|
|
@@ -1,39 +1,61 @@
|
|
|
1
|
+## Piratebay (Videos, Music, Files)
|
|
|
2
|
+#
|
|
|
3
|
+# @website https://thepiratebay.se
|
|
|
4
|
+# @provide-api no (nothing found)
|
|
|
5
|
+#
|
|
|
6
|
+# @using-api no
|
|
|
7
|
+# @results HTML (using search portal)
|
|
|
8
|
+# @stable yes (HTML can change)
|
|
|
9
|
+# @parse url, title, content, seed, leech, magnetlink
|
|
|
10
|
+
|
|
1
|
11
|
from urlparse import urljoin
|
|
2
|
12
|
from cgi import escape
|
|
3
|
13
|
from urllib import quote
|
|
4
|
14
|
from lxml import html
|
|
5
|
15
|
from operator import itemgetter
|
|
6
|
16
|
|
|
7
|
|
-categories = ['videos', 'music']
|
|
|
17
|
+# engine dependent config
|
|
|
18
|
+categories = ['videos', 'music', 'files']
|
|
|
19
|
+paging = True
|
|
8
|
20
|
|
|
|
21
|
+# search-url
|
|
9
|
22
|
url = 'https://thepiratebay.se/'
|
|
10
|
23
|
search_url = url + 'search/{search_term}/{pageno}/99/{search_type}'
|
|
11
|
|
-search_types = {'videos': '200',
|
|
|
24
|
+
|
|
|
25
|
+# piratebay specific type-definitions
|
|
|
26
|
+search_types = {'files': '0',
|
|
12
|
27
|
'music': '100',
|
|
13
|
|
- 'files': '0'}
|
|
|
28
|
+ 'videos': '200'}
|
|
14
|
29
|
|
|
|
30
|
+# specific xpath variables
|
|
15
|
31
|
magnet_xpath = './/a[@title="Download this torrent using magnet"]'
|
|
16
|
32
|
content_xpath = './/font[@class="detDesc"]//text()'
|
|
17
|
33
|
|
|
18
|
|
-paging = True
|
|
19
|
|
-
|
|
20
|
34
|
|
|
|
35
|
+# do search-request
|
|
21
|
36
|
def request(query, params):
|
|
22
|
|
- search_type = search_types.get(params['category'], '200')
|
|
|
37
|
+ search_type = search_types.get(params['category'], '0')
|
|
|
38
|
+
|
|
23
|
39
|
params['url'] = search_url.format(search_term=quote(query),
|
|
24
|
40
|
search_type=search_type,
|
|
25
|
41
|
pageno=params['pageno'] - 1)
|
|
|
42
|
+
|
|
26
|
43
|
return params
|
|
27
|
44
|
|
|
28
|
45
|
|
|
|
46
|
+# get response from search-request
|
|
29
|
47
|
def response(resp):
|
|
30
|
48
|
results = []
|
|
|
49
|
+
|
|
31
|
50
|
dom = html.fromstring(resp.text)
|
|
|
51
|
+
|
|
32
|
52
|
search_res = dom.xpath('//table[@id="searchResult"]//tr')
|
|
33
|
53
|
|
|
|
54
|
+ # return empty array if nothing is found
|
|
34
|
55
|
if not search_res:
|
|
35
|
|
- return results
|
|
|
56
|
+ return []
|
|
36
|
57
|
|
|
|
58
|
+ # parse results
|
|
37
|
59
|
for result in search_res[1:]:
|
|
38
|
60
|
link = result.xpath('.//div[@class="detName"]//a')[0]
|
|
39
|
61
|
href = urljoin(url, link.attrib.get('href'))
|
|
|
@@ -41,17 +63,21 @@ def response(resp):
|
|
41
|
63
|
content = escape(' '.join(result.xpath(content_xpath)))
|
|
42
|
64
|
seed, leech = result.xpath('.//td[@align="right"]/text()')[:2]
|
|
43
|
65
|
|
|
|
66
|
+ # convert seed to int if possible
|
|
44
|
67
|
if seed.isdigit():
|
|
45
|
68
|
seed = int(seed)
|
|
46
|
69
|
else:
|
|
47
|
70
|
seed = 0
|
|
48
|
71
|
|
|
|
72
|
+ # convert leech to int if possible
|
|
49
|
73
|
if leech.isdigit():
|
|
50
|
74
|
leech = int(leech)
|
|
51
|
75
|
else:
|
|
52
|
76
|
leech = 0
|
|
53
|
77
|
|
|
54
|
78
|
magnetlink = result.xpath(magnet_xpath)[0]
|
|
|
79
|
+
|
|
|
80
|
+ # append result
|
|
55
|
81
|
results.append({'url': href,
|
|
56
|
82
|
'title': title,
|
|
57
|
83
|
'content': content,
|
|
|
@@ -60,4 +86,5 @@ def response(resp):
|
|
60
|
86
|
'magnetlink': magnetlink.attrib['href'],
|
|
61
|
87
|
'template': 'torrent.html'})
|
|
62
|
88
|
|
|
|
89
|
+ # return results sorted by seeder
|
|
63
|
90
|
return sorted(results, key=itemgetter('seed'), reverse=True)
|
Thomas Pointhuber
10 年前