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

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

Browse Source
This commit is contained in:
Kovid Goyal 2023-07-18 07:22:51 +05:30
commit 1dda886dc4
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 83 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

51
recipes/bloomberg-business-week.recipe
View File

@ -108,7 +108,7 @@ class Bloomberg(BasicNewsRecipe):
if 'ledeImageUrl' in data:
if data['ledeImageUrl'] is not None:
lede = '<p><img src="{}">'.format(data['ledeImageUrl'])
lede = '<p id="img"><img src="{}">'.format(data['ledeImageUrl'])
if 'ledeDescription' in data:
if data['ledeDescription'] is not None:
@ -125,22 +125,49 @@ class Bloomberg(BasicNewsRecipe):
else:
body = ''
body_data = data['body']['content']
for objects in body_data:
if objects['type'] == 'media':
if objects['subType'] == 'photo':
if objects['type'] == 'media' and objects['subType'] == 'photo':
body += '<p id="img"><img src="{}">'.format(objects['data']['photo']['src'])
body += '<span id="cap">' + objects['data']['photo']['caption'] + '</span></p>'
if objects['type'] == 'paragraph' or 'heading':
body += '<span>' + objects['data']['photo']['caption'] + '</span></p>'
if objects['type'] == 'media' and objects['subType'] == 'chart':
if objects['data'] and objects['data']['chart']:
body += '<p id="img"><img src="{}">'.format(objects['data']['chart']['fallback'])
if objects['type'] == 'paragraph' or 'heading': # lists are missed :(
body += '<p>'
if 'content' not in objects:
continue
for content in objects['content']:
if 'value' in content:
body += content['value']
elif 'content' in content:
for val_cont in content['content']:
if 'value' in val_cont:
body += val_cont['value']
for item in objects['content']:
if item['type'] == 'text' and item['value']:
body += item['value']
elif item['type'] == 'link' and item['data']:
if 'href' not in item['data']:
continue
if item['content'] and item['content'][0] and item['content'][0]['value']:
body += '<a href="' + item['data']['href'] + '">' + item['content'][0]['value'] + '</a>'
elif item['type'] == 'entity':
if item['content'] and item['content'][0] and item['content'][0]['value']:
if item['subType'] == 'person' or 'security':
body += item['content'][0]['value']
elif item['subType'] == 'story':
if item['data'] and item['data']['link'] and item['data']['link']['destination'] and item['data']['link']['destination']['web']:
body += '<a href="' + item['data']['link']['destination']['web'] + '">' + item.content[0].value + '</a>'
if objects['type'] == 'quote':
if 'content' not in objects:
continue
for item in objects['content']:
if item['type'] == 'paragraph' and item['content'] and item['content'][0]:
if 'value' not in item['content'][0]:
continue
body += '<blockquote id="subhead">' + item['content'][0]['value'] + '</blockquote>'
html = '<html><body>' + cat + title + subhead + auth + lede + caption + '<div>' + body
return html

58
recipes/bloomberg.recipe
View File

@ -61,7 +61,7 @@ class Bloomberg(BasicNewsRecipe):
'https://news.google.com/rss/search?q=when:27h+allinurl:bloomberg.com%2Fnews%2Fnewsletters%2F&hl=en-US&gl=US&ceid=US:en'),
('News',
'https://news.google.com/rss/search?q=when:27h+allinurl:bloomberg.com%2Fnews%2Farticles%2F&hl=en-US&gl=US&ceid=US:en'),
('Others', 'https://news.google.com/rss/search?q=when:27h+allinurl:bloomberg.com%2F&hl=en-US&gl=US&ceid=US:en')
('Others', 'https://news.google.com/rss/search?q=when:27h+allinurl:bloomberg.com&hl=en-US&gl=US&ceid=US:en')
]
def preprocess_raw_html(self, raw, *a):
@ -71,13 +71,12 @@ class Bloomberg(BasicNewsRecipe):
m = root.xpath('//script[@data-component-props="FeatureBody"]')
if not m:
m2 = root.xpath('//script[@id="__NEXT_DATA__"]')
if not m2:
return raw
if m:
data = json.loads(m[0].text)
data = data['story']
else:
elif m2:
data = json.loads(m2[0].text)
data = data['props']['pageProps']['story']
@ -103,7 +102,7 @@ class Bloomberg(BasicNewsRecipe):
if 'ledeImageUrl' in data:
if data['ledeImageUrl'] is not None:
lede = '<p><img src="{}">'.format(data['ledeImageUrl'])
lede = '<p id="img"><img src="{}">'.format(data['ledeImageUrl'])
if 'ledeDescription' in data:
if data['ledeDescription'] is not None:
@ -117,25 +116,52 @@ class Bloomberg(BasicNewsRecipe):
if m:
body = data['body']
else:
elif m2:
body = ''
body_data = data['body']['content']
for objects in body_data:
if objects['type'] == 'media':
if objects['subType'] == 'photo':
if objects['type'] == 'media' and objects['subType'] == 'photo':
body += '<p id="img"><img src="{}">'.format(objects['data']['photo']['src'])
body += '<span id="cap">' + objects['data']['photo']['caption'] + '</span></p>'
body += '<span>' + objects['data']['photo']['caption'] + '</span></p>'
if objects['type'] == 'media' and objects['subType'] == 'chart':
if objects['data'] and objects['data']['chart']:
body += '<p id="img"><img src="{}">'.format(objects['data']['chart']['fallback'])
if objects['type'] == 'paragraph' or 'heading': # lists are missed :(
body += '<p>'
if 'content' not in objects:
continue
for content in objects['content']:
if 'value' in content:
body += content['value']
elif 'content' in content:
for val_cont in content['content']:
if 'value' in val_cont:
body += val_cont['value']
for item in objects['content']:
if item['type'] == 'text' and item['value']:
body += item['value']
elif item['type'] == 'link' and item['data']:
if 'href' not in item['data']:
continue
if item['content'] and item['content'][0] and item['content'][0]['value']:
body += '<a href="' + item['data']['href'] + '">' + item['content'][0]['value'] + '</a>'
elif item['type'] == 'entity':
if item['content'] and item['content'][0] and item['content'][0]['value']:
if item['subType'] == 'person' or 'security':
body += item['content'][0]['value']
elif item['subType'] == 'story':
if item['data'] and item['data']['link'] and item['data']['link']['destination'] and item['data']['link']['destination']['web']:
body += '<a href="' + item['data']['link']['destination']['web'] + '">' + item.content[0].value + '</a>'
if objects['type'] == 'quote':
if 'content' not in objects:
continue
for item in objects['content']:
if item['type'] == 'paragraph' and item['content'] and item['content'][0]:
if 'value' not in item['content'][0]:
continue
body += '<blockquote id="subhead">' + item['content'][0]['value'] + '</blockquote>'
html = '<html><body>' + cat + title + subhead + auth + lede + caption + '<div>' + body
return html