|
@@ -0,0 +1,85 @@
|
|
1
|
+"""
|
|
2
|
+ Acgsou (Japanese Animation/Music/Comics Bittorrent tracker)
|
|
3
|
+
|
|
4
|
+ @website https://www.acgsou.com/
|
|
5
|
+ @provide-api no
|
|
6
|
+ @using-api no
|
|
7
|
+ @results HTML
|
|
8
|
+ @stable no (HTML can change)
|
|
9
|
+ @parse url, title, content, seed, leech, torrentfile
|
|
10
|
+"""
|
|
11
|
+
|
|
12
|
+from lxml import html
|
|
13
|
+from searx.engines.xpath import extract_text
|
|
14
|
+from searx.url_utils import urlencode
|
|
15
|
+from searx.utils import get_torrent_size, int_or_zero
|
|
16
|
+
|
|
17
|
+# engine dependent config
|
|
18
|
+categories = ['files', 'images', 'videos', 'music']
|
|
19
|
+paging = True
|
|
20
|
+
|
|
21
|
+# search-url
|
|
22
|
+base_url = 'https://www.acgsou.com/'
|
|
23
|
+search_url = base_url + 'search.php?{query}&page={offset}'
|
|
24
|
+# xpath queries
|
|
25
|
+xpath_results = '//table[contains(@class, "list_style table_fixed")]//tr[not(th)]'
|
|
26
|
+xpath_category = './/td[2]/a[1]'
|
|
27
|
+xpath_title = './/td[3]/a[last()]'
|
|
28
|
+xpath_torrent_links = './/td[3]/a'
|
|
29
|
+xpath_filesize = './/td[4]/text()'
|
|
30
|
+
|
|
31
|
+# do search-request
|
|
32
|
+def request(query, params):
|
|
33
|
+ query = urlencode({'keyword': query})
|
|
34
|
+ params['url'] = search_url.format(query=query, offset=params['pageno'])
|
|
35
|
+ return params
|
|
36
|
+
|
|
37
|
+
|
|
38
|
+# get response from search-request
|
|
39
|
+def response(resp):
|
|
40
|
+ results = []
|
|
41
|
+ dom = html.fromstring(resp.text)
|
|
42
|
+ print(resp.text)
|
|
43
|
+ for result in dom.xpath(xpath_results):
|
|
44
|
+ # defaults
|
|
45
|
+ filesize = 0
|
|
46
|
+ magnet_link = "magnet:?xt=urn:btih:{}&tr=http://tracker.acgsou.com:2710/announce"
|
|
47
|
+ torrent_link = ""
|
|
48
|
+
|
|
49
|
+ # category in which our torrent belongs
|
|
50
|
+ try:
|
|
51
|
+ category = extract_text(result.xpath(xpath_category)[0])
|
|
52
|
+ except:
|
|
53
|
+ pass
|
|
54
|
+
|
|
55
|
+ # torrent title
|
|
56
|
+ page_a = result.xpath(xpath_title)[0]
|
|
57
|
+ title = extract_text(page_a)
|
|
58
|
+
|
|
59
|
+ # link to the page
|
|
60
|
+ href = base_url + page_a.attrib.get('href')
|
|
61
|
+
|
|
62
|
+ #magnet link
|
|
63
|
+ magnet_link = magnet_link.format(page_a.attrib.get('href')[5:-5])
|
|
64
|
+
|
|
65
|
+ # let's try to calculate the torrent size
|
|
66
|
+ try:
|
|
67
|
+ filesize_info = result.xpath(xpath_filesize)[0]
|
|
68
|
+ filesize = filesize_info[:-2]
|
|
69
|
+ filesize_multiplier = filesize_info[-2:]
|
|
70
|
+ filesize = get_torrent_size(filesize, filesize_multiplier)
|
|
71
|
+ except :
|
|
72
|
+ pass
|
|
73
|
+
|
|
74
|
+ # content string contains all information not included into template
|
|
75
|
+ content = 'Category: "{category}".'
|
|
76
|
+ content = content.format(category=category)
|
|
77
|
+
|
|
78
|
+ results.append({'url': href,
|
|
79
|
+ 'title': title,
|
|
80
|
+ 'content': content,
|
|
81
|
+ 'filesize': filesize,
|
|
82
|
+ 'magnetlink': magnet_link,
|
|
83
|
+ 'template': 'torrent.html'})
|
|
84
|
+
|
|
85
|
+ return results
|