb-online.de, boerse.ard.de, sportschau.de
|
# 3: Added rules for rbb-online.de, boerse.ard.de, sportschau.de
|
||||||
# 4: New design of tagesschau.de implemented. Simplyfied.
|
# 4: New design of tagesschau.de implemented. Simplified.
|
||||||
# 5: Taken out the pictures.
|
# 5: Taken out the pictures.
|
||||||
|
|
||||||
|
|
||||||
|
@ -105,8 +105,8 @@ class DunyaHalleri(BasicNewsRecipe):
|
|||||||
p.append(img)
|
p.append(img)
|
||||||
div.replaceWith(p)
|
div.replaceWith(p)
|
||||||
|
|
||||||
# youtube embeded normalization
|
# youtube embedded normalization
|
||||||
# this block finds the cover image for each embeded youtube video then
|
# this block finds the cover image for each embedded youtube video then
|
||||||
# changes it to "a href" and "img"
|
# changes it to "a href" and "img"
|
||||||
for iframe in soup.findAll('iframe'):
|
for iframe in soup.findAll('iframe'):
|
||||||
a = new_tag(soup, 'a')
|
a = new_tag(soup, 'a')
|
||||||
@ -124,7 +124,7 @@ class DunyaHalleri(BasicNewsRecipe):
|
|||||||
a_href = 'https://www.youtube.com/watch?v=' + m.group('vid')
|
a_href = 'https://www.youtube.com/watch?v=' + m.group('vid')
|
||||||
else:
|
else:
|
||||||
# not youtube
|
# not youtube
|
||||||
# default cover image for non-youtube embeded pages
|
# default cover image for non-youtube embedded pages
|
||||||
img_src = 'http://www.warnerclassics.com/img_style/default_video_m.jpg'
|
img_src = 'http://www.warnerclassics.com/img_style/default_video_m.jpg'
|
||||||
a_href = iframe['src']
|
a_href = iframe['src']
|
||||||
|
|
||||||
|
@ -170,8 +170,8 @@ class DunyaHalleri_HaftaninOzeti(BasicNewsRecipe):
|
|||||||
p.append(img)
|
p.append(img)
|
||||||
div.replaceWith(p)
|
div.replaceWith(p)
|
||||||
|
|
||||||
# youtube embeded normalization
|
# youtube embedded normalization
|
||||||
# this block finds the cover image for each embeded youtube video then
|
# this block finds the cover image for each embedded youtube video then
|
||||||
# changes it to "a href" and "img"
|
# changes it to "a href" and "img"
|
||||||
for iframe in soup.findAll('iframe'):
|
for iframe in soup.findAll('iframe'):
|
||||||
a = new_tag(soup, 'a')
|
a = new_tag(soup, 'a')
|
||||||
@ -189,7 +189,7 @@ class DunyaHalleri_HaftaninOzeti(BasicNewsRecipe):
|
|||||||
a_href = 'https://www.youtube.com/watch?v=' + m.group('vid')
|
a_href = 'https://www.youtube.com/watch?v=' + m.group('vid')
|
||||||
else:
|
else:
|
||||||
# not youtube
|
# not youtube
|
||||||
# default cover image for non-youtube embeded pages
|
# default cover image for non-youtube embedded pages
|
||||||
img_src = 'http://www.warnerclassics.com/img_style/default_video_m.jpg'
|
img_src = 'http://www.warnerclassics.com/img_style/default_video_m.jpg'
|
||||||
a_href = iframe['src']
|
a_href = iframe['src']
|
||||||
|
|
||||||
|
@ -162,6 +162,6 @@ class eenadu(BasicNewsRecipe):
|
|||||||
today = datetime.now()
|
today = datetime.now()
|
||||||
if (today - date) > timedelta(1.5):
|
if (today - date) > timedelta(1.5):
|
||||||
self.abort_article('Skipping old article')
|
self.abort_article('Skipping old article')
|
||||||
else: # may not be an artilce.
|
else: # may not be an article.
|
||||||
self.abort_article()
|
self.abort_article()
|
||||||
return soup
|
return soup
|
||||||
|
@ -21,7 +21,7 @@ class NYTimes(BasicNewsRecipe):
|
|||||||
def nejm_get_index(self):
|
def nejm_get_index(self):
|
||||||
return self.index_to_soup('http://www.focus.pl/')
|
return self.index_to_soup('http://www.focus.pl/')
|
||||||
|
|
||||||
# To parse artice toc
|
# To parse article toc
|
||||||
def parse_index(self):
|
def parse_index(self):
|
||||||
soup = self.nejm_get_index()
|
soup = self.nejm_get_index()
|
||||||
|
|
||||||
|
@ -64,7 +64,7 @@ class gazetaprawna(BasicNewsRecipe):
|
|||||||
]
|
]
|
||||||
|
|
||||||
def parse_feeds(self):
|
def parse_feeds(self):
|
||||||
self.log(_('Gazeta Prawna overrided parse_feeds()'))
|
self.log(_('Gazeta Prawna overrode parse_feeds()'))
|
||||||
parsed_feeds = BasicNewsRecipe.parse_feeds(self)
|
parsed_feeds = BasicNewsRecipe.parse_feeds(self)
|
||||||
for n, feed in enumerate(parsed_feeds):
|
for n, feed in enumerate(parsed_feeds):
|
||||||
for a, article in enumerate(feed):
|
for a, article in enumerate(feed):
|
||||||
|
@ -13,16 +13,16 @@ terms_to_search_for = (
|
|||||||
|
|
||||||
|
|
||||||
class google_news_de(BasicNewsRecipe):
|
class google_news_de(BasicNewsRecipe):
|
||||||
# Titel of the Recipe - this is a sample
|
# Title of the Recipe - this is a sample
|
||||||
title = 'Google News'
|
title = 'Google News'
|
||||||
cover_url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/d/da/Google_News_icon.svg/500px-Google_News_icon.svg.png'
|
cover_url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/d/da/Google_News_icon.svg/500px-Google_News_icon.svg.png'
|
||||||
# Author
|
# Author
|
||||||
__author__ = 'Volker Heggemann, VoHe'
|
__author__ = 'Volker Heggemann, VoHe'
|
||||||
# oldes article to download (in days) ---- can be edit by user
|
# oldest article to download (in days) ---- can be edit by user
|
||||||
oldest_article = 2
|
oldest_article = 2
|
||||||
# describes itself, ---- can be edit by user
|
# describes itself, ---- can be edit by user
|
||||||
max_articles_per_feed = 200
|
max_articles_per_feed = 200
|
||||||
# speed up the download on fast computers be carefull (I test max.20)
|
# speed up the download on fast computers be careful (I test max.20)
|
||||||
# ---- can be edit by user
|
# ---- can be edit by user
|
||||||
simultaneous_downloads = 10
|
simultaneous_downloads = 10
|
||||||
# description, some Reader show this in titlepage
|
# description, some Reader show this in titlepage
|
||||||
@ -64,7 +64,7 @@ class google_news_de(BasicNewsRecipe):
|
|||||||
)
|
)
|
||||||
for searchfor in terms_to_search_for:
|
for searchfor in terms_to_search_for:
|
||||||
self.feeds.append(
|
self.feeds.append(
|
||||||
('Google news intrested in ' + searchfor,
|
('Google news interested in ' + searchfor,
|
||||||
'https://news.google.com/news?cf=all&hl=' + country_code +
|
'https://news.google.com/news?cf=all&hl=' + country_code +
|
||||||
'+&pz=1&ned=' + country_code + '&q=' + searchfor + '&output=rss'))
|
'+&pz=1&ned=' + country_code + '&q=' + searchfor + '&output=rss'))
|
||||||
return BasicNewsRecipe.get_feeds(self)
|
return BasicNewsRecipe.get_feeds(self)
|
||||||
|
@ -19,7 +19,7 @@ class AdvancedUserRecipe1277305250(BasicNewsRecipe):
|
|||||||
__author__ = 'rty'
|
__author__ = 'rty'
|
||||||
__version__ = '1.0'
|
__version__ = '1.0'
|
||||||
language = 'zh'
|
language = 'zh'
|
||||||
pubisher = 'http://www.infzm.com'
|
publisher = 'http://www.infzm.com'
|
||||||
description = 'Chinese Weekly Tabloid'
|
description = 'Chinese Weekly Tabloid'
|
||||||
category = 'News, China'
|
category = 'News, China'
|
||||||
remove_javascript = True
|
remove_javascript = True
|
||||||
|
@ -15,7 +15,7 @@ class JakartaGlobe(BasicNewsRecipe):
|
|||||||
(u'Sports', u'http://www.thejakartaglobe.com/sports/feed/'),
|
(u'Sports', u'http://www.thejakartaglobe.com/sports/feed/'),
|
||||||
]
|
]
|
||||||
__author__ = 'rty'
|
__author__ = 'rty'
|
||||||
pubisher = 'JakartaGlobe.com'
|
publisher = 'JakartaGlobe.com'
|
||||||
description = 'JakartaGlobe, Indonesia, Newspaper'
|
description = 'JakartaGlobe, Indonesia, Newspaper'
|
||||||
category = 'News, Indonesia'
|
category = 'News, Indonesia'
|
||||||
|
|
||||||
|
@ -31,7 +31,7 @@ class JournalofHospitalMedicine(BasicNewsRecipe):
|
|||||||
def johm_get_index(self):
|
def johm_get_index(self):
|
||||||
return self.index_to_soup('https://shmpublications.onlinelibrary.wiley.com/toc/15535606/current')
|
return self.index_to_soup('https://shmpublications.onlinelibrary.wiley.com/toc/15535606/current')
|
||||||
|
|
||||||
# To parse artice toc
|
# To parse article toc
|
||||||
def parse_index(self):
|
def parse_index(self):
|
||||||
soup = self.johm_get_index()
|
soup = self.johm_get_index()
|
||||||
toc = soup.find(id='issueTocGroups')
|
toc = soup.find(id='issueTocGroups')
|
||||||
|
@ -59,7 +59,7 @@ class JerusalemPost(BasicNewsRecipe):
|
|||||||
# ------------------------------------------
|
# ------------------------------------------
|
||||||
return print_url
|
return print_url
|
||||||
|
|
||||||
# example of how links should be formated
|
# example of how links should be formatted
|
||||||
# -------------------------------------------------------------------------
|
# -------------------------------------------------------------------------
|
||||||
# org version = http://fr.jpost.com/servlet/Satellite?pagename=JFrench/JPArticle/ShowFull&cid=1282804806075
|
# org version = http://fr.jpost.com/servlet/Satellite?pagename=JFrench/JPArticle/ShowFull&cid=1282804806075
|
||||||
# print version = http://fr.jpost.com/servlet/Satellite?cid=1282804806075&pagename=JFrench%2FJPArticle%2FPrinter
|
# print version = http://fr.jpost.com/servlet/Satellite?cid=1282804806075&pagename=JFrench%2FJPArticle%2FPrinter
|
||||||
|
@ -49,7 +49,7 @@ class KANewsRecipe(BasicNewsRecipe):
|
|||||||
dict(name=['span'], attrs={'class': 'comm_info'}),
|
dict(name=['span'], attrs={'class': 'comm_info'}),
|
||||||
dict(name=['h3'], attrs={'id': 'artdetail_unterzeile'})]
|
dict(name=['h3'], attrs={'id': 'artdetail_unterzeile'})]
|
||||||
|
|
||||||
# removing style attribute _after_ removing specifig tags above
|
# removing style attribute _after_ removing specific tags above
|
||||||
remove_attributes = ['width', 'height', 'style']
|
remove_attributes = ['width', 'height', 'style']
|
||||||
|
|
||||||
extra_css = '''
|
extra_css = '''
|
||||||
|
@ -50,7 +50,7 @@ class JASN(BasicNewsRecipe):
|
|||||||
def jasn_get_index(self):
|
def jasn_get_index(self):
|
||||||
return self.index_to_soup('http://jasn.asnjournals.org/current.shtml')
|
return self.index_to_soup('http://jasn.asnjournals.org/current.shtml')
|
||||||
|
|
||||||
# To parse artice toc
|
# To parse article toc
|
||||||
def parse_index(self):
|
def parse_index(self):
|
||||||
parse_soup = self.jasn_get_index()
|
parse_soup = self.jasn_get_index()
|
||||||
|
|
||||||
|
@ -6,13 +6,13 @@ from calibre.web.feeds.news import BasicNewsRecipe
|
|||||||
|
|
||||||
class AdvancedUserRecipe1591780224(BasicNewsRecipe):
|
class AdvancedUserRecipe1591780224(BasicNewsRecipe):
|
||||||
title = 'Linux News'
|
title = 'Linux News'
|
||||||
# Titel of the Recipe
|
# Title of the Recipe
|
||||||
cover_url = 'https://linuxnews.de/wp-content/themes/linuxnews/images/linuxnews-logo.png'
|
cover_url = 'https://linuxnews.de/wp-content/themes/linuxnews/images/linuxnews-logo.png'
|
||||||
# Author
|
# Author
|
||||||
__author__ = 'Volker Heggemann, VoHe'
|
__author__ = 'Volker Heggemann, VoHe'
|
||||||
# oldes article to download (in days)
|
# oldest article to download (in days)
|
||||||
oldest_article = 4
|
oldest_article = 4
|
||||||
# speed up the download on fast computers be carefull (I test max.20)
|
# speed up the download on fast computers be careful (I test max.20)
|
||||||
# ---- can be edit by user
|
# ---- can be edit by user
|
||||||
simultaneous_downloads = 10
|
simultaneous_downloads = 10
|
||||||
# description, some Reader show this in titlepage
|
# description, some Reader show this in titlepage
|
||||||
|
@ -7,7 +7,7 @@ class LondonFreePress(BasicNewsRecipe):
|
|||||||
oldest_article = 4
|
oldest_article = 4
|
||||||
max_articles_per_feed = 100
|
max_articles_per_feed = 100
|
||||||
|
|
||||||
pubisher = 'lfpress.com'
|
publisher = 'lfpress.com'
|
||||||
description = 'Ontario Canada Newspaper'
|
description = 'Ontario Canada Newspaper'
|
||||||
category = 'News, Ontario, Canada'
|
category = 'News, Ontario, Canada'
|
||||||
remove_javascript = True
|
remove_javascript = True
|
||||||
|
@ -5,7 +5,7 @@
|
|||||||
# 1) Summary of the article are noow available
|
# 1) Summary of the article are noow available
|
||||||
# 2) Additional sections International, France, Economie and Culture have
|
# 2) Additional sections International, France, Economie and Culture have
|
||||||
# been added through custom entries in the function my_parse_index.
|
# been added through custom entries in the function my_parse_index.
|
||||||
# 3) Fix the cover image so it doesnt disappear from the Kindle menu
|
# 3) Fix the cover image so it doesn't disappear from the Kindle menu
|
||||||
# ( cover image format is changed to .jpeg)
|
# ( cover image format is changed to .jpeg)
|
||||||
# 14 Jan 2021 - Add Mediapart Logo url as masthead_url and change cover
|
# 14 Jan 2021 - Add Mediapart Logo url as masthead_url and change cover
|
||||||
# by overlaying the date on top of the Mediapart cover
|
# by overlaying the date on top of the Mediapart cover
|
||||||
@ -69,7 +69,7 @@ class Mediapart(BasicNewsRecipe):
|
|||||||
# The feed at 'http://www.mediapart.fr/articles/feed' only displayed the 10
|
# The feed at 'http://www.mediapart.fr/articles/feed' only displayed the 10
|
||||||
# last elements so the articles are indexed on specific pages
|
# last elements so the articles are indexed on specific pages
|
||||||
# in the function my_parse_index. In this function the article are parsed
|
# in the function my_parse_index. In this function the article are parsed
|
||||||
# using the funtion get_articles and the dict values dict_article_sources
|
# using the function get_articles and the dict values dict_article_sources
|
||||||
|
|
||||||
def parse_feeds(self):
|
def parse_feeds(self):
|
||||||
feeds = super(Mediapart, self).parse_feeds()
|
feeds = super(Mediapart, self).parse_feeds()
|
||||||
|
@ -33,7 +33,7 @@ from calibre.utils.magick import Image
|
|||||||
Changed a lot of custom code into calibre code as the default code of calibre has become much faster since the first version fo this recipe
|
Changed a lot of custom code into calibre code as the default code of calibre has become much faster since the first version fo this recipe
|
||||||
Added new feeds
|
Added new feeds
|
||||||
Updated css
|
Updated css
|
||||||
Changed order of regex to speedup proces
|
Changed order of regex to speedup process
|
||||||
Version 1.9.3 23-05-2012
|
Version 1.9.3 23-05-2012
|
||||||
Updated Cover image
|
Updated Cover image
|
||||||
Version 1.9.4 19-04-2013
|
Version 1.9.4 19-04-2013
|
||||||
|
@ -6,17 +6,17 @@ from datetime import datetime
|
|||||||
|
|
||||||
|
|
||||||
class MyDealzDE(BasicNewsRecipe):
|
class MyDealzDE(BasicNewsRecipe):
|
||||||
# Titel of the Recipe
|
# Title of the Recipe
|
||||||
title = 'MyDealz'
|
title = 'MyDealz'
|
||||||
# Author
|
# Author
|
||||||
__author__ = 'Volker Heggemann, VoHe'
|
__author__ = 'Volker Heggemann, VoHe'
|
||||||
# oldes article to download (in days) ---- can be edit by user
|
# oldest article to download (in days) ---- can be edit by user
|
||||||
oldest_article = 5
|
oldest_article = 5
|
||||||
# describes itself, ---- can be edit by user
|
# describes itself, ---- can be edit by user
|
||||||
max_articles_per_feed = 100
|
max_articles_per_feed = 100
|
||||||
# Cover Picture
|
# Cover Picture
|
||||||
cover_url = 'https://pbs.twimg.com/profile_images/817053687545741313/0wFqvfqC_400x400.jpg'
|
cover_url = 'https://pbs.twimg.com/profile_images/817053687545741313/0wFqvfqC_400x400.jpg'
|
||||||
# speed up the download on fast computers be carefull (I test max.20)
|
# speed up the download on fast computers be careful (I test max.20)
|
||||||
# ---- can be edit by user
|
# ---- can be edit by user
|
||||||
simultaneous_downloads = 10
|
simultaneous_downloads = 10
|
||||||
# description, some Reader show this in titlepage
|
# description, some Reader show this in titlepage
|
||||||
|
@ -4,7 +4,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
|
|||||||
class NBOnline(BasicNewsRecipe):
|
class NBOnline(BasicNewsRecipe):
|
||||||
title = u'Nikkei Business Online'
|
title = u'Nikkei Business Online'
|
||||||
language = 'ja'
|
language = 'ja'
|
||||||
description = u'Nikkei Business Online.\u6CE8\uFF1A\u30E6\u30FC\u30B6\u30FC\u540D\u306Bemail\u30A2\u30C9\u30EC\u30B9\u3068\u30E6\u30FC\u30B6\u30FC\u540D\u3092\u30BB\u30DF\u30B3\u30ED\u30F3\u3067\u533A\u5207\u3063\u3066\u5165\u308C\u3066\u304F\u3060\u3055\u3044\u3002\u4F8B\uFF1Aemail@address.jp;username . PLEASE NOTE: You need to put your email address and username into username filed separeted by ; (semi-colon).' # noqa
|
description = u'Nikkei Business Online.\u6CE8\uFF1A\u30E6\u30FC\u30B6\u30FC\u540D\u306Bemail\u30A2\u30C9\u30EC\u30B9\u3068\u30E6\u30FC\u30B6\u30FC\u540D\u3092\u30BB\u30DF\u30B3\u30ED\u30F3\u3067\u533A\u5207\u3063\u3066\u5165\u308C\u3066\u304F\u3060\u3055\u3044\u3002\u4F8B\uFF1Aemail@address.jp;username . PLEASE NOTE: You need to put your email address and username into username field separated by ; (semi-colon).' # noqa
|
||||||
__author__ = 'Ado Nishimura'
|
__author__ = 'Ado Nishimura'
|
||||||
needs_subscription = True
|
needs_subscription = True
|
||||||
oldest_article = 7
|
oldest_article = 7
|
||||||
|
@ -41,7 +41,7 @@ class NEJM(BasicNewsRecipe):
|
|||||||
def nejm_get_index(self):
|
def nejm_get_index(self):
|
||||||
return self.index_to_soup('https://www.nejm.org/toc/nejm/medical-journal')
|
return self.index_to_soup('https://www.nejm.org/toc/nejm/medical-journal')
|
||||||
|
|
||||||
# To parse artice toc
|
# To parse article toc
|
||||||
def parse_index(self):
|
def parse_index(self):
|
||||||
soup = self.nejm_get_index()
|
soup = self.nejm_get_index()
|
||||||
feeds = []
|
feeds = []
|
||||||
|
@ -324,7 +324,7 @@ class NewYorkTimes(BasicNewsRecipe):
|
|||||||
return self.parse_web_sections()
|
return self.parse_web_sections()
|
||||||
return self.parse_todays_page()
|
return self.parse_todays_page()
|
||||||
|
|
||||||
# The NYT occassionally returns bogus articles for some reason just in case
|
# The NYT occasionally returns bogus articles for some reason just in case
|
||||||
# it is because of cookies, dont store cookies
|
# it is because of cookies, dont store cookies
|
||||||
def get_browser(self, *args, **kwargs):
|
def get_browser(self, *args, **kwargs):
|
||||||
return self
|
return self
|
||||||
|
@ -324,7 +324,7 @@ class NewYorkTimes(BasicNewsRecipe):
|
|||||||
return self.parse_web_sections()
|
return self.parse_web_sections()
|
||||||
return self.parse_todays_page()
|
return self.parse_todays_page()
|
||||||
|
|
||||||
# The NYT occassionally returns bogus articles for some reason just in case
|
# The NYT occasionally returns bogus articles for some reason just in case
|
||||||
# it is because of cookies, dont store cookies
|
# it is because of cookies, dont store cookies
|
||||||
def get_browser(self, *args, **kwargs):
|
def get_browser(self, *args, **kwargs):
|
||||||
return self
|
return self
|
||||||
|
@ -22,7 +22,7 @@ class AdvancedUserRecipe1279258912(BasicNewsRecipe):
|
|||||||
u'http://feeds.feedburner.com/orlandosentinel/features/lifestyle'),
|
u'http://feeds.feedburner.com/orlandosentinel/features/lifestyle'),
|
||||||
]
|
]
|
||||||
__author__ = 'rty'
|
__author__ = 'rty'
|
||||||
pubisher = 'OrlandoSentinel.com'
|
publisher = 'OrlandoSentinel.com'
|
||||||
description = 'Orlando, Florida, Newspaper'
|
description = 'Orlando, Florida, Newspaper'
|
||||||
category = 'News, Orlando, Florida'
|
category = 'News, Orlando, Florida'
|
||||||
|
|
||||||
|
@ -11,7 +11,7 @@ class AdvancedUserRecipe1277129332(BasicNewsRecipe):
|
|||||||
max_articles_per_feed = 100
|
max_articles_per_feed = 100
|
||||||
__author__ = 'ceapas'
|
__author__ = 'ceapas'
|
||||||
|
|
||||||
pubisher = 'people.com.cn'
|
publisher = 'people.com.cn'
|
||||||
description = 'People Daily Newspaper'
|
description = 'People Daily Newspaper'
|
||||||
language = 'zh'
|
language = 'zh'
|
||||||
category = 'News, China'
|
category = 'News, China'
|
||||||
|
@ -6,15 +6,15 @@ from datetime import datetime
|
|||||||
|
|
||||||
|
|
||||||
class PressePortalDE(BasicNewsRecipe):
|
class PressePortalDE(BasicNewsRecipe):
|
||||||
# Titel of the Recipe
|
# Title of the Recipe
|
||||||
title = 'Presseportal DE'
|
title = 'Presseportal DE'
|
||||||
# Author
|
# Author
|
||||||
__author__ = 'Volker Heggemann, VoHe'
|
__author__ = 'Volker Heggemann, VoHe'
|
||||||
# oldes article to download (in days) ---- can be edit by user
|
# oldest article to download (in days) ---- can be edit by user
|
||||||
oldest_article = 1
|
oldest_article = 1
|
||||||
# describes itself, ---- can be edit by user
|
# describes itself, ---- can be edit by user
|
||||||
max_articles_per_feed = 100
|
max_articles_per_feed = 100
|
||||||
# speed up the download on fast computers be carefull (I test max.20)
|
# speed up the download on fast computers be careful (I test max.20)
|
||||||
# ---- can be edit by user
|
# ---- can be edit by user
|
||||||
simultaneous_downloads = 10
|
simultaneous_downloads = 10
|
||||||
# description, some Reader show this in titlepage
|
# description, some Reader show this in titlepage
|
||||||
|
@ -25,7 +25,7 @@ class TodaysZaman_en(BasicNewsRecipe):
|
|||||||
|
|
||||||
# def preprocess_html(self, soup):
|
# def preprocess_html(self, soup):
|
||||||
# return self.adeify_images(soup)
|
# return self.adeify_images(soup)
|
||||||
# def print_version(self, url): #there is a probem caused by table format
|
# def print_version(self, url): #there is a problem caused by table format
|
||||||
# return
|
# return
|
||||||
# url.replace('http://www.todayszaman.com/newsDetail_getNewsById.action?load=detay&',
|
# url.replace('http://www.todayszaman.com/newsDetail_getNewsById.action?load=detay&',
|
||||||
# 'http://www.todayszaman.com/newsDetail_openPrintPage.action?')
|
# 'http://www.todayszaman.com/newsDetail_openPrintPage.action?')
|
||||||
|
@ -15,16 +15,16 @@ feel free to modify this to your own needs
|
|||||||
|
|
||||||
|
|
||||||
class Spiegel_DE_all(BasicNewsRecipe):
|
class Spiegel_DE_all(BasicNewsRecipe):
|
||||||
# Titel of the Recipe
|
# Title of the Recipe
|
||||||
title = u'Spiegel Online RSS - German alle Themen'
|
title = u'Spiegel Online RSS - German alle Themen'
|
||||||
# Author
|
# Author
|
||||||
__author__ = u'Volker Heggemann, VoHe'
|
__author__ = u'Volker Heggemann, VoHe'
|
||||||
# oldes 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!
|
# be careful, if there is a lot of news, the file size exceeds!
|
||||||
oldest_article = 7
|
oldest_article = 7
|
||||||
# describes itself, ---- can be edit by user
|
# describes itself, ---- can be edit by user
|
||||||
max_articles_per_feed = 100
|
max_articles_per_feed = 100
|
||||||
# speed up the download on fast computers be carefull (I test max.20)
|
# speed up the download on fast computers be careful (I test max.20)
|
||||||
# ---- can be edit by user
|
# ---- can be edit by user
|
||||||
simultaneous_downloads = 10
|
simultaneous_downloads = 10
|
||||||
# description, some Reader show this in titlepage
|
# description, some Reader show this in titlepage
|
||||||
|
@ -24,7 +24,7 @@ class T_Online_Recipe(BasicNewsRecipe):
|
|||||||
masthead_url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/3/31/T-online.de.svg/1280px-T-online.de.svg.png'
|
masthead_url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/3/31/T-online.de.svg/1280px-T-online.de.svg.png'
|
||||||
# all possible feeds look at:
|
# all possible feeds look at:
|
||||||
# https://www.t-online.de/themen/rss-feed/
|
# https://www.t-online.de/themen/rss-feed/
|
||||||
# there are tons of feeds, may you just type the words of intrest after the http://feeds.t-online.de/rss/ link.
|
# there are tons of feeds, just type the words of interest after the http://feeds.t-online.de/rss/ link.
|
||||||
feeds = [
|
feeds = [
|
||||||
('Germany', 'http://feeds.t-online.de/rss/deutschland'),
|
('Germany', 'http://feeds.t-online.de/rss/deutschland'),
|
||||||
('NEWS', 'http://feeds.t-online.de/rss/nachrichten'),
|
('NEWS', 'http://feeds.t-online.de/rss/nachrichten'),
|
||||||
|
@ -4,7 +4,7 @@ import re
|
|||||||
# 1: Base Version
|
# 1: Base Version
|
||||||
# 2: Added rules for wdr.de, ndr.de, br-online.de
|
# 2: Added rules for wdr.de, ndr.de, br-online.de
|
||||||
# 3: Added rules for rbb-online.de, boerse.ard.de, sportschau.de
|
# 3: Added rules for rbb-online.de, boerse.ard.de, sportschau.de
|
||||||
# 4: New design of tagesschau.de implemented. Simplyfied.
|
# 4: New design of tagesschau.de implemented. Simplified.
|
||||||
# 5: Taken out the pictures.
|
# 5: Taken out the pictures.
|
||||||
|
|
||||||
|
|
||||||
|
@ -19,7 +19,7 @@ class TheBudgetFashionista(BasicNewsRecipe):
|
|||||||
use_embedded_content = False
|
use_embedded_content = False
|
||||||
encoding = 'utf-8'
|
encoding = 'utf-8'
|
||||||
publisher = 'TBF GROUP, LLC.'
|
publisher = 'TBF GROUP, LLC.'
|
||||||
category = 'news, fashion, comsetics, women'
|
category = 'news, fashion, cosmetics, women'
|
||||||
lang = 'en-US'
|
lang = 'en-US'
|
||||||
language = 'en'
|
language = 'en'
|
||||||
auto_cleanup = True
|
auto_cleanup = True
|
||||||
|
@ -4,7 +4,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
|
|||||||
class AdvancedUserRecipe1278773519(BasicNewsRecipe):
|
class AdvancedUserRecipe1278773519(BasicNewsRecipe):
|
||||||
title = u'Waco Tribune Herald'
|
title = u'Waco Tribune Herald'
|
||||||
__author__ = 'rty'
|
__author__ = 'rty'
|
||||||
pubisher = 'A Robinson Media Company'
|
publisher = 'A Robinson Media Company'
|
||||||
description = 'Waco, Texas, Newspaper'
|
description = 'Waco, Texas, Newspaper'
|
||||||
category = 'News, Texas, Waco'
|
category = 'News, Texas, Waco'
|
||||||
oldest_article = 7
|
oldest_article = 7
|
||||||
|
@ -53,7 +53,7 @@ class CanWestPaper(BasicNewsRecipe):
|
|||||||
dict(name='li', attrs={'class': 'print'}), dict(name='li', attrs={'class': 'share'}), dict(name='ul', attrs={'class': 'bullet'})]
|
dict(name='li', attrs={'class': 'print'}), dict(name='li', attrs={'class': 'share'}), dict(name='ul', attrs={'class': 'bullet'})]
|
||||||
|
|
||||||
def preprocess_html(self, soup):
|
def preprocess_html(self, soup):
|
||||||
# delete iempty id attributes--they screw up the TOC for unknow reasons
|
# delete iempty id attributes--they screw up the TOC for unknown reasons
|
||||||
divtags = soup.findAll('div', attrs={'id': ''})
|
divtags = soup.findAll('div', attrs={'id': ''})
|
||||||
if divtags:
|
if divtags:
|
||||||
for div in divtags:
|
for div in divtags:
|
||||||
|
@ -6,7 +6,7 @@ class AdvancedUserRecipe1277647803(BasicNewsRecipe):
|
|||||||
__author__ = 'rty'
|
__author__ = 'rty'
|
||||||
__version__ = '1.0'
|
__version__ = '1.0'
|
||||||
oldest_article = 2
|
oldest_article = 2
|
||||||
pubisher = 'www.winnipegsun.com'
|
publisher = 'www.winnipegsun.com'
|
||||||
description = 'Winnipeg Newspaper'
|
description = 'Winnipeg Newspaper'
|
||||||
category = 'News, Winnipeg, Canada'
|
category = 'News, Winnipeg, Canada'
|
||||||
max_articles_per_feed = 100
|
max_articles_per_feed = 100
|
||||||
|
@ -28,5 +28,5 @@ class Yagmur(BasicNewsRecipe):
|
|||||||
(u'Yagmur', u'http://open.dapper.net/services/yagmur'),
|
(u'Yagmur', u'http://open.dapper.net/services/yagmur'),
|
||||||
]
|
]
|
||||||
|
|
||||||
def print_version(self, url): # there is a probem caused by table format
|
def print_version(self, url): # there is a problem caused by table format
|
||||||
return url.replace('http://www.yagmurdergisi.com.tr/konu_goster.php?konu_id=', 'http://www.yagmurdergisi.com.tr/yazformati.php?konu_id=')
|
return url.replace('http://www.yagmurdergisi.com.tr/konu_goster.php?konu_id=', 'http://www.yagmurdergisi.com.tr/yazformati.php?konu_id=')
|
||||||
|
@ -27,5 +27,5 @@ class YeniUmit(BasicNewsRecipe):
|
|||||||
(u'Yeni Umit', u'http://open.dapper.net/services/yeniumit'),
|
(u'Yeni Umit', u'http://open.dapper.net/services/yeniumit'),
|
||||||
]
|
]
|
||||||
|
|
||||||
def print_version(self, url): # there is a probem caused by table format
|
def print_version(self, url): # there is a problem caused by table format
|
||||||
return url.replace('http://www.yeniumit.com.tr/konular', 'http://www.yeniumit.com.tr/yazdir')
|
return url.replace('http://www.yeniumit.com.tr/konular', 'http://www.yeniumit.com.tr/yazdir')
|
||||||
|
@ -95,7 +95,7 @@ class ZAOBAO(BasicNewsRecipe):
|
|||||||
return soup
|
return soup
|
||||||
|
|
||||||
def parse_feeds(self):
|
def parse_feeds(self):
|
||||||
self.log(_('ZAOBAO overrided parse_feeds()'))
|
self.log(_('ZAOBAO overrode parse_feeds()'))
|
||||||
parsed_feeds = BasicNewsRecipe.parse_feeds(self)
|
parsed_feeds = BasicNewsRecipe.parse_feeds(self)
|
||||||
|
|
||||||
for id, obj in enumerate(self.INDEXES):
|
for id, obj in enumerate(self.INDEXES):
|
||||||
|
Loading…
x
Reference in New Issue
Block a user