Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

...

Browse Source
This commit is contained in:
Kovid Goyal 2022-11-27 13:59:54 +05:30
parent d9fa980ca4
commit a91a614142
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 7 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
recipes/hindu.recipe
View File

@ -11,7 +11,7 @@ def absurl(url):
return url return url
local_edition = 'th_hyderabad' local_edition = None
# Chennai is default edition, for other editions use 'th_hyderabad', 'th_bangalore', 'th_delhi', 'th_kolkata' etc # Chennai is default edition, for other editions use 'th_hyderabad', 'th_bangalore', 'th_delhi', 'th_kolkata' etc
@ -23,8 +23,9 @@ class TheHindu(BasicNewsRecipe):
masthead_url = 'https://www.thehindu.com/theme/images/th-online/thehindu-logo.svg' masthead_url = 'https://www.thehindu.com/theme/images/th-online/thehindu-logo.svg'
remove_attributes = ['style', 'height', 'width'] remove_attributes = ['style', 'height', 'width']
extra_css = '.caption{font-size:small; text-align:center;}'\ extra_css = '.caption{font-size:small; text-align:center;}'\
'.author{font-size:small;}'\ '.author{font-size:small; font-weight:bold;}'\
'.subhead{font-weight:bold;}' '.subhead, .subhead_lead {font-weight:bold;}'\
'img {display:block; margin:0 auto;}'
ignore_duplicate_articles = {'url'} ignore_duplicate_articles = {'url'}
@ -38,17 +39,11 @@ class TheHindu(BasicNewsRecipe):
def preprocess_html(self, soup): def preprocess_html(self, soup):
for cap in soup.findAll('p', attrs={'class':'caption'}): for cap in soup.findAll('p', attrs={'class':'caption'}):
cap.name = 'span' cap.name = 'figcaption'
for img in soup.findAll('img', attrs={'data-original':True}): for img in soup.findAll('img', attrs={'data-original':True}):
img['src'] = img['data-original'] img['src'] = img['data-original']
return soup return soup
def populate_article_metadata(self, article, soup, first):
if first and hasattr(self, 'add_toc_thumbnail'):
image = soup.find('img')
if image is not None:
self.add_toc_thumbnail(article, image['src'])
def parse_index(self): def parse_index(self):
if local_edition: if local_edition:
yr = str(date.today().year) yr = str(date.today().year)
@ -85,7 +80,7 @@ class TheHindu(BasicNewsRecipe):
section = sec.replace('TH_', '') section = sec.replace('TH_', '')
title = item['articleheadline'] title = item['articleheadline']
url = absurl(item['href']) url = absurl(item['href'])
desc = 'from page no.' + item['pageno'] + ' | ' + item['teaser_text'] or '' desc = 'Page no.' + item['pageno'] + ' | ' + item['teaser_text'] or ''
self.log('\t', title, '\n\t\t', url) self.log('\t', title, '\n\t\t', url)
feeds_dict[section].append({"title": title, "url": url, "description": desc}) 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()]

2
recipes/indian_express_print_edition.recipe
View File

@ -66,7 +66,7 @@ class IndianExpressPrint(BasicNewsRecipe):
def parse_index(self): def parse_index(self):
soup = self.index_to_soup('https://indianexpress.com/todays-paper/') soup = self.index_to_soup('https://indianexpress.com/todays-paper/')
feeds_dict = defaultdict(list) feeds_dict = defaultdict(list)
for div in soup.findAll('div', attrs={'class':['lead-story', 'section']}): for div in soup.findAll('div', attrs={'class':['lead-story', 'section', 'today-paper']}):
for a in div.findAll('a', attrs={'href':lambda x: x and x.startswith('https://indianexpress.com/article/')}): for a in div.findAll('a', attrs={'href':lambda x: x and x.startswith('https://indianexpress.com/article/')}):
if not a.find('img'): if not a.find('img'):
url = a['href'] url = a['href']