searx

commit: 15a4c10c990bb8d99e29a30d8d52638d3e3d8fe8
parent 41aca9a068cbaf4e630461b844a152e7f2444548
Author: Cqoicebordel <Cqoicebordel@users.noreply.github.com>
Date:   Tue,  9 Dec 2014 19:19:39 +0100

First pass at Kickass Engine

Parse and return results correctly. Pages numbers taken care of.

Not done, and maybe to do :
- 'content' : I don't know what it could be. Maybe votes ?
- 'categories' : the results are not filtered by categories, because I don't see how to do it properly : there are too much categories on Kickass. Is 'video' only movies, or also tv show or porn ? So for now, the category is 'all'.
- Favicon/icon : may be a good idea.
Diffstat:
A
searx/engines/kickass.py
83
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

1 file changed, 83 insertions(+), 0 deletions(-)
diff --git a/searx/engines/kickass.py b/searx/engines/kickass.py
@@ -0,0 +1,83 @@
+## Kickass Torrent (Videos, Music, Files)
+# 
+# @website     https://kickass.so
+# @provide-api no (nothing found)
+# 
+# @using-api   no
+# @results     HTML (using search portal)
+# @stable      yes (HTML can change)
+# @parse       url, title, content, seed, leech, magnetlink
+
+from urlparse import urljoin
+from cgi import escape
+from urllib import quote
+from lxml import html
+from operator import itemgetter
+
+# engine dependent config
+categories = ['videos', 'music', 'files']
+paging = True
+
+# search-url
+url = 'https://kickass.so/'
+search_url = url + 'search/{search_term}/{pageno}/'
+
+# specific xpath variables
+magnet_xpath = './/a[@title="Torrent magnet link"]'
+#content_xpath = './/font[@class="detDesc"]//text()'
+
+
+# do search-request
+def request(query, params):
+    params['url'] = search_url.format(search_term=quote(query),
+                                      pageno=params['pageno'])
+
+    return params
+
+
+# get response from search-request
+def response(resp):
+    results = []
+
+    dom = html.fromstring(resp.text)
+
+    search_res = dom.xpath('//table[@class="data"]//tr')
+
+    # return empty array if nothing is found
+    if not search_res:
+        return []
+
+    # parse results
+    for result in search_res[1:]:
+        link = result.xpath('.//a[@class="cellMainLink"]')[0]
+        href = urljoin(url, link.attrib['href'])
+        title = ' '.join(link.xpath('.//text()'))
+        #content = escape(' '.join(result.xpath(content_xpath)))
+        seed = result.xpath('.//td[contains(@class, "green")]/text()')[0]
+        leech = result.xpath('.//td[contains(@class, "red")]/text()')[0]
+
+        # convert seed to int if possible
+        if seed.isdigit():
+            seed = int(seed)
+        else:
+            seed = 0
+
+        # convert leech to int if possible
+        if leech.isdigit():
+            leech = int(leech)
+        else:
+            leech = 0
+
+        magnetlink = result.xpath(magnet_xpath)[0].attrib['href']
+
+        # append result
+        results.append({'url': href,
+                        'title': title,
+                        'content': '',
+                        'seed': seed,
+                        'leech': leech,
+                        'magnetlink': magnetlink,
+                        'template': 'torrent.html'})
+
+    # return results sorted by seeder
+    return sorted(results, key=itemgetter('seed'), reverse=True)