mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
...
This commit is contained in:
parent
1aab6b2bed
commit
90967016cc
@ -1,6 +1,16 @@
|
|||||||
from calibre.web.feeds.news import BasicNewsRecipe
|
from calibre.web.feeds.news import BasicNewsRecipe
|
||||||
import json
|
import json
|
||||||
|
|
||||||
|
def json_to_html(raw, link):
|
||||||
|
data = json.loads(raw)
|
||||||
|
data = data['data']['content']
|
||||||
|
title = '<h1 title="{}">'.format(link) + data['subject'] + '</h1>'
|
||||||
|
auth = '<p><b>' + data['author'] + '</b></p>'
|
||||||
|
sub = '<p class="intro"><i>' + data['introtext'] + '</i></p>'
|
||||||
|
body = data['fulltext']
|
||||||
|
return '<html><body><div>' + title + auth + sub + body + '</div></body></html>'
|
||||||
|
|
||||||
|
|
||||||
class infzm(BasicNewsRecipe):
|
class infzm(BasicNewsRecipe):
|
||||||
title = '南方周末'
|
title = '南方周末'
|
||||||
__author__ = 'unkn0wn'
|
__author__ = 'unkn0wn'
|
||||||
@ -13,6 +23,7 @@ class infzm(BasicNewsRecipe):
|
|||||||
remove_empty_feeds = True
|
remove_empty_feeds = True
|
||||||
use_embedded_content = False
|
use_embedded_content = False
|
||||||
remove_attributes = ['style', 'height', 'width']
|
remove_attributes = ['style', 'height', 'width']
|
||||||
|
masthead_url = 'http://ssimg.kkod.cn/web/02/14227.gif'
|
||||||
|
|
||||||
articles_are_obfuscated = True
|
articles_are_obfuscated = True
|
||||||
|
|
||||||
@ -28,15 +39,9 @@ class infzm(BasicNewsRecipe):
|
|||||||
link = soup.find('a', href=True)['href'].split('?')[0]
|
link = soup.find('a', href=True)['href'].split('?')[0]
|
||||||
res_link = link.replace('https://www.infzm.com', 'https://api.infzm.com/mobile') \
|
res_link = link.replace('https://www.infzm.com', 'https://api.infzm.com/mobile') \
|
||||||
+ '?platform=wap&version=1.89.0&machine_id=35458aa29603f2b246636e5492122b50&user_id=&token=&member_type='
|
+ '?platform=wap&version=1.89.0&machine_id=35458aa29603f2b246636e5492122b50&user_id=&token=&member_type='
|
||||||
|
# if article is paywalled, add code to figure out machine_id
|
||||||
raw = br.open(res_link).read()
|
raw = br.open(res_link).read()
|
||||||
data = json.loads(raw)
|
html = json_to_html(raw, link)
|
||||||
data = data['data']
|
|
||||||
content = data['content']
|
|
||||||
title = '<h1 title="{}">'.format(link) + content['subject'] + '</h1>'
|
|
||||||
auth = '<p><b>' + content['author'] + '</b></p>'
|
|
||||||
sub = '<p class="intro"><i>' + content['introtext'] + '</i></p>'
|
|
||||||
body = content['fulltext']
|
|
||||||
html = '<html><body><div>' + title + auth + body + '</div></body></html>'
|
|
||||||
return ({ 'data': html, 'url': link })
|
return ({ 'data': html, 'url': link })
|
||||||
|
|
||||||
extra_css = '''
|
extra_css = '''
|
||||||
|
Loading…
x
Reference in New Issue
Block a user