Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update SciAm

Browse Source
This commit is contained in:
unkn0w7n 2024-09-19 09:18:58 +05:30
parent 2637cbfb5d
commit 62bf0ab006
2 changed files with 8 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
recipes/nytfeeds.recipe
View File

@ -33,9 +33,11 @@ def parse_img_grid(g):
def parse_byline(byl): def parse_byline(byl):
for b in byl.get('bylines', {}): for b in byl.get('bylines', {}):
yield '<div>' + b['renderedRepresentation'] + '</div>' yield '<div>' + b['renderedRepresentation'] + '</div>'
yield '<div><b><i>'
for rl in byl.get('role', {}): for rl in byl.get('role', {}):
if ''.join(parse_cnt(rl)).strip(): if ''.join(parse_cnt(rl)).strip():
yield '<div><i>' + ''.join(parse_cnt(rl)) + '</i></div>' yield ''.join(parse_cnt(rl))
yield '</i></b></div>'
def iso_date(x): def iso_date(x):
dt = datetime.fromisoformat(x[:-1]) + timedelta(seconds=time.timezone) dt = datetime.fromisoformat(x[:-1]) + timedelta(seconds=time.timezone)
@ -47,7 +49,7 @@ def parse_header(h):
if h.get('headline'): if h.get('headline'):
yield ''.join(parse_types(h['headline'])) yield ''.join(parse_types(h['headline']))
if h.get('summary'): if h.get('summary'):
yield '<p class="sub">' + ''.join(parse_types(h['summary'])) + '</p>' yield '<p><i>' + ''.join(parse_types(h['summary'])) + '</i></p>'
if h.get('ledeMedia'): if h.get('ledeMedia'):
yield ''.join(parse_types(h['ledeMedia'])) yield ''.join(parse_types(h['ledeMedia']))
if h.get('byline'): if h.get('byline'):
@ -201,7 +203,6 @@ class nytFeeds(BasicNewsRecipe):
.byl, .time { font-size:small; color:#202020; } .byl, .time { font-size:small; color:#202020; }
.cap { font-size:small; text-align:center; } .cap { font-size:small; text-align:center; }
.cred { font-style:italic; font-size:small; } .cred { font-style:italic; font-size:small; }
.sub { font-style:italic; }
em, blockquote { color: #202020; } em, blockquote { color: #202020; }
.sc { font-variant: small-caps; } .sc { font-variant: small-caps; }
.lbl { font-size:small; color:#404040; } .lbl { font-size:small; color:#404040; }
@ -263,5 +264,6 @@ class nytFeeds(BasicNewsRecipe):
def get_article_url(self, article): def get_article_url(self, article):
url = BasicNewsRecipe.get_article_url(self, article) url = BasicNewsRecipe.get_article_url(self, article)
if not re.search(r'/video/|live|/athletic/', url): # you can remove '|/espanol/' from code below to include spanish articles.
if not re.search(r'/video/|live|/athletic/|/espanol/', url):
return url return url

4
recipes/scientific_american.recipe
View File

@ -36,7 +36,7 @@ class ScientificAmerican(BasicNewsRecipe):
keep_only_tags = [ keep_only_tags = [
prefixed_classes( prefixed_classes(
'article_hed- article_dek- article_authors- lead_image- article__content- bio-' 'article_hed- article_dek- article_authors- lead_image- article__body- bio-'
), ),
] ]
remove_tags = [ remove_tags = [
@ -45,7 +45,7 @@ class ScientificAmerican(BasicNewsRecipe):
def preprocess_html(self, soup): def preprocess_html(self, soup):
for fig in soup.findAll('figcaption'): for fig in soup.findAll('figcaption'):
for p in fig.findAll('p'): for p in fig.findAll(['p', 'div']):
p.name = 'span' p.name = 'span'
return soup return soup