| 1 |
#!/usr/bin/env python |
| 2 |
import json |
| 3 |
|
| 4 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 5 |
|
| 6 |
|
| 7 |
def absurl(url): |
| 8 |
if url.startswith('/'): |
| 9 |
return 'https://www.infzm.com' + url |
| 10 |
|
| 11 |
|
| 12 |
def json_to_html(raw, link): |
| 13 |
data = json.loads(raw) |
| 14 |
data = data['data']['content'] |
| 15 |
title = '<h1 title="{}">'.format(link) + data['subject'] + '</h1>' |
| 16 |
auth = '<p><b>' + data['author'] + '</b></p>' |
| 17 |
sub = '<p class="intro"><i>' + data['introtext'] + '</i></p>' |
| 18 |
body = data['fulltext'] |
| 19 |
return '<html><body><div>' + title + auth + sub + body + '</div></body></html>' |
| 20 |
|
| 21 |
|
| 22 |
class infzm(BasicNewsRecipe): |
| 23 |
title = '南方周末' |
| 24 |
__author__ = 'unkn0wn' |
| 25 |
description = 'Southern Weekly (infzm.com), founded in 1984, is a Chinese weekly newspaper based in Guangzhou. Download Weekly.' |
| 26 |
language = 'zh' |
| 27 |
encoding = 'utf-8' |
| 28 |
no_stylesheets = True |
| 29 |
remove_javascript = True |
| 30 |
ignore_duplicate_articles = {'title', 'url'} |
| 31 |
remove_empty_feeds = True |
| 32 |
use_embedded_content = False |
| 33 |
remove_attributes = ['style', 'height', 'width'] |
| 34 |
masthead_url = 'http://ssimg.kkod.cn/web/02/14227.gif' |
| 35 |
|
| 36 |
remove_tags = [dict(name=['video', 'svg', 'button'])] |
| 37 |
|
| 38 |
articles_are_obfuscated = True |
| 39 |
|
| 40 |
def get_obfuscated_article(self, url): |
| 41 |
br = self.get_browser() |
| 42 |
link = url |
| 43 |
res_link = ( |
| 44 |
link.replace('https://www.infzm.com', 'https://api.infzm.com/mobile') |
| 45 |
+ '?platform=wap&version=1.89.0&machine_id=35458aa29603f2b246636e5492122b50&user_id=&token=&member_type=' |
| 46 |
) |
| 47 |
# if article is paywalled, add code to figure out machine_id |
| 48 |
raw = br.open(res_link).read() |
| 49 |
html = json_to_html(raw, link) |
| 50 |
return {'data': html, 'url': link} |
| 51 |
|
| 52 |
extra_css = ''' |
| 53 |
img {display:block; margin:0 auto;} |
| 54 |
.cm_pic_caption, .cm_pic_author { font-size:small; text-align:center; } |
| 55 |
''' |
| 56 |
|
| 57 |
def parse_index(self): |
| 58 |
index = 'https://www.infzm.com/' |
| 59 |
sections = ['contents'] |
| 60 |
feeds = [] |
| 61 |
soup = self.index_to_soup(index) |
| 62 |
for sec in sections: |
| 63 |
section = sec.capitalize() |
| 64 |
self.log(section) |
| 65 |
articles = [] |
| 66 |
for a in soup.findAll('a', attrs={'href': lambda x: x and x.startswith('/' + sec + '/')}): |
| 67 |
url = absurl(a['href'].split('?')[0]) |
| 68 |
if url in {index + sec + '/', index + sec}: |
| 69 |
continue |
| 70 |
title = self.tag_to_string(a) |
| 71 |
self.log('\t', title, '\n\t\t', url) |
| 72 |
articles.append({'title': title, 'url': url}) |
| 73 |
if articles: |
| 74 |
feeds.append((section, articles)) |
| 75 |
return feeds |
| 76 |
|
| 77 |
def populate_article_metadata(self, article, soup, first): |
| 78 |
if soup.find(attrs={'class': 'intro'}): |
| 79 |
article.summary = article.text_summary = self.tag_to_string(soup.find(attrs={'class': 'intro'})) |