Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-11-04 03:27:00 -05:00
Code Issues Packages Projects Releases Wiki Activity

Update bloomberg-business-week.recipe

Browse Source
This commit is contained in:
unkn0w7n 2023-07-16 23:59:05 +05:30
parent 3e5fe65fe5
commit 7d37665a83
1 changed files with 46 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
recipes/bloomberg-business-week.recipe
View File

@ -1,5 +1,6 @@
from calibre.web.feeds.news import BasicNewsRecipe, classes
from calibre import browser
from html5_parser import parse
import json
import re
@ -19,7 +20,7 @@ class Bloomberg(BasicNewsRecipe):
#auth {font-size:small; font-weight:bold;}
#time, .chart {font-size:small;}
#subhead {font-style:italic; color:#404040;}
.news-figure-caption-text, #cap {font-size:small; text-align:center;}
.news-figure-caption-text, #cap, #img {font-size:small; text-align:center;}
.news-figure-credit {font-size:small; text-align:center; color:#202020;}
'''
@ -70,17 +71,22 @@ class Bloomberg(BasicNewsRecipe):
return feeds
def preprocess_raw_html(self, raw, *a):
m = re.search('data-component-props="ArticleBody">', raw)
root = parse(raw)
m = root.xpath('//script[@data-component-props="ArticleBody"]')
if not m:
m = re.search('data-component-props="FeatureBody">', raw)
m = root.xpath('//script[@data-component-props="FeatureBody"]')
if not m:
m2 = root.xpath('//script[@id="__NEXT_DATA__"]')
if not m2:
return raw
raw = raw[m.start():]
raw = raw.split('>', 1)[1]
data = json.JSONDecoder().raw_decode(raw)[0]
if m:
data = json.loads(m[0].text)
data = data['story']
else:
data = json.loads(m2[0].text)
data = data['props']['pageProps']['story']
title = '<h1>' + data['headline'] + '</h1>'
cat = subhead = lede = auth = caption = ''
@ -105,10 +111,38 @@ class Bloomberg(BasicNewsRecipe):
if data['ledeImageUrl'] is not None:
lede = '<p><img src="{}">'.format(data['ledeImageUrl'])
if 'ledeDescription' in data:
if data['ledeDescription'] is not None:
caption = '<span id="cap">' + data['ledeDescription'] + '</span>'
else:
if 'lede' in data:
if data['lede'] is not None:
if 'alt' in data['lede']:
if data['lede']['alt'] is not None:
caption = '<span id="cap">' + data['lede']['alt'] + '</span>'
if m:
body = data['body']
else:
body = ''
body_data = data['body']['content']
for objects in body_data:
if objects['type'] == 'media':
if 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 += '<p>'
if not 'content' 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']
html = '<html><body>' + cat + title + subhead + auth + lede + caption + '<div>' + body
return html