Debian Codegraph @

recipes/am730.recipe

raw
1 # vim:fileencoding=UTF-8
2 from __future__ import print_function, unicode_literals
3
4 __license__ = 'GPL v3'
5 __copyright__ = '2013, Eddie Lau'
6 __Date__ = ''
7
8 '''
9 Change Log:
10 2013/09/28 -- update due to website redesign, add cover
11 2013/03/30 -- first version
12 '''
13
14 try:
15 from urllib.parse import unquote
16 except ImportError:
17 from urllib import unquote
18
19 from calibre.web.feeds.recipes import BasicNewsRecipe
20
21
22 class AM730(BasicNewsRecipe):
23 title = 'AM730'
24 __author__ = 'Eddie Lau'
25 publisher = 'AM730'
26 oldest_article = 1
27 max_articles_per_feed = 100
28 language = 'zh'
29 encoding = 'utf-8'
30 auto_cleanup = False
31 remove_javascript = True
32 use_embedded_content = False
33 no_stylesheets = True
34 description = 'http://www.am730.com.hk'
35 category = 'Chinese, News, Hong Kong'
36 masthead_url = 'https://upload.wikimedia.org/wikipedia/en/5/58/Am730_Hong_Kong_newspaper_logo.png'
37 extra_css = 'img {display: block; margin-left: auto; margin-right: auto; margin-top: 20px; margin-bottom: 20px; max-height:70%;} div[id=articleHeader] {font-size:200%; text-align:left; font-weight:bold;} li {font-size:50%; margin-left:auto; margin-right:auto;}' # noqa: E501
38 remove_tags = [
39 dict(name='div', attrs={'class': 'col-xs-12 col-sm-1 col-md-1 share-button'}),
40 dict(name='div', attrs={'class': 'logo-container print-logo'}),
41 dict(name='div', attrs={'id': 'galleria'}),
42 ]
43 keep_only_tags = [
44 dict(name='div', attrs={'class': 'col-xs-12 col-sm-12 col-md-12 news-detail-content-container'}),
45 # dict(name='div',attrs={'class':'columns-left'})]
46 ]
47 compress_news_images = True
48 compress_news_images_auto_size = 16
49 compress_news_images_max_size = 20 # kB
50 scale_news_images = (600, 800)
51 ignore_duplicate_articles = {'title', 'url'}
52
53 debug = False
54
55 def get_cover_url(self):
56 return self.masthead_url
57
58 def getAMSectionArticles(self, sectionName, url):
59 # print(sectionName)
60 soup = self.index_to_soup(url)
61 articles = []
62 for aTag in soup.findAll('a', attrs={'class': 'newsimglink'}):
63 href = aTag.get('href', False)
64 if not href.encode('utf-8').startswith(url.encode('utf-8')):
65 continue # not in same section
66
67 title = href.split('/')[-1].split('-')[0]
68 title = unquote(title.encode('ASCII')) # .decode('utf-8')
69 if self.debug:
70 print(title)
71 try:
72 if articles.index({'title': title, 'url': href}) >= 0:
73 # print('already added')
74 continue # already added
75 except Exception:
76 pass
77
78 articles.append({'title': title, 'url': href})
79
80 if len(articles) >= self.max_articles_per_feed:
81 break
82 if self.debug:
83 print(articles)
84 return sectionName, articles
85
86 def parse_index(self):
87 # hard code sections
88 Sections = [
89 ('新聞', 'https://www.am730.com.hk/news/%E6%96%B0%E8%81%9E'),
90 ('財經', 'https://www.am730.com.hk/news/%E8%B2%A1%E7%B6%93'),
91 ('健康', 'https://www.am730.com.hk/news/%E5%81%A5%E5%BA%B7'),
92 ('科技', 'https://www.am730.com.hk/news/%E7%A7%91%E6%8A%80'),
93 ('體育', 'https://www.am730.com.hk/news/%E9%AB%94%E8%82%B2'),
94 ('娛樂', 'https://www.am730.com.hk/news/%E5%A8%9B%E6%A8%82'),
95 ('旅遊.飲食', 'https://www.am730.com.hk/news/%E6%97%85%E9%81%8A.%E9%A3%B2%E9%A3%9F'),
96 ] # articles =[]
97 SectionsArticles = []
98 for title, url in Sections:
99 if self.debug:
100 print(title)
101 print(url)
102 SectionsArticles.append(self.getAMSectionArticles(title, url))
103 # feeds.append(articles[0]['url'])
104 return SectionsArticles