diff --git a/recipes/ancient_egypt.recipe b/recipes/ancient_egypt.recipe
index fdede7664d..c2116a00a4 100644
--- a/recipes/ancient_egypt.recipe
+++ b/recipes/ancient_egypt.recipe
@@ -46,13 +46,21 @@ class ancientegypt(BasicNewsRecipe):
exp.name = 'p'
return soup
+ recipe_specific_options = {
+ 'issue': {
+ 'short': 'Enter the Issue Number you want to download ',
+ 'long': 'For example, 136'
+ }
+ }
+
def parse_index(self):
soup = self.index_to_soup('https://the-past.com/category/magazines/ae/')
art = soup.find('article', attrs={'class':lambda x: x and 'tag-magazines' in x.split()})
url = art.h2.a['href']
- # for past editions, add url
- # url = ''
+ d = self.recipe_specific_options.get('issue')
+ if d and isinstance(d, str):
+ url = 'https://the-past.com/magazines/ae/ancient-egypt-magazine-' + d + '/'
issue = self.index_to_soup(url)
ti = issue.find('h1', attrs={'class':lambda x: x and 'post-title' in x.split()})
diff --git a/recipes/atlantic.recipe b/recipes/atlantic.recipe
index 9766ed9ae3..0733c23895 100644
--- a/recipes/atlantic.recipe
+++ b/recipes/atlantic.recipe
@@ -199,7 +199,9 @@ class TheAtlantic(BasicNewsRecipe):
self.cover_url = img['src']
current_section, current_articles = 'Cover Story', []
feeds = []
- for x in soup.findAll(**prefix_classes('TocFeaturedSection_heading__ TocSection_heading__ TocHeroGridItem_hedLink__ TocGridItem_hedLink__')):
+ for x in soup.findAll(**prefix_classes(
+ 'TocFeaturedSection_heading__ TocSection_heading__ TocHeroGridItem_hedLink__ TocGridItem_hedLink__ RiverGridItem_hedLink__'
+ )):
cls = x['class']
if not isinstance(cls, str):
cls = ' '.join(cls)
diff --git a/recipes/bloomberg-business-week.recipe b/recipes/bloomberg-business-week.recipe
index 3d94f6868a..d6bfa7f12d 100644
--- a/recipes/bloomberg-business-week.recipe
+++ b/recipes/bloomberg-business-week.recipe
@@ -5,9 +5,6 @@ from datetime import datetime
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.web.feeds.news import BasicNewsRecipe, classes
-# https://www.bloomberg.com/magazine/businessweek/24_12
-# Set past_edition to edition id, which is '24_12'.
-past_edition = None
def get_contents(x):
if x == '':
@@ -47,7 +44,7 @@ def get_contents(x):
class Bloomberg(BasicNewsRecipe):
title = 'Bloomberg Businessweek'
- language = 'en'
+ language = 'en_US'
__author__ = 'unkn0wn'
no_stylesheets = True
remove_attributes = ['style', 'height', 'width']
@@ -60,6 +57,13 @@ class Bloomberg(BasicNewsRecipe):
)
remove_empty_feeds = True
+ recipe_specific_options = {
+ 'date': {
+ 'short': 'The ID of the edition to download (YY_XX format)',
+ 'long': 'For example, 24_17\nHint: Edition ID can be found at the end of its URL'
+ }
+ }
+
remove_tags = [
dict(name=['button', 'svg', 'meta']),
dict(name='div', attrs={'id':['bb-that', 'bb-nav']}),
@@ -82,7 +86,8 @@ class Bloomberg(BasicNewsRecipe):
inx = 'https://cdn-mobapi.bloomberg.com'
sec = self.index_to_soup(inx + '/wssmobile/v1/bw/news/list?limit=1', raw=True)
id = json.loads(sec)['magazines'][0]['id']
- if past_edition:
+ past_edition = self.recipe_specific_options.get('date')
+ if past_edition and isinstance(past_edition, str):
id = past_edition
edit = self.index_to_soup(inx + '/wssmobile/v1/bw/news/week/' + id, raw=True)
d = json.loads(edit)
diff --git a/recipes/bloomberg.recipe b/recipes/bloomberg.recipe
index 3a9557570b..656a9aa9fe 100644
--- a/recipes/bloomberg.recipe
+++ b/recipes/bloomberg.recipe
@@ -55,7 +55,7 @@ class Bloomberg(BasicNewsRecipe):
'Bloomberg delivers business and markets news, data, analysis, and video'
' to the world, featuring stories from Businessweek and Bloomberg News.'
)
- oldest_article = 1 # days
+ oldest_article = 1.2 # days
resolve_internal_links = True
remove_empty_feeds = True
cover_url = 'https://assets.bwbx.io/images/users/iqjWHBFdfxIU/ivUxvlPidC3M/v0/600x-1.jpg'
@@ -78,7 +78,18 @@ class Bloomberg(BasicNewsRecipe):
.news-figure-credit {font-size:small; text-align:center; color:#202020;}
'''
+ recipe_specific_options = {
+ 'days': {
+ 'short': 'Oldest article to download from this news source. In days ',
+ 'long': 'For example, 0.5, gives you articles for the past 12 hours',
+ 'default': str(oldest_article),
+ }
+ }
+
def parse_index(self):
+ d = self.recipe_specific_options.get('days')
+ if d and isinstance(d, str):
+ self.oldest_article = float(d)
inx = 'https://cdn-mobapi.bloomberg.com'
sec = self.index_to_soup(inx + '/wssmobile/v1/navigation/bloomberg_app/search-v2', raw=True)
sec_data = json.loads(sec)['searchNav']
diff --git a/recipes/business_standard_print.recipe b/recipes/business_standard_print.recipe
index b7c772e0d9..ff7d63ff98 100644
--- a/recipes/business_standard_print.recipe
+++ b/recipes/business_standard_print.recipe
@@ -4,12 +4,6 @@ from datetime import datetime
from calibre.web.feeds.news import BasicNewsRecipe
from html5_parser import parse
-today = datetime.today().strftime('%d-%m-%Y')
-
-# today = '20-09-2023'
-
-day, month, year = (int(x) for x in today.split('-'))
-dt = datetime(year, month, day)
class BusinessStandardPrint(BasicNewsRecipe):
title = 'Business Standard Print Edition'
@@ -18,18 +12,12 @@ class BusinessStandardPrint(BasicNewsRecipe):
language = 'en_IN'
masthead_url = 'https://bsmedia.business-standard.com/include/_mod/site/html5/images/business-standard-logo.png'
encoding = 'utf-8'
- timefmt = ' [' + dt.strftime('%b %d, %Y') + ']'
resolve_internal_links = True
remove_empty_feeds = True
no_stylesheets = True
remove_javascript = True
- remove_attributes = ['width', 'height', 'float', 'style']
-
- def __init__(self, *args, **kwargs):
- BasicNewsRecipe.__init__(self, *args, **kwargs)
- if self.output_profile.short_name.startswith('kindle'):
- self.title = 'Business Standard ' + dt.strftime('%b %d, %Y')
+ remove_attributes = ['width', 'height', 'style']
def get_browser(self):
return BasicNewsRecipe.get_browser(self, user_agent='common_words/based')
@@ -40,16 +28,35 @@ class BusinessStandardPrint(BasicNewsRecipe):
extra_css = '''
img {display:block; margin:0 auto;}
+ .sub { font-style:italic; color:#202020; }
.auth, .cat { font-size:small; color:#202020; }
.cap { font-size:small; text-align:center; }
'''
+ recipe_specific_options = {
+ 'date': {
+ 'short': 'The date of the print edition to download (DD-MM-YYYY format)',
+ 'long': 'For example, 20-09-2023'
+ }
+ }
+
def get_cover_url(self):
- soup = self.index_to_soup('https://www.magzter.com/IN/Business-Standard-Private-Ltd/Business-Standard/Newspaper/')
- for citem in soup.findAll('meta', content=lambda s: s and s.endswith('view/3.jpg')):
- return citem['content']
+ d = self.recipe_specific_options.get('date')
+ if not (d and isinstance(d, str)):
+ soup = self.index_to_soup('https://www.magzter.com/IN/Business-Standard-Private-Ltd/Business-Standard/Newspaper/')
+ for citem in soup.findAll('meta', content=lambda s: s and s.endswith('view/3.jpg')):
+ return citem['content']
def parse_index(self):
+ today = datetime.today().strftime('%d-%m-%Y')
+ d = self.recipe_specific_options.get('date')
+ if d and isinstance(d, str):
+ today = d
+
+ day, month, year = (int(x) for x in today.split('-'))
+ dt = datetime(year, month, day)
+ self.timefmt = ' [' + dt.strftime('%b %d, %Y') + ']'
+
if dt.weekday() == 6:
self.log.warn(
'Business Standard Does Not Have A Print Publication On Sunday. The Reports'
@@ -97,10 +104,10 @@ class BusinessStandardPrint(BasicNewsRecipe):
if 'defaultArticleCat' in data and data['defaultArticleCat'] is not None:
if 'h1_tag' in data['defaultArticleCat'] and data['defaultArticleCat']['h1_tag'] is not None:
- cat = '' + data['defaultArticleCat']['h1_tag'] + '
' + data['defaultArticleCat']['h1_tag'] + '
'
if 'metaDescription' in data and data['metaDescription'] is not None:
- subhead = '' + data['metaDescription'] + '
'
+ subhead = '' + data['metaDescription'] + '
'
self.art_desc = data['metaDescription']
date = (datetime.fromtimestamp(int(data['publishDate']))).strftime('%b %d, %Y | %I:%M %p')
@@ -120,6 +127,13 @@ class BusinessStandardPrint(BasicNewsRecipe):
if 'alt_text' in data['featuredImageObj']:
caption = '' + data['featuredImageObj']['alt_text'] + ''
- body = data['htmlContent']
+ body = data['htmlContent'].replace('
\r\n\t\t ', '
')
- return '' + cat + title + subhead + auth + lede + caption + ''
+ return '' + cat + title + subhead + auth + lede + caption + '
' + body + '
'
+
+ def preprocess_html(self, soup):
+ for img in soup.findAll('img'):
+ img.attrs = {'src': img.get('src', '')}
+ for x in soup.findAll('div'):
+ x.attrs = {'class': x.get('class', '')}
+ return soup
diff --git a/recipes/economist.recipe b/recipes/economist.recipe
index 3ecf3082f5..9139ef5e20 100644
--- a/recipes/economist.recipe
+++ b/recipes/economist.recipe
@@ -215,7 +215,7 @@ class Economist(BasicNewsRecipe):
def publication_date(self):
edition_date = self.recipe_specific_options.get('date')
- if edition_date:
+ if edition_date and isinstance(edition_date, str):
return parse_only_date(edition_date, as_utc=False)
url = self.browser.open("https://www.economist.com/printedition").geturl()
return parse_only_date(url.split("/")[-1], as_utc=False)
@@ -245,7 +245,7 @@ class Economist(BasicNewsRecipe):
'operationName': 'LatestWeeklyAutoEditionQuery',
'variables': '{"ref":"/content/d06tg8j85rifiq3oo544c6b9j61dno2n"}',
}
- if edition_date:
+ if edition_date and isinstance(edition_date, str):
url = 'https://www.economist.com/weeklyedition/' + edition_date
soup = self.index_to_soup(url)
script_tag = soup.find("script", id="__NEXT_DATA__")
@@ -268,7 +268,7 @@ class Economist(BasicNewsRecipe):
def economist_parse_index(self, raw):
edition_date = self.recipe_specific_options.get('date')
- if edition_date:
+ if edition_date and isinstance(edition_date, str):
data = json.loads(raw)['data']['section']
else:
data = json.loads(raw)['data']['canonical']['hasPart']['parts'][0]
@@ -336,7 +336,7 @@ class Economist(BasicNewsRecipe):
def parse_index(self):
edition_date = self.recipe_specific_options.get('date')
# return self.economist_test_article()
- if edition_date:
+ if edition_date and isinstance(edition_date, str):
url = 'https://www.economist.com/weeklyedition/' + edition_date
self.timefmt = ' [' + edition_date + ']'
else:
@@ -423,10 +423,11 @@ class Economist(BasicNewsRecipe):
x.set('style', 'color:#404040;')
raw = etree.tostring(root, encoding='unicode')
return raw
+
def parse_index_from_printedition(self):
# return self.economist_test_article()
edition_date = self.recipe_specific_options.get('date')
- if edition_date:
+ if edition_date and isinstance(edition_date, str):
url = 'https://www.economist.com/weeklyedition/' + edition_date
self.timefmt = ' [' + edition_date + ']'
else:
diff --git a/recipes/economist_free.recipe b/recipes/economist_free.recipe
index 3ecf3082f5..9139ef5e20 100644
--- a/recipes/economist_free.recipe
+++ b/recipes/economist_free.recipe
@@ -215,7 +215,7 @@ class Economist(BasicNewsRecipe):
def publication_date(self):
edition_date = self.recipe_specific_options.get('date')
- if edition_date:
+ if edition_date and isinstance(edition_date, str):
return parse_only_date(edition_date, as_utc=False)
url = self.browser.open("https://www.economist.com/printedition").geturl()
return parse_only_date(url.split("/")[-1], as_utc=False)
@@ -245,7 +245,7 @@ class Economist(BasicNewsRecipe):
'operationName': 'LatestWeeklyAutoEditionQuery',
'variables': '{"ref":"/content/d06tg8j85rifiq3oo544c6b9j61dno2n"}',
}
- if edition_date:
+ if edition_date and isinstance(edition_date, str):
url = 'https://www.economist.com/weeklyedition/' + edition_date
soup = self.index_to_soup(url)
script_tag = soup.find("script", id="__NEXT_DATA__")
@@ -268,7 +268,7 @@ class Economist(BasicNewsRecipe):
def economist_parse_index(self, raw):
edition_date = self.recipe_specific_options.get('date')
- if edition_date:
+ if edition_date and isinstance(edition_date, str):
data = json.loads(raw)['data']['section']
else:
data = json.loads(raw)['data']['canonical']['hasPart']['parts'][0]
@@ -336,7 +336,7 @@ class Economist(BasicNewsRecipe):
def parse_index(self):
edition_date = self.recipe_specific_options.get('date')
# return self.economist_test_article()
- if edition_date:
+ if edition_date and isinstance(edition_date, str):
url = 'https://www.economist.com/weeklyedition/' + edition_date
self.timefmt = ' [' + edition_date + ']'
else:
@@ -423,10 +423,11 @@ class Economist(BasicNewsRecipe):
x.set('style', 'color:#404040;')
raw = etree.tostring(root, encoding='unicode')
return raw
+
def parse_index_from_printedition(self):
# return self.economist_test_article()
edition_date = self.recipe_specific_options.get('date')
- if edition_date:
+ if edition_date and isinstance(edition_date, str):
url = 'https://www.economist.com/weeklyedition/' + edition_date
self.timefmt = ' [' + edition_date + ']'
else:
diff --git a/recipes/harpers.recipe b/recipes/harpers.recipe
index 0c7ac1250c..be5a87086e 100644
--- a/recipes/harpers.recipe
+++ b/recipes/harpers.recipe
@@ -54,11 +54,24 @@ class Harpers(BasicNewsRecipe):
img['src'] = src.split()[0]
return soup
+ recipe_specific_options = {
+ 'date': {
+ 'short': 'The date of the edition to download (YYYY/MM format)',
+ 'long': 'For example, 2023/08',
+ }
+ }
+
def parse_index(self):
issues_soup = self.index_to_soup("https://harpers.org/issues/")
a_ele = issues_soup.select_one("div.issue-card a")
self.timefmt = ' [' + self.tag_to_string(a_ele.find(attrs={'class':'issue-title'})) + ']'
url = a_ele['href']
+
+ edition = self.recipe_specific_options.get('date')
+ if edition and isinstance(edition, str):
+ url = 'https://harpers.org/archive/' + edition
+ self.timefmt = ' [' +edition + ']'
+
soup = self.index_to_soup(url)
cov_div = soup.find('div', attrs={'class':'issue-cover'})
if cov_div:
diff --git a/recipes/hindu.recipe b/recipes/hindu.recipe
index 616e123cdd..8b81d0b405 100644
--- a/recipes/hindu.recipe
+++ b/recipes/hindu.recipe
@@ -32,7 +32,8 @@ class TheHindu(BasicNewsRecipe):
recipe_specific_options = {
'location': {
'short': 'The name of the local edition',
- 'long': 'If The Hindu is available in your local town/city,\nset this to your location, for example, hyderabad'
+ 'long': 'If The Hindu is available in your local town/city,\nset this to your location, for example, hyderabad',
+ 'default': 'international'
},
'date': {
'short': 'The date of the edition to download (YYYY-MM-DD format)',
@@ -60,47 +61,32 @@ class TheHindu(BasicNewsRecipe):
return soup
def parse_index(self):
- mag_url = None
- local_edition = self.recipe_specific_options.get('location')
- if local_edition:
- local_edition = 'th_' + local_edition
+ local_edition = 'th_international'
+ d = self.recipe_specific_options.get('location')
+ if d and isinstance(d, str):
+ local_edition = 'th_' + d
+
past_edition = self.recipe_specific_options.get('date')
dt = date.today()
- if past_edition:
- year, month, day = (int(x) for x in past_edition.split('-'))
+ if past_edition and isinstance(past_edition, str):
+ year, month, day = (int(x) for x in past_edition.split('-'))
dt = date(year, month, day)
- is_monday = dt.weekday() == 0
- is_friday = dt.weekday() == 4
- is_saturday = dt.weekday() == 5
- is_sunday = dt.weekday() == 6
+ today = dt.strftime('%Y-%m-%d')
+ self.log('Downloading The Hindu, ' + local_edition[3:] + ' edition, ' + today)
+ url = absurl('/todays-paper/' + today + '/' + local_edition + '/')
- if local_edition or past_edition:
- if local_edition is None:
- local_edition = 'th_chennai'
- today = date.today().strftime('%Y-%m-%d')
- if past_edition:
- today = past_edition
- self.log('Downloading past edition of', local_edition + ' from ' + today)
- url = absurl('/todays-paper/' + today + '/' + local_edition + '/')
- if is_monday:
- mag_url = url + '?supplement=' + local_edition + '-epbs'
- if is_saturday:
- mag_url = url + '?supplement=' + local_edition + '-mp'
- if is_sunday:
- mag_url = url + '?supplement=' + local_edition + '-sm'
- else:
- url = 'https://www.thehindu.com/todays-paper/'
- if is_monday:
- mag_url = url + '?supplement=th_chennai-epbs'
- if is_friday:
- mag_url = url + '?supplement=th_chennai-fr'
- if is_saturday:
- mag_url = url + '?supplement=th_chennai-mp'
- if is_sunday:
- mag_url = url + '?supplement=th_chennai-sm'
+ mag_url = None
+ if dt.weekday() == 0:
+ mag_url = url + '?supplement=' + local_edition + '-epbs'
+ if dt.weekday() == 4:
+ mag_url = url + '?supplement=' + local_edition + '-fr'
+ if dt.weekday() == 5:
+ mag_url = url + '?supplement=' + local_edition + '-mp'
+ if dt.weekday() == 6:
+ mag_url = url + '?supplement=' + local_edition + '-sm'
raw = self.index_to_soup(url, raw=True)
soup = self.index_to_soup(raw)
@@ -139,7 +125,7 @@ class TheHindu(BasicNewsRecipe):
title = item['articleheadline']
url = absurl(item['href'])
desc = 'Page no.' + item['pageno'] + ' | ' + item['teaser_text'] or ''
- self.log('\t', title, '\n\t\t', url)
+ self.log(' ', title, '\n\t', url)
feeds_dict[section].append({"title": title, "url": url, "description": desc})
return [(section, articles) for section, articles in feeds_dict.items()]
else:
diff --git a/recipes/lex_fridman_podcast.recipe b/recipes/lex_fridman_podcast.recipe
index 814c7d7902..5fc387f036 100644
--- a/recipes/lex_fridman_podcast.recipe
+++ b/recipes/lex_fridman_podcast.recipe
@@ -19,6 +19,20 @@ class lexfridman(BasicNewsRecipe):
timefmt = ' [%b, %Y]'
cover_url = 'https://i.scdn.co/image/ab6765630000ba8a563ebb538d297875b10114b7'
+ recipe_specific_options = {
+ 'days': {
+ 'short': 'Oldest article to download from this news source. In days ',
+ 'long': 'For example, 0.5, gives you articles from the past 12 hours',
+ 'default': str(oldest_article)
+ }
+ }
+
+ def __init__(self, *args, **kwargs):
+ BasicNewsRecipe.__init__(self, *args, **kwargs)
+ d = self.recipe_specific_options.get('days')
+ if d and isinstance(d, str):
+ self.oldest_article = float(d)
+
extra_css = '''
.ts-name { font-weight:bold; }
.ts-timestamp { font-size:small; }
diff --git a/recipes/military_history.recipe b/recipes/military_history.recipe
index ae35606799..09d330a09b 100644
--- a/recipes/military_history.recipe
+++ b/recipes/military_history.recipe
@@ -45,13 +45,21 @@ class milthist(BasicNewsRecipe):
exp.name = 'p'
return soup
+ recipe_specific_options = {
+ 'issue': {
+ 'short': 'Enter the Issue Number you want to download ',
+ 'long': 'For example, 136'
+ }
+ }
+
def parse_index(self):
soup = self.index_to_soup('https://the-past.com/category/magazines/mhm/')
art = soup.find('article', attrs={'class':lambda x: x and 'tag-magazines' in x.split()})
url = art.h2.a['href']
- # for past editions, add url
- # url = ''
+ d = self.recipe_specific_options.get('issue')
+ if d and isinstance(d, str):
+ url = 'https://the-past.com/magazines/military-history-matters-' + d + '/'
issue = self.index_to_soup(url)
ti = issue.find('h1', attrs={'class':lambda x: x and 'post-title' in x.split()})
diff --git a/recipes/minerva_magazine.recipe b/recipes/minerva_magazine.recipe
index 181d5c88f9..203d9b3520 100644
--- a/recipes/minerva_magazine.recipe
+++ b/recipes/minerva_magazine.recipe
@@ -45,13 +45,21 @@ class minerva(BasicNewsRecipe):
exp.name = 'p'
return soup
+ recipe_specific_options = {
+ 'issue': {
+ 'short': 'Enter the Issue Number you want to download ',
+ 'long': 'For example, 136'
+ }
+ }
+
def parse_index(self):
soup = self.index_to_soup('https://the-past.com/category/magazines/minerva/')
art = soup.find('article', attrs={'class':lambda x: x and 'tag-magazines' in x.split()})
url = art.h2.a['href']
- # for past editions, add url
- # url = ''
+ d = self.recipe_specific_options.get('issue')
+ if d and isinstance(d, str):
+ url = 'https://the-past.com/magazines/minerva-magazine-' + d + '/'
issue = self.index_to_soup(url)
ti = issue.find('h1', attrs={'class':lambda x: x and 'post-title' in x.split()})
diff --git a/recipes/natgeomag.recipe b/recipes/natgeomag.recipe
index d8933ee1c5..c95b239d8f 100644
--- a/recipes/natgeomag.recipe
+++ b/recipes/natgeomag.recipe
@@ -10,9 +10,6 @@ from calibre import prepare_string_for_xml as escape
from calibre.utils.iso8601 import parse_iso8601
from calibre.web.feeds.news import BasicNewsRecipe
-edition = date.today().strftime('%B-%Y')
-
-# edition = 'March-2023'
def classes(classes):
q = frozenset(classes.split(' '))
@@ -175,7 +172,18 @@ class NatGeo(BasicNewsRecipe):
.auth, .time, .sub { font-size:small; color:#5c5c5c; }
'''
+ recipe_specific_options = {
+ 'date': {
+ 'short': 'The date of the edition to download (Month-YYYY format)',
+ 'long': 'For example, March-2023'
+ }
+ }
+
def parse_index(self):
+ edition = date.today().strftime('%B-%Y')
+ d = self.recipe_specific_options.get('date')
+ if d and isinstance(d, str):
+ edition = d
url = 'https://www.nationalgeographic.com/magazine/issue/' + edition.lower()
self.log('Downloading ', url)
self.timefmt = ' [' + edition + ']'
@@ -185,7 +193,7 @@ class NatGeo(BasicNewsRecipe):
self.cover_url = soup.find('meta', attrs={'property':'og:image'})['content'].split('?')[0] + '?w=1000'
name = soup.find(attrs={'class':lambda x: x and 'Header__Description' in x.split()})
- self.title = 'National Geographic ' + self.tag_to_string(name)
+ # self.title = 'National Geographic ' + self.tag_to_string(name)
ans = {}
if photoart := soup.find(attrs={'class':lambda x: x and 'BgImagePromo__Container__Text__Link' in x.split()}):
section = 'Photo Essay'
diff --git a/recipes/psych.recipe b/recipes/psych.recipe
index 5cad8e823b..b5353a4f1e 100644
--- a/recipes/psych.recipe
+++ b/recipes/psych.recipe
@@ -53,7 +53,7 @@ class PsychologyToday(BasicNewsRecipe):
a = soup.find(**classes('magazine-thumbnail')).a
url = a['href']
past_edition = self.recipe_specific_options.get('date')
- if past_edition:
+ if past_edition and isinstance(past_edition, str):
url = '/us/magazine/archive/' + past_edition
soup = self.index_to_soup(absurl(url))
cov = soup.find(**classes('content-header--cover-image'))
diff --git a/recipes/reuters.recipe b/recipes/reuters.recipe
index 417d40a9e2..e22b1a61f4 100644
--- a/recipes/reuters.recipe
+++ b/recipes/reuters.recipe
@@ -21,7 +21,7 @@ class Reuters(BasicNewsRecipe):
masthead_url = 'https://www.reutersprofessional.com/wp-content/uploads/2024/03/primary-logo.svg'
language = 'en'
encoding = 'utf-8'
- oldest_article = 2 # days
+ oldest_article = 1.2 # days
no_javascript = True
no_stylesheets = True
remove_attributes = ['style', 'height', 'width']
@@ -30,10 +30,24 @@ class Reuters(BasicNewsRecipe):
extra_css = '''
.label, .auth { font-size:small; color:#202020; }
- .figc { font-size:small; text-align:center; }
+ .figc { font-size:small; }
img {display:block; margin:0 auto;}
'''
+ recipe_specific_options = {
+ 'days': {
+ 'short': 'Oldest article to download from this news source. In days ',
+ 'long': 'For example, 0.5, gives you articles from the past 12 hours',
+ 'default': str(oldest_article)
+ }
+ }
+
+ def __init__(self, *args, **kwargs):
+ BasicNewsRecipe.__init__(self, *args, **kwargs)
+ d = self.recipe_specific_options.get('days')
+ if d and isinstance(d, str):
+ self.oldest_article = float(d)
+
def parse_index(self):
index = 'https://www.reuters.com'
today = datetime.now()
diff --git a/recipes/tls_mag.recipe b/recipes/tls_mag.recipe
index d29b798b4e..c8f8b239b6 100644
--- a/recipes/tls_mag.recipe
+++ b/recipes/tls_mag.recipe
@@ -48,9 +48,21 @@ class tls(BasicNewsRecipe):
.det { font-size:small; color:#202020; font-weight:bold; }
'''
+ recipe_specific_options = {
+ 'date': {
+ 'short': 'The date of the edition to download\nlower case Month-DD-YYYY format',
+ 'long': 'For example, july-12-2024',
+ 'default': 'current-issue'
+ }
+ }
+
def parse_index(self):
- # for past edition, change the issue link below
issue = 'https://www.the-tls.co.uk/issues/current-issue/'
+
+ d = self.recipe_specific_options.get('date')
+ if d and isinstance(d, str):
+ issue = 'https://www.the-tls.co.uk/issues/' + d + '/'
+
url = 'https://www.the-tls.co.uk/wp-json/tls/v2/contents-page/' + get_id(issue)
raw = self.index_to_soup(url, raw=True)
data = json.loads(raw)
diff --git a/recipes/world_archeology.recipe b/recipes/world_archeology.recipe
index 103f159eb5..31d467a3fd 100644
--- a/recipes/world_archeology.recipe
+++ b/recipes/world_archeology.recipe
@@ -47,13 +47,21 @@ class worldarch(BasicNewsRecipe):
exp.name = 'p'
return soup
+ recipe_specific_options = {
+ 'issue': {
+ 'short': 'Enter the Issue Number you want to download ',
+ 'long': 'For example, 136'
+ }
+ }
+
def parse_index(self):
soup = self.index_to_soup('https://the-past.com/category/magazines/cwa/')
art = soup.find('article', attrs={'class':lambda x: x and 'tag-magazines' in x.split()})
url = art.h2.a['href']
- # for past editions, add url
- # url = ''
+ d = self.recipe_specific_options.get('issue')
+ if d and isinstance(d, str):
+ url = 'https://the-past.com/magazines/current-world-archaeology-' + d + '/'
issue = self.index_to_soup(url)
ti = issue.find('h1', attrs={'class':lambda x: x and 'post-title' in x.split()})
diff --git a/recipes/wsj.recipe b/recipes/wsj.recipe
index b8571040dc..35587f971d 100644
--- a/recipes/wsj.recipe
+++ b/recipes/wsj.recipe
@@ -107,7 +107,8 @@ class WSJ(BasicNewsRecipe):
return soup
def _download_cover(self):
- if not self.recipe_specific_options.get('date'):
+ d = self.recipe_specific_options.get('date')
+ if not (d and isinstance(d, str)):
import os
from contextlib import closing
@@ -143,7 +144,7 @@ class WSJ(BasicNewsRecipe):
past_edition = self.recipe_specific_options.get('date')
for itm in catalog['items']:
- if past_edition:
+ if past_edition and isinstance(past_edition, str):
if itm['key'] == 'ITPNEXTGEN' + past_edition:
key = itm['key']
manifest = itm['manifest']