|
@@ -0,0 +1,59 @@
|
|
1
|
+## Subtitleseeker (Video)
|
|
2
|
+#
|
|
3
|
+# @website http://www.subtitleseeker.com
|
|
4
|
+# @provide-api no
|
|
5
|
+#
|
|
6
|
+# @using-api no
|
|
7
|
+# @results HTML
|
|
8
|
+# @stable no (HTML can change)
|
|
9
|
+# @parse url, title, content
|
|
10
|
+
|
|
11
|
+from cgi import escape
|
|
12
|
+from urllib import quote_plus
|
|
13
|
+from lxml import html
|
|
14
|
+
|
|
15
|
+# engine dependent config
|
|
16
|
+categories = ['videos']
|
|
17
|
+paging = True
|
|
18
|
+
|
|
19
|
+# search-url
|
|
20
|
+url = 'http://www.subtitleseeker.com/'
|
|
21
|
+search_url = url+'search/TITLES/{query}&p={pageno}'
|
|
22
|
+
|
|
23
|
+# specific xpath variables
|
|
24
|
+results_xpath = '//div[@class="boxRows"]'
|
|
25
|
+
|
|
26
|
+
|
|
27
|
+# do search-request
|
|
28
|
+def request(query, params):
|
|
29
|
+ params['url'] = search_url.format(query=quote_plus(query),
|
|
30
|
+ pageno=params['pageno'])
|
|
31
|
+ return params
|
|
32
|
+
|
|
33
|
+
|
|
34
|
+# get response from search-request
|
|
35
|
+def response(resp):
|
|
36
|
+ results = []
|
|
37
|
+
|
|
38
|
+ dom = html.fromstring(resp.text)
|
|
39
|
+
|
|
40
|
+ # parse results
|
|
41
|
+ for result in dom.xpath(results_xpath):
|
|
42
|
+ link = result.xpath(".//a")[0]
|
|
43
|
+ href = link.attrib.get('href')
|
|
44
|
+ title = escape(link.xpath(".//text()")[0])
|
|
45
|
+
|
|
46
|
+ content = result.xpath('.//div[contains(@class,"red")]//text()')[0]
|
|
47
|
+ content = content + " - "
|
|
48
|
+ content = content + html.tostring(result.xpath('.//div[contains(@class,"grey-web")]')[0], method='text')
|
|
49
|
+
|
|
50
|
+ if result.xpath(".//span") != []:
|
|
51
|
+ content = content + " - (" + result.xpath(".//span//text()")[0].strip() + ")"
|
|
52
|
+
|
|
53
|
+ # append result
|
|
54
|
+ results.append({'url': href,
|
|
55
|
+ 'title': title,
|
|
56
|
+ 'content': escape(content)})
|
|
57
|
+
|
|
58
|
+ # return results
|
|
59
|
+ return results
|