calibre/recipes/ifzm.recipe
2025-01-24 11:14:25 +01:00

80 lines
2.8 KiB
Python

#!/usr/bin/env python
import json
from calibre.web.feeds.news import BasicNewsRecipe
def absurl(url):
if url.startswith('/'):
return 'https://www.infzm.com' + url
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):
title = '南方周末'
__author__ = 'unkn0wn'
description = 'Southern Weekly (infzm.com), founded in 1984, is a Chinese weekly newspaper based in Guangzhou. Download Weekly.'
language = 'zh'
encoding = 'utf-8'
no_stylesheets = True
remove_javascript = True
ignore_duplicate_articles = {'title', 'url'}
remove_empty_feeds = True
use_embedded_content = False
remove_attributes = ['style', 'height', 'width']
masthead_url = 'http://ssimg.kkod.cn/web/02/14227.gif'
remove_tags = [dict(name=['video', 'svg', 'button'])]
articles_are_obfuscated = True
def get_obfuscated_article(self, url):
br = self.get_browser()
link = url
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=')
# if article is paywalled, add code to figure out machine_id
raw = br.open(res_link).read()
html = json_to_html(raw, link)
return ({'data': html, 'url': link})
extra_css = '''
img {display:block; margin:0 auto;}
.cm_pic_caption, .cm_pic_author { font-size:small; text-align:center; }
'''
def parse_index(self):
index = 'https://www.infzm.com/'
sections = [
'contents'
]
feeds = []
soup = self.index_to_soup(index)
for sec in sections:
section = sec.capitalize()
self.log(section)
articles = []
for a in soup.findAll('a', attrs={'href':lambda x: x and x.startswith('/' + sec + '/')}):
url = absurl(a['href'].split('?')[0])
if url in {index + sec + '/', index + sec}:
continue
title = self.tag_to_string(a)
self.log('\t', title, '\n\t\t', url)
articles.append({'title': title, 'url': url})
if articles:
feeds.append((section, articles))
return feeds
def populate_article_metadata(self, article, soup, first):
if soup.find(attrs={'class':'intro'}):
article.summary = article.text_summary = self.tag_to_string(soup.find(attrs={'class':'intro'}))