This commit is contained in:
unkn0w7n 2024-02-27 23:12:27 +05:30
parent f6185b2e55
commit aae88fa07e

View File

@ -34,6 +34,7 @@ class NewYorker(BasicNewsRecipe):
timefmt = ' [%b %d]' timefmt = ' [%b %d]'
encoding = 'utf-8' encoding = 'utf-8'
extra_css = ''' extra_css = '''
img { display:block; margin:0 auto; }
.byline { font-size:smaller; font-weight: bold;} .byline { font-size:smaller; font-weight: bold;}
h3 { margin-bottom: 6px; } h3 { margin-bottom: 6px; }
.caption { font-size: smaller; font-style: italic; font-weight: normal; } .caption { font-size: smaller; font-style: italic; font-weight: normal; }
@ -72,6 +73,21 @@ class NewYorker(BasicNewsRecipe):
self.log.warn('Kindle Output profile being used, reducing image quality to keep file size below amazon email threshold') self.log.warn('Kindle Output profile being used, reducing image quality to keep file size below amazon email threshold')
def preprocess_html(self, soup): def preprocess_html(self, soup):
w = '/w_320' # use '/w_640' for highres
for img in soup.findAll('img'):
if img.has_attr('srcset'):
for x in img['srcset'].split():
if w in x:
img['src'] = x
elif img.find_previous_sibling('source', attrs={'srcset':True}):
srcset = img.find_previous_sibling('source', attrs={'srcset':True})
for x in srcset['srcset'].split():
if w in x:
img['src'] = x
elif '/w_560' in x:
img['src'] = x
for src in soup.findAll('source'):
src.decompose()
for noscript in soup.findAll('noscript'): for noscript in soup.findAll('noscript'):
noscript.name = 'div' noscript.name = 'div'
return soup return soup