summaryrefslogtreecommitdiff
path: root/searx
diff options
context:
space:
mode:
Diffstat (limited to 'searx')
-rw-r--r--searx/engines/btdigg.py16
-rw-r--r--searx/engines/digbt.py58
-rw-r--r--searx/engines/json_engine.py2
-rw-r--r--searx/engines/xpath.py2
-rw-r--r--searx/results.py2
-rw-r--r--searx/settings.yml20
-rw-r--r--searx/utils.py18
7 files changed, 100 insertions, 18 deletions
diff --git a/searx/engines/btdigg.py b/searx/engines/btdigg.py
index c2b22f003..ea6baf1c8 100644
--- a/searx/engines/btdigg.py
+++ b/searx/engines/btdigg.py
@@ -16,6 +16,7 @@ from urllib import quote
from lxml import html
from operator import itemgetter
from searx.engines.xpath import extract_text
+from searx.utils import get_torrent_size
# engine dependent config
categories = ['videos', 'music', 'files']
@@ -68,20 +69,7 @@ def response(resp):
leech = 0
# convert filesize to byte if possible
- try:
- filesize = float(filesize)
-
- # convert filesize to byte
- if filesize_multiplier == 'TB':
- filesize = int(filesize * 1024 * 1024 * 1024 * 1024)
- elif filesize_multiplier == 'GB':
- filesize = int(filesize * 1024 * 1024 * 1024)
- elif filesize_multiplier == 'MB':
- filesize = int(filesize * 1024 * 1024)
- elif filesize_multiplier == 'KB':
- filesize = int(filesize * 1024)
- except:
- filesize = None
+ filesize = get_torrent_size(filesize, filesize_multiplier)
# convert files to int if possible
if files.isdigit():
diff --git a/searx/engines/digbt.py b/searx/engines/digbt.py
new file mode 100644
index 000000000..c35327e8c
--- /dev/null
+++ b/searx/engines/digbt.py
@@ -0,0 +1,58 @@
+"""
+ DigBT (Videos, Music, Files)
+
+ @website https://digbt.org
+ @provide-api no
+
+ @using-api no
+ @results HTML (using search portal)
+ @stable no (HTML can change)
+ @parse url, title, content, magnetlink
+"""
+
+from urlparse import urljoin
+from lxml import html
+from searx.engines.xpath import extract_text
+from searx.utils import get_torrent_size
+
+categories = ['videos', 'music', 'files']
+paging = True
+
+URL = 'https://digbt.org'
+SEARCH_URL = URL + '/search/{query}-time-{pageno}'
+FILESIZE = 3
+FILESIZE_MULTIPLIER = 4
+
+
+def request(query, params):
+ params['url'] = SEARCH_URL.format(query=query, pageno=params['pageno'])
+
+ return params
+
+
+def response(resp):
+ dom = html.fromstring(resp.content)
+ search_res = dom.xpath('.//td[@class="x-item"]')
+
+ if not search_res:
+ return list()
+
+ results = list()
+ for result in search_res:
+ url = urljoin(URL, result.xpath('.//a[@title]/@href')[0])
+ title = result.xpath('.//a[@title]/text()')[0]
+ content = extract_text(result.xpath('.//div[@class="files"]'))
+ files_data = extract_text(result.xpath('.//div[@class="tail"]')).split()
+ filesize = get_torrent_size(files_data[FILESIZE], files_data[FILESIZE_MULTIPLIER])
+ magnetlink = result.xpath('.//div[@class="tail"]//a[@class="title"]/@href')[0]
+
+ results.append({'url': url,
+ 'title': title,
+ 'content': content,
+ 'filesize': filesize,
+ 'magnetlink': magnetlink,
+ 'seed': 'N/A',
+ 'leech': 'N/A',
+ 'template': 'torrent.html'})
+
+ return results
diff --git a/searx/engines/json_engine.py b/searx/engines/json_engine.py
index a824c38e5..4604c3cac 100644
--- a/searx/engines/json_engine.py
+++ b/searx/engines/json_engine.py
@@ -81,7 +81,7 @@ def request(query, params):
fp = {'query': query}
if paging and search_url.find('{pageno}') >= 0:
- fp['pageno'] = (params['pageno'] + first_page_num - 1) * page_size
+ fp['pageno'] = (params['pageno'] - 1) * page_size + first_page_num
params['url'] = search_url.format(**fp)
params['query'] = query
diff --git a/searx/engines/xpath.py b/searx/engines/xpath.py
index e701c02bf..e5c0c5bea 100644
--- a/searx/engines/xpath.py
+++ b/searx/engines/xpath.py
@@ -87,7 +87,7 @@ def request(query, params):
fp = {'query': query}
if paging and search_url.find('{pageno}') >= 0:
- fp['pageno'] = (params['pageno'] + first_page_num - 1) * page_size
+ fp['pageno'] = (params['pageno'] - 1) * page_size + first_page_num
params['url'] = search_url.format(**fp)
params['query'] = query
diff --git a/searx/results.py b/searx/results.py
index 9a4ec0b28..32832f199 100644
--- a/searx/results.py
+++ b/searx/results.py
@@ -28,7 +28,7 @@ def compare_urls(url_a, url_b):
else:
host_b = url_b.netloc
- if host_a != host_b or url_a.query != url_b.query:
+ if host_a != host_b or url_a.query != url_b.query or url_a.fragment != url_b.fragment:
return False
# remove / from the end of the url if required
diff --git a/searx/settings.yml b/searx/settings.yml
index f0d33e50e..905f07472 100644
--- a/searx/settings.yml
+++ b/searx/settings.yml
@@ -87,7 +87,7 @@ engines:
- name : btdigg
engine : btdigg
shortcut : bt
-
+
- name : crossref
engine : json_engine
paging : True
@@ -118,6 +118,12 @@ engines:
weight : 2
disabled : True
+ - name : digbt
+ engine : digbt
+ shortcut : dbt
+ timeout : 6.0
+ disabled : True
+
- name : digg
engine : digg
shortcut : dg
@@ -281,6 +287,18 @@ engines:
disabled : True
shortcut : habr
+ - name : hoogle
+ engine : json_engine
+ paging : True
+ search_url : https://www.haskell.org/hoogle/?mode=json&hoogle={query}&start={pageno}
+ results_query : results
+ url_query : location
+ title_query : self
+ content_query : docs
+ page_size : 20
+ categories : it
+ shortcut : ho
+
- name : ina
engine : ina
shortcut : in
diff --git a/searx/utils.py b/searx/utils.py
index aa8ce92a1..744142e36 100644
--- a/searx/utils.py
+++ b/searx/utils.py
@@ -237,3 +237,21 @@ def list_get(a_list, index, default=None):
return a_list[index]
else:
return default
+
+
+def get_torrent_size(filesize, filesize_multiplier):
+ try:
+ filesize = float(filesize)
+
+ if filesize_multiplier == 'TB':
+ filesize = int(filesize * 1024 * 1024 * 1024 * 1024)
+ elif filesize_multiplier == 'GB':
+ filesize = int(filesize * 1024 * 1024 * 1024)
+ elif filesize_multiplier == 'MB':
+ filesize = int(filesize * 1024 * 1024)
+ elif filesize_multiplier == 'KB':
+ filesize = int(filesize * 1024)
+ except:
+ filesize = None
+
+ return filesize
generated by cgit v1.2.3 (git 2.25.1) at 2026-06-13 00:02:31 +0000