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 18:28:05 +05:30
commit 7792a0c3be
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 35 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
recipes/nytfeeds.recipe
View File

@ -34,16 +34,25 @@ def parse_img_grid(g):
yield '</div>'
def parse_cnt(cnt):
txt = ''
if cnt['__typename'] == 'TextInline':
if cnt.get('formats'):
for fmt in cnt.get('formats', {}):
if fmt['__typename'] == 'ItalicFormat':
txt += '<i>'
if fmt['__typename'] == 'LinkFormat':
hrf = fmt['url']
yield '<a href="{}">'.format(hrf) + cnt['text'] + '</a>'
else:
yield cnt['text']
else:
yield cnt['text']
txt += '<a href="{}">'.format(fmt['url'])
txt += cnt['text']
elif cnt['__typename'] == 'LineBreakInline':
txt += '<br/>'
if '<i>' in txt and '<a href' in txt:
yield txt + '</a></i>'
elif '<i>' in txt:
yield txt + '</i>'
elif '<a href' in txt:
yield txt + '</a>'
else:
yield txt
def parse_byline(byl):
for b in byl.get('bylines', {}):
@ -69,8 +78,8 @@ def header_parse(h):
if h['ledeMedia'].get('__typename', '') == 'ImageBlock':
yield ''.join(parse_image(h['ledeMedia']['media']))
if h.get('byline'):
yield '<br><div class="byl">'
yield '\t'.join(parse_byline(h['byline']))
yield '<div class="byl"><br/>'
yield '\t' + '\t'.join(parse_byline(h['byline']))
if h.get('timestampBlock'):
yield '\t<div>' + iso_date(h['timestampBlock']['timestamp']) + '</div>'
yield '</div>'
@ -81,33 +90,35 @@ def article_parse(data):
if x.get('__typename', '') in {'HeaderBasicBlock', 'HeaderFullBleedVerticalBlock', 'HeaderFullBleedHorizontalBlock'}:
yield '\n'.join(header_parse(x))
elif x.get('__typename', '') == 'ParagraphBlock':
yield '<p>'
p_txt = ''
for para in x['content']:
yield '\t'.join(parse_cnt(para))
yield '</p>'
p_txt += ''.join(parse_cnt(para))
if p_txt.strip():
yield '<p>' + p_txt + '</p>'
elif x.get('__typename', '') in {'Heading2Block', 'Heading3Block'}:
yield '<h4>'
h4_txt = ''
for h2 in x['content']:
yield '\t'.join(parse_cnt(h2))
yield '</h4>'
h4_txt += ''.join(parse_cnt(h2))
if h4_txt.strip():
yield '<h4>' + h4_txt + '</h4>'
elif x.get('__typename', '') == 'Heading1Block':
yield '<h1>'
h1_txt = ''
for h1 in x['content']:
yield '\t'.join(parse_cnt(h1))
yield '</h1>'
h1_txt += ''.join(parse_cnt(h1))
if h1_txt.strip():
yield '<h1>' + h1_txt + '</h1>'
elif x.get('__typename', '') == 'BylineBlock':
yield '<br><div class="byl">'
yield '\t'.join(parse_byline(x))
yield '</div>'
yield '<div class="byl">\n<br/>\t' + '\t'.join(parse_byline(x)) + '</div>'
elif x.get('__typename', '') == 'ImageBlock':
yield ''.join(parse_image(x['media']))
elif x.get('__typename', '') == 'GridBlock':
yield ''.join(parse_img_grid(x))
elif x.get('content'):
yield '<p><i>'
o_txt = ''
for i in x['content']:
yield '\t'.join(parse_cnt(i))
yield '</i></p>'
o_txt += ''.join(parse_cnt(i))
if o_txt.strip():
yield '<p><i>' + o_txt + '</i></p>'
yield "</body></html>"
@ -207,5 +218,5 @@ class nytFeeds(BasicNewsRecipe):
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
img['src'] = img['src'].rsplit('-article', 1)[0] + res
return soup