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

Merge branch 'master' of https://github.com/unkn0w7n/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2024-09-16 08:04:00 +05:30
commit 361718e4be
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 34 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
recipes/nytfeeds.recipe
View File

@ -15,11 +15,11 @@ def parse_image(i):
if i['__typename'] == 'Image':
yield '<div>'
yield '<img src="{}">'.format(i['crops'][0]['renditions'][0]['url'])
if 'caption' in i and i['caption']:
if i.get('caption'):
yield '<div class="cap">{}'.format(
i['caption'].get('text', '')
)
if 'credit' in i and i['credit']:
if i.get('credit'):
yield '<span class="cred"> ' + i['credit'] + '</span>'
yield '</div>'
yield '</div>'
@ -27,15 +27,15 @@ def parse_image(i):
def parse_img_grid(g):
for grd in g.get('gridMedia', {}):
yield ''.join(parse_image(grd))
if 'caption' in g and g['caption']:
if g.get('caption'):
yield '<div class="cap">{}'.format(g['caption'])
if 'credit' in g and g['credit']:
if g.get('credit'):
yield '<span class="cred"> ' + g['credit'] + '</span>'
yield '</div>'
def parse_cnt(cnt):
if cnt['__typename'] == 'TextInline':
if 'formats' in cnt and cnt['formats']:
if cnt.get('formats'):
for fmt in cnt.get('formats', {}):
if fmt['__typename'] == 'LinkFormat':
hrf = fmt['url']
@ -58,34 +58,43 @@ def iso_date(x):
def header_parse(h):
for ch in h['headline']['content']:
yield '<h1>' + ''.join(parse_cnt(ch)) + '</h1>'
if 'summary' in h and h['summary']:
if h.get('summary'):
for cs in h['summary']['content']:
yield '<p class="sub">' + ''.join(parse_cnt(cs)) + '</p>'
if 'ledeMedia' in h and h['ledeMedia']:
if h.get('ledeMedia'):
if h['ledeMedia'].get('__typename', '') == 'ImageBlock':
yield ''.join(parse_image(h['ledeMedia']['media']))
if 'byline' in h and h['byline']:
if h.get('byline'):
yield '<br><div class="byl">'
yield '\t'.join(parse_byline(h['byline']))
if 'timestampBlock' in h and h['timestampBlock']:
if h.get('timestampBlock'):
yield '\t<div>' + iso_date(h['timestampBlock']['timestamp']) + '</div>'
yield '</div>'
def article_parse(data):
yield "<html><body>"
for x in data:
if x.get('__typename', '') in {'HeaderBasicBlock', 'HeaderFullBleedVerticalBlock'}:
if x.get('__typename', '') in {'HeaderBasicBlock', 'HeaderFullBleedVerticalBlock', 'HeaderFullBleedHorizontalBlock'}:
yield '\n'.join(header_parse(x))
elif x.get('__typename', '') == 'ParagraphBlock':
yield '<p>'
for para in x['content']:
yield '\t'.join(parse_cnt(para))
yield '</p>'
elif x.get('__typename', '') == 'Heading2Block':
elif x.get('__typename', '') in {'Heading2Block', 'Heading3Block'}:
yield '<h4>'
for para in x['content']:
yield '\t'.join(parse_cnt(para))
for h2 in x['content']:
yield '\t'.join(parse_cnt(h2))
yield '</h4>'
elif x.get('__typename', '') == 'Heading1Block':
yield '<h1>'
for h1 in x['content']:
yield '\t'.join(parse_cnt(h1))
yield '</h1>'
elif x.get('__typename', '') == 'BylineBlock':
yield '<br><div class="byl">'
yield '\t'.join(parse_byline(x))
yield '</div>'
elif x.get('__typename', '') == 'ImageBlock':
yield ''.join(parse_image(x['media']))
elif x.get('__typename', '') == 'GridBlock':
@ -133,6 +142,10 @@ class nytFeeds(BasicNewsRecipe):
'short': 'Reverse the order of articles in each feed?',
'long': 'enter yes',
'default': 'no'
},
'res': {
'short': 'For hi-res images, select a resolution from the\nfollowing options: popup, jumbo, mobileMasterAt3x, superJumbo',
'long': 'This is useful for non e-ink devices, and for a lower file size\nthan the default(articleLarge), use articleInline.',
}
}
@ -182,3 +195,11 @@ class nytFeeds(BasicNewsRecipe):
def preprocess_raw_html(self, raw_html, url):
data = extract_json(raw_html)
return '\n'.join(article_parse(data))
def preprocess_html(self, soup):
w = self.recipe_specific_options.get('res')
if w and isinstance(w, str):
res = '-' + w + '.jpg'
for img in soup.findAll('img', attrs={'src':True}):
img['src'] = img['src'].rsplit('-', 1)[0] + res
return soup