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

Update Frontline and Outlook Magazine

Browse Source
This commit is contained in:
Kovid Goyal 2023-04-15 21:24:44 +05:30
parent c94e0b719f
commit c0d533f7ec
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 33 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

54
recipes/frontline.recipe
View File

@ -1,7 +1,6 @@
from collections import defaultdict from collections import defaultdict
from calibre.web.feeds.news import BasicNewsRecipe, classes from calibre.web.feeds.news import BasicNewsRecipe, classes
class Frontline(BasicNewsRecipe): class Frontline(BasicNewsRecipe):
title = u'Frontline' title = u'Frontline'
__author__ = 'unkn0wn' __author__ = 'unkn0wn'
@ -16,18 +15,21 @@ class Frontline(BasicNewsRecipe):
remove_attributes = ['height', 'width'] remove_attributes = ['height', 'width']
resolve_internal_links = True resolve_internal_links = True
extra_css = ''' extra_css = '''
.overline{ font-size:small; color:#404040; } .environment, .publish-time, .author { font-size:small; color:#404040; }
.person-name { font-size:small; font-weight:bold; } .caption { font-size:small; text-align:center; }
.lead-img-caption, .caption-cont { font-size:small; text-align:center; } img { display:block; margin:0 auto; }
.question {font-weight:bold;}
''' '''
keep_only_tags = [ keep_only_tags = [
classes('article') dict(name='div', attrs={'class':'container article-section'})
] ]
remove_tags = [ remove_tags = [
classes('shareicon-article articleBottomLine secheader mobilesocialicons'), classes(
dict(name='h2', attrs={'class':'title'}) 'breadcrumb comments-shares share-page article-video '
'referpara slide-mobile title-patch hide-mobile related-stories'
),
] ]
def preprocess_html(self, soup): def preprocess_html(self, soup):
@ -36,11 +38,11 @@ class Frontline(BasicNewsRecipe):
source = img.findPrevious('source', srcset=True) source = img.findPrevious('source', srcset=True)
img.extract() img.extract()
if source: if source:
source['src'] = source['srcset'] source['src'] = source['srcset'].replace('_320','_1200')
source.name = 'img' source.name = 'img'
else: else:
img['src'] = img['data-original'] img['src'] = img['data-original']
for cap in soup.findAll(**classes('caption-cont')): for cap in soup.findAll(**classes('caption')):
cap.name = 'figcaption' cap.name = 'figcaption'
return soup return soup
@ -50,30 +52,32 @@ class Frontline(BasicNewsRecipe):
return soup return soup
def parse_index(self): def parse_index(self):
soup = self.index_to_soup('https://frontline.thehindu.com/magazine/') soup = self.index_to_soup('https://frontline.thehindu.com/current-issue/')
issue = soup.find(**classes('sptar-archive-item')).find('a')['href']
self.log(issue) if cover := soup.find('div', attrs={'class':'magazine'}):
soup = self.index_to_soup(issue) self.cover_url = cover.find(**classes('sptar-image')).img['data-original'].replace('_320', '_1200')
time = soup.find(**classes('date')).findNext('h3') self.log('Cover ', self.cover_url)
if time: if desc := cover.find(**classes('sub-text')):
self.timefmt = ' ' + self.tag_to_string(time) self.description = self.tag_to_string(desc)
self.log('Downloading Issue:', self.timefmt)
self.cover_url = soup.find(**classes('sptar-cover-item')).find('img')['data-original'].replace('FREE_320', 'FREE_810')
feeds_dict = defaultdict(list) feeds_dict = defaultdict(list)
for div in soup.findAll('div', attrs={'class':'brief-list-item'}):
a = div.find(**classes('brief-title')).find('a') mag = soup.find(**classes('section-magazine'))
for div in mag.findAll('div', attrs={'class':'content'}):
a = div.find(**classes('title')).find('a')
url = a['href'] url = a['href']
title = self.tag_to_string(a) title = self.tag_to_string(a)
section = 'Articles' section = 'Articles'
cat = div.find(**classes('brief-cat')) if cat := div.find(**classes('label')):
if cat:
section = self.tag_to_string(cat) section = self.tag_to_string(cat)
desc = '' desc = ''
art = div.find(**classes('artbody'))
if art: if art := div.find(**classes('sub-text')):
desc = self.tag_to_string(art) desc = self.tag_to_string(art)
if auth := div.find(**classes('author')):
desc = self.tag_to_string(auth) + ' | ' + desc
if not url or not title: if not url or not title:
continue continue
self.log(section, '\n\t', title, '\n\t', desc, '\n\t\t', url) self.log(section, '\n\t', title, '\n\t', desc, '\n\t\t', url)
feeds_dict[section].append({"title": title, "url": url}) feeds_dict[section].append({"title": title, "url": url, "description": desc})
return [(section, articles) for section, articles in feeds_dict.items()] return [(section, articles) for section, articles in feeds_dict.items()]

3
recipes/outlook_india.recipe
View File

@ -32,6 +32,9 @@ class outlook(BasicNewsRecipe):
) )
] ]
def get_browser(self):
return BasicNewsRecipe.get_browser(self, user_agent='common_words/based')
def parse_index(self): def parse_index(self):
soup = self.index_to_soup('https://www.outlookindia.com/magazine') soup = self.index_to_soup('https://www.outlookindia.com/magazine')
div = soup.find('div', attrs={'class':'wrapper'}) div = soup.find('div', attrs={'class':'wrapper'})