Debian Codegraph @

recipes/ancient_egypt.recipe

raw
1 #!/usr/bin/env python
2 # vim:fileencoding=utf-8
3 """
4 https://ancientegyptmagazine.com
5 """
6
7 from calibre import browser
8 from calibre.web.feeds.news import BasicNewsRecipe
9
10
11 class ancientegypt(BasicNewsRecipe):
12 title = 'The Past: Ancient Egypt Magazine'
13 language = 'en'
14 __author__ = 'unkn0wn'
15 description = (
16 "Ancient Egypt is the world's leading Egyptology magazine, exploring the history, people and culture of the Nile Valley. "
17 'Now in a larger format with a fresh new design, AE brings you the latest news and discoveries, and feature articles covering '
18 'more than 5000 years of Egyptian history. Published bimonthly.'
19 )
20 no_stylesheets = True
21 use_embedded_content = False
22 remove_attributes = ['style', 'height', 'width']
23 ignore_duplicate_articles = {'url'}
24 resolve_internal_links = True
25 masthead_url = 'https://ancientegyptmagazine.com/media/website/ae-logo-2.png'
26 simultaneous_downloads = 1
27
28 extra_css = '''
29 [class^="meta"], [class~="__author__text"], [class~="__date"] { font-size:small; }
30 .post-subtitle { font-style: italic; color:#202020; }
31 .wp-block-image { font-size:small; text-align:center; }
32 '''
33
34 keep_only_tags = [
35 dict(
36 attrs={
37 'class': lambda x: (
38 x
39 and any(
40 tag in x
41 for tag in [
42 '__image',
43 '__header',
44 '__background',
45 '__body_area',
46 '__author__text',
47 '__date',
48 ]
49 )
50 )
51 }
52 )
53 ]
54
55 remove_tags = [
56 dict(attrs={'class': 'ad-break'}),
57 dict(attrs={'class': lambda x: x and any(cls in x.split() for cls in ['avatar', 'what-mag-row'])}),
58 dict(attrs={'class': lambda x: x and '--share' in x}),
59 ]
60
61 def preprocess_html(self, soup):
62 for img in soup.findAll('img', attrs={'src': True}):
63 if '?w=' in img['src']:
64 res = '?w=600'
65 w = self.recipe_specific_options.get('res')
66 if w and isinstance(w, str):
67 res = '?w=' + w
68 img['src'] = img['src'].split('?')[0] + res
69 img.attrs = {'src': img['src']}
70 exp = soup.find(attrs={'class': lambda x: x and 'post-subtitle' in x.split()})
71 if exp:
72 exp.name = 'p'
73 return soup
74
75 recipe_specific_options = {
76 'issue': {
77 'short': 'Enter the Issue Number you want to download ',
78 'long': 'For example, 136',
79 },
80 'res': {
81 'short': 'For hi-res images, select a resolution from the\nfollowing options: 800, 1000, 1200 or 1500',
82 'long': 'This is useful for non e-ink devices, and for a lower file size\nthan the default, use 400 or 300.',
83 'default': '600',
84 },
85 }
86
87 def parse_index(self):
88 soup = self.index_to_soup('https://the-past.com/category/magazines/ae/')
89 art = soup.find('article', attrs={'class': lambda x: x and 'tag-magazines' in x.split()})
90 url = art.h2.a['href']
91
92 d = self.recipe_specific_options.get('issue')
93 if d and isinstance(d, str):
94 url = 'https://the-past.com/magazines/ae/ancient-egypt-magazine-' + d + '/'
95
96 issue = self.index_to_soup(url)
97 ti = issue.find('h1', attrs={'class': lambda x: x and 'post-title' in x.split()})
98 if ti:
99 self.title = self.tag_to_string(ti).strip()
100 dt = soup.find(attrs={'class': lambda x: x and '__date' in x})
101 if dt:
102 self.timefmt = ' [' + self.tag_to_string(dt).strip() + ']'
103 edit = issue.find('h2', attrs={'id': 'from-the-editor'})
104 if edit and edit.findParent('div'):
105 self.description = self.tag_to_string(edit.findParent('div'))
106 cov = issue.find('figure', attrs={'class': lambda x: x and 'wp-block-image' in x.split()})
107 if cov:
108 self.cover_url = cov.img['src'].split('?')[0] + '?w=600'
109 div = issue.find('div', attrs={'class': lambda x: x and 'entry-content' in x.split()})
110
111 feeds = []
112
113 h2 = div.findAll('h2', attrs={'class': lambda x: x and 'wp-block-heading' in x.split()})
114 lt = div.findAll(attrs={'class': 'display-posts-listing'})
115 for x, y in zip(h2, lt):
116 section = self.tag_to_string(x).strip()
117 self.log(section)
118 articles = []
119 for a in y.findAll('a', href=True, attrs={'class': 'title'}):
120 url = a['href']
121 title = self.tag_to_string(a).strip()
122 desc = ''
123 exp = a.findNext(attrs={'class': 'excerpt'})
124 if exp:
125 desc = self.tag_to_string(exp).strip()
126 self.log('\t', title, '\n\t', desc, '\n\t\t', url)
127 articles.append({'title': title, 'description': desc, 'url': url})
128 if articles:
129 feeds.append((section, articles))
130 return feeds
131
132 def get_browser(self, *args, **kwargs):
133 return self
134
135 def clone_browser(self, *args, **kwargs):
136 return self.get_browser()
137
138 def open_novisit(self, *args, **kwargs):
139 br = browser()
140 return br.open_novisit(*args, **kwargs)
141
142 open = open_novisit