commit: 0e6f8393ab8b29b2e85d1fafdc7442455767f753
parent: 03137eebd9fdfaa57452cb364c1bc9f31b243f67
Author: Adam Tauber <adam.tauber@balabit.com>
Date: Mon, 2 Feb 2015 09:37:12 +0100
Merge branch 'Cqoicebordel-unit-tests'
Diffstat:
45 files changed, 3692 insertions(+), 71 deletions(-)
diff --git a/.gitignore b/.gitignore
@@ -23,3 +23,4 @@ local/
parts/
searx.egg-info/
var/
+node_modules/
diff --git a/searx/engines/bing.py b/searx/engines/bing.py
@@ -14,6 +14,7 @@
from urllib import urlencode
from cgi import escape
from lxml import html
+from searx.engines.xpath import extract_text
# engine dependent config
categories = ['general']
@@ -55,8 +56,8 @@ def response(resp):
for result in dom.xpath('//div[@class="sa_cc"]'):
link = result.xpath('.//h3/a')[0]
url = link.attrib.get('href')
- title = ' '.join(link.xpath('.//text()'))
- content = escape(' '.join(result.xpath('.//p//text()')))
+ title = extract_text(link)
+ content = escape(extract_text(result.xpath('.//p')))
# append result
results.append({'url': url,
@@ -71,8 +72,8 @@ def response(resp):
for result in dom.xpath('//li[@class="b_algo"]'):
link = result.xpath('.//h2/a')[0]
url = link.attrib.get('href')
- title = ' '.join(link.xpath('.//text()'))
- content = escape(' '.join(result.xpath('.//p//text()')))
+ title = extract_text(link)
+ content = escape(extract_text(result.xpath('.//p')))
# append result
results.append({'url': url,
diff --git a/searx/engines/bing_images.py b/searx/engines/bing_images.py
@@ -33,7 +33,10 @@ def request(query, params):
offset = (params['pageno'] - 1) * 10 + 1
# required for cookie
- language = 'en-US'
+ if params['language'] == 'all':
+ language = 'en-US'
+ else:
+ language = params['language'].replace('_', '-')
search_path = search_string.format(
query=urlencode({'q': query}),
diff --git a/searx/engines/bing_news.py b/searx/engines/bing_news.py
@@ -15,6 +15,7 @@ from lxml import html
from datetime import datetime, timedelta
from dateutil import parser
import re
+from searx.engines.xpath import extract_text
# engine dependent config
categories = ['news']
@@ -42,6 +43,7 @@ def request(query, params):
params['cookies']['_FP'] = "ui=en-US"
params['url'] = base_url + search_path
+
return params
@@ -55,44 +57,35 @@ def response(resp):
for result in dom.xpath('//div[@class="sn_r"]'):
link = result.xpath('.//div[@class="newstitle"]/a')[0]
url = link.attrib.get('href')
- title = ' '.join(link.xpath('.//text()'))
- contentXPath = result.xpath('.//div[@class="sn_txt"]/div'
- '//span[@class="sn_snip"]//text()')
- if contentXPath is not None:
- content = escape(' '.join(contentXPath))
+ title = extract_text(link)
+ contentXPath = result.xpath('.//div[@class="sn_txt"]/div//span[@class="sn_snip"]')
+ content = escape(extract_text(contentXPath))
# parse publishedDate
publishedDateXPath = result.xpath('.//div[@class="sn_txt"]/div'
'//span[contains(@class,"sn_ST")]'
- '//span[contains(@class,"sn_tm")]'
- '//text()')
- if publishedDateXPath is not None:
- publishedDate = escape(' '.join(publishedDateXPath))
+ '//span[contains(@class,"sn_tm")]')
+
+ publishedDate = escape(extract_text(publishedDateXPath))
if re.match("^[0-9]+ minute(s|) ago$", publishedDate):
timeNumbers = re.findall(r'\d+', publishedDate)
- publishedDate = datetime.now()\
- - timedelta(minutes=int(timeNumbers[0]))
+ publishedDate = datetime.now() - timedelta(minutes=int(timeNumbers[0]))
elif re.match("^[0-9]+ hour(s|) ago$", publishedDate):
timeNumbers = re.findall(r'\d+', publishedDate)
- publishedDate = datetime.now()\
- - timedelta(hours=int(timeNumbers[0]))
- elif re.match("^[0-9]+ hour(s|),"
- " [0-9]+ minute(s|) ago$", publishedDate):
+ publishedDate = datetime.now() - timedelta(hours=int(timeNumbers[0]))
+ elif re.match("^[0-9]+ hour(s|), [0-9]+ minute(s|) ago$", publishedDate):
timeNumbers = re.findall(r'\d+', publishedDate)
publishedDate = datetime.now()\
- timedelta(hours=int(timeNumbers[0]))\
- timedelta(minutes=int(timeNumbers[1]))
elif re.match("^[0-9]+ day(s|) ago$", publishedDate):
timeNumbers = re.findall(r'\d+', publishedDate)
- publishedDate = datetime.now()\
- - timedelta(days=int(timeNumbers[0]))
+ publishedDate = datetime.now() - timedelta(days=int(timeNumbers[0]))
else:
try:
- # FIXME use params['language'] to parse either mm/dd or dd/mm
publishedDate = parser.parse(publishedDate, dayfirst=False)
except TypeError:
- # FIXME
publishedDate = datetime.now()
# append result
diff --git a/searx/engines/btdigg.py b/searx/engines/btdigg.py
@@ -23,11 +23,6 @@ paging = True
url = 'https://btdigg.org'
search_url = url + '/search?q={search_term}&p={pageno}'
-# specific xpath variables
-magnet_xpath = './/a[@title="Torrent magnet link"]'
-torrent_xpath = './/a[@title="Download torrent file"]'
-content_xpath = './/span[@class="font11px lightgrey block"]'
-
# do search-request
def request(query, params):
@@ -52,8 +47,8 @@ def response(resp):
# parse results
for result in search_res:
link = result.xpath('.//td[@class="torrent_name"]//a')[0]
- href = urljoin(url, link.attrib['href'])
- title = escape(extract_text(link.xpath('.//text()')))
+ href = urljoin(url, link.attrib.get('href'))
+ title = escape(extract_text(link))
content = escape(extract_text(result.xpath('.//pre[@class="snippet"]')[0]))
content = "<br />".join(content.split("\n"))
@@ -81,7 +76,7 @@ def response(resp):
filesize = int(filesize * 1024 * 1024 * 1024)
elif filesize_multiplier == 'MB':
filesize = int(filesize * 1024 * 1024)
- elif filesize_multiplier == 'kb':
+ elif filesize_multiplier == 'KB':
filesize = int(filesize * 1024)
except:
filesize = None
diff --git a/searx/engines/deviantart.py b/searx/engines/deviantart.py
@@ -14,6 +14,7 @@ from urllib import urlencode
from urlparse import urljoin
from lxml import html
import re
+from searx.engines.xpath import extract_text
# engine dependent config
categories = ['images']
@@ -50,9 +51,9 @@ def response(resp):
for result in dom.xpath('//div[contains(@class, "tt-a tt-fh")]'):
link = result.xpath('.//a[contains(@class, "thumb")]')[0]
url = urljoin(base_url, link.attrib.get('href'))
- title_links = result.xpath('.//span[@class="details"]//a[contains(@class, "t")]') # noqa
- title = ''.join(title_links[0].xpath('.//text()'))
- thumbnail_src = link.xpath('.//img')[0].attrib['src']
+ title_links = result.xpath('.//span[@class="details"]//a[contains(@class, "t")]')
+ title = extract_text(title_links[0])
+ thumbnail_src = link.xpath('.//img')[0].attrib.get('src')
img_src = regex.sub('/', thumbnail_src)
# append result
diff --git a/searx/engines/digg.py b/searx/engines/digg.py
@@ -44,7 +44,7 @@ def response(resp):
search_result = loads(resp.text)
- if search_result['html'] == '':
+ if 'html' not in search_result or search_result['html'] == '':
return results
dom = html.fromstring(search_result['html'])
diff --git a/searx/engines/flickr_noapi.py b/searx/engines/flickr_noapi.py
@@ -21,7 +21,7 @@ logger = logger.getChild('flickr-noapi')
categories = ['images']
url = 'https://secure.flickr.com/'
-search_url = url+'search/?{query}&page={page}'
+search_url = url + 'search/?{query}&page={page}'
photo_url = 'https://www.flickr.com/photos/{userid}/{photoid}'
regex = re.compile(r"\"search-photos-models\",\"photos\":(.*}),\"totalItems\":", re.DOTALL)
image_sizes = ('o', 'k', 'h', 'b', 'c', 'z', 'n', 'm', 't', 'q', 's')
diff --git a/searx/engines/google_images.py b/searx/engines/google_images.py
@@ -18,7 +18,7 @@ paging = True
# search-url
url = 'https://ajax.googleapis.com/'
-search_url = url + 'ajax/services/search/images?v=1.0&start={offset}&rsz=large&safe=off&filter=off&{query}' # noqa
+search_url = url + 'ajax/services/search/images?v=1.0&start={offset}&rsz=large&safe=off&filter=off&{query}'
# do search-request
@@ -45,14 +45,14 @@ def response(resp):
for result in search_res['responseData']['results']:
href = result['originalContextUrl']
title = result['title']
- if not result['url']:
+ if 'url' not in result:
continue
thumbnail_src = result['tbUrl']
# append result
results.append({'url': href,
'title': title,
- 'content': '',
+ 'content': result['content'],
'thumbnail_src': thumbnail_src,
'img_src': unquote(result['url']),
'template': 'images.html'})
diff --git a/searx/engines/google_news.py b/searx/engines/google_news.py
@@ -20,7 +20,7 @@ language_support = True
# engine dependent config
url = 'https://ajax.googleapis.com/'
-search_url = url + 'ajax/services/search/news?v=2.0&start={offset}&rsz=large&safe=off&filter=off&{query}&hl={language}' # noqa
+search_url = url + 'ajax/services/search/news?v=2.0&start={offset}&rsz=large&safe=off&filter=off&{query}&hl={lang}'
# do search-request
@@ -33,7 +33,7 @@ def request(query, params):
params['url'] = search_url.format(offset=offset,
query=urlencode({'q': query}),
- language=language)
+ lang=language)
return params
@@ -52,6 +52,8 @@ def response(resp):
for result in search_res['responseData']['results']:
# parse publishedDate
publishedDate = parser.parse(result['publishedDate'])
+ if 'url' not in result:
+ continue
# append result
results.append({'url': result['unescapedUrl'],
diff --git a/searx/engines/kickass.py b/searx/engines/kickass.py
@@ -13,6 +13,7 @@ from cgi import escape
from urllib import quote
from lxml import html
from operator import itemgetter
+from searx.engines.xpath import extract_text
# engine dependent config
categories = ['videos', 'music', 'files']
@@ -56,9 +57,8 @@ def response(resp):
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(html.tostring(result.xpath(content_xpath)[0],
- method="text"))
+ title = extract_text(link)
+ content = escape(extract_text(result.xpath(content_xpath)))
seed = result.xpath('.//td[contains(@class, "green")]/text()')[0]
leech = result.xpath('.//td[contains(@class, "red")]/text()')[0]
filesize = result.xpath('.//td[contains(@class, "nobr")]/text()')[0]
@@ -88,7 +88,7 @@ def response(resp):
filesize = int(filesize * 1024 * 1024 * 1024)
elif filesize_multiplier == 'MB':
filesize = int(filesize * 1024 * 1024)
- elif filesize_multiplier == 'kb':
+ elif filesize_multiplier == 'KB':
filesize = int(filesize * 1024)
except:
filesize = None
diff --git a/searx/engines/piratebay.py b/searx/engines/piratebay.py
@@ -13,6 +13,7 @@ from cgi import escape
from urllib import quote
from lxml import html
from operator import itemgetter
+from searx.engines.xpath import extract_text
# engine dependent config
categories = ['videos', 'music', 'files']
@@ -29,7 +30,8 @@ search_types = {'files': '0',
# specific xpath variables
magnet_xpath = './/a[@title="Download this torrent using magnet"]'
-content_xpath = './/font[@class="detDesc"]//text()'
+torrent_xpath = './/a[@title="Download this torrent"]'
+content_xpath = './/font[@class="detDesc"]'
# do search-request
@@ -59,8 +61,8 @@ def response(resp):
for result in search_res[1:]:
link = result.xpath('.//div[@class="detName"]//a')[0]
href = urljoin(url, link.attrib.get('href'))
- title = ' '.join(link.xpath('.//text()'))
- content = escape(' '.join(result.xpath(content_xpath)))
+ title = extract_text(link)
+ content = escape(extract_text(result.xpath(content_xpath)))
seed, leech = result.xpath('.//td[@align="right"]/text()')[:2]
# convert seed to int if possible
@@ -76,6 +78,7 @@ def response(resp):
leech = 0
magnetlink = result.xpath(magnet_xpath)[0]
+ torrentfile = result.xpath(torrent_xpath)[0]
# append result
results.append({'url': href,
@@ -83,7 +86,8 @@ def response(resp):
'content': content,
'seed': seed,
'leech': leech,
- 'magnetlink': magnetlink.attrib['href'],
+ 'magnetlink': magnetlink.attrib.get('href'),
+ 'torrentfile': torrentfile.attrib.get('href'),
'template': 'torrent.html'})
# return results sorted by seeder
diff --git a/searx/engines/searchcode_code.py b/searx/engines/searchcode_code.py
@@ -42,7 +42,7 @@ def response(resp):
search_results = loads(resp.text)
# parse results
- for result in search_results['results']:
+ for result in search_results.get('results', []):
href = result['url']
title = "" + result['name'] + " - " + result['filename']
repo = result['repo']
diff --git a/searx/engines/searchcode_doc.py b/searx/engines/searchcode_doc.py
@@ -35,7 +35,7 @@ def response(resp):
search_results = loads(resp.text)
# parse results
- for result in search_results['results']:
+ for result in search_results.get('results', []):
href = result['url']
title = "[" + result['type'] + "] " +\
result['namespace'] +\
diff --git a/searx/engines/stackoverflow.py b/searx/engines/stackoverflow.py
@@ -12,6 +12,7 @@ from urlparse import urljoin
from cgi import escape
from urllib import urlencode
from lxml import html
+from searx.engines.xpath import extract_text
# engine dependent config
categories = ['it']
@@ -24,8 +25,7 @@ search_url = url+'search?{query}&page={pageno}'
# specific xpath variables
results_xpath = '//div[contains(@class,"question-summary")]'
link_xpath = './/div[@class="result-link"]//a|.//div[@class="summary"]//h3//a'
-title_xpath = './/text()'
-content_xpath = './/div[@class="excerpt"]//text()'
+content_xpath = './/div[@class="excerpt"]'
# do search-request
@@ -46,8 +46,8 @@ def response(resp):
for result in dom.xpath(results_xpath):
link = result.xpath(link_xpath)[0]
href = urljoin(url, link.attrib.get('href'))
- title = escape(' '.join(link.xpath(title_xpath)))
- content = escape(' '.join(result.xpath(content_xpath)))
+ title = escape(extract_text(link))
+ content = escape(extract_text(result.xpath(content_xpath)))
# append result
results.append({'url': href,
diff --git a/searx/engines/vimeo.py b/searx/engines/vimeo.py
@@ -59,8 +59,7 @@ def response(resp):
url = base_url + videoid
title = p.unescape(extract_text(result.xpath(title_xpath)))
thumbnail = extract_text(result.xpath(content_xpath)[0])
- publishedDate = parser.parse(extract_text(
- result.xpath(publishedDate_xpath)[0]))
+ publishedDate = parser.parse(extract_text(result.xpath(publishedDate_xpath)[0]))
embedded = embedded_url.format(videoid=videoid)
# append result
diff --git a/searx/engines/www500px.py b/searx/engines/www500px.py
@@ -15,6 +15,7 @@ from urllib import urlencode
from urlparse import urljoin
from lxml import html
import re
+from searx.engines.xpath import extract_text
# engine dependent config
categories = ['images']
@@ -22,7 +23,7 @@ paging = True
# search-url
base_url = 'https://500px.com'
-search_url = base_url+'/search?search?page={pageno}&type=photos&{query}'
+search_url = base_url + '/search?search?page={pageno}&type=photos&{query}'
# do search-request
@@ -44,11 +45,11 @@ def response(resp):
for result in dom.xpath('//div[@class="photo"]'):
link = result.xpath('.//a')[0]
url = urljoin(base_url, link.attrib.get('href'))
- title = result.xpath('.//div[@class="title"]//text()')[0]
- thumbnail_src = link.xpath('.//img')[0].attrib['src']
+ title = extract_text(result.xpath('.//div[@class="title"]'))
+ thumbnail_src = link.xpath('.//img')[0].attrib.get('src')
# To have a bigger thumbnail, uncomment the next line
- #thumbnail_src = regex.sub('4.jpg', thumbnail_src)
- content = result.xpath('.//div[@class="info"]//text()')[0]
+ # thumbnail_src = regex.sub('4.jpg', thumbnail_src)
+ content = extract_text(result.xpath('.//div[@class="info"]'))
img_src = regex.sub('2048.jpg', thumbnail_src)
# append result
diff --git a/searx/engines/xpath.py b/searx/engines/xpath.py
@@ -28,13 +28,13 @@ def extract_text(xpath_results):
result = ''
for e in xpath_results:
result = result + extract_text(e)
- return result
+ return result.strip()
elif type(xpath_results) in [_ElementStringResult, _ElementUnicodeResult]:
# it's a string
return ''.join(xpath_results)
else:
# it's a element
- return html_to_text(xpath_results.text_content())
+ return html_to_text(xpath_results.text_content()).strip()
def extract_url(xpath_results, search_url):
diff --git a/searx/engines/youtube.py b/searx/engines/youtube.py
@@ -57,7 +57,7 @@ def response(resp):
url = [x['href'] for x in result['link'] if x['type'] == 'text/html']
if not url:
- return
+ continue
# remove tracking
url = url[0].replace('feature=youtube_gdata', '')
@@ -73,7 +73,7 @@ def response(resp):
pubdate = result['published']['$t']
publishedDate = parser.parse(pubdate)
- if result['media$group']['media$thumbnail']:
+ if 'media$thumbnail' in result['media$group']:
thumbnail = result['media$group']['media$thumbnail'][0]['url']
content = result['content']['$t']
diff --git a/searx/settings.yml b/searx/settings.yml
@@ -161,9 +161,9 @@ engines:
engine : photon
shortcut : ph
-# - name : piratebay
-# engine : piratebay
-# shortcut : tpb
+ - name : piratebay
+ engine : piratebay
+ shortcut : tpb
- name : kickass
engine : kickass
diff --git a/searx/tests/engines/test_bing.py b/searx/tests/engines/test_bing.py
@@ -0,0 +1,90 @@
+from collections import defaultdict
+import mock
+from searx.engines import bing
+from searx.testing import SearxTestCase
+
+
+class TestBingEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 0
+ dicto['language'] = 'fr_FR'
+ params = bing.request(query, dicto)
+ self.assertTrue('url' in params)
+ self.assertTrue(query in params['url'])
+ self.assertTrue('bing.com' in params['url'])
+ self.assertTrue('SRCHHPGUSR' in params['cookies'])
+ self.assertTrue('fr' in params['cookies']['SRCHHPGUSR'])
+
+ dicto['language'] = 'all'
+ params = bing.request(query, dicto)
+ self.assertTrue('SRCHHPGUSR' in params['cookies'])
+ self.assertTrue('en' in params['cookies']['SRCHHPGUSR'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, bing.response, None)
+ self.assertRaises(AttributeError, bing.response, [])
+ self.assertRaises(AttributeError, bing.response, '')
+ self.assertRaises(AttributeError, bing.response, '[]')
+
+ response = mock.Mock(content='<html></html>')
+ self.assertEqual(bing.response(response), [])
+
+ response = mock.Mock(content='<html></html>')
+ self.assertEqual(bing.response(response), [])
+
+ html = """
+ <div class="sa_cc" u="0|5109|4755453613245655|UAGjXgIrPH5yh-o5oNHRx_3Zta87f_QO">
+ <div Class="sa_mc">
+ <div class="sb_tlst">
+ <h3>
+ <a href="http://this.should.be.the.link/" h="ID=SERP,5124.1">
+ <strong>This</strong> should be the title</a>
+ </h3>
+ </div>
+ <div class="sb_meta"><cite><strong>this</strong>.meta.com</cite>
+ <span class="c_tlbxTrg">
+ <span class="c_tlbxH" H="BASE:CACHEDPAGEDEFAULT" K="SERP,5125.1">
+ </span>
+ </span>
+ </div>
+ <p><strong>This</strong> should be the content.</p>
+ </div>
+ </div>
+ """
+ response = mock.Mock(content=html)
+ results = bing.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'This should be the title')
+ self.assertEqual(results[0]['url'], 'http://this.should.be.the.link/')
+ self.assertEqual(results[0]['content'], 'This should be the content.')
+
+ html = """
+ <li class="b_algo" u="0|5109|4755453613245655|UAGjXgIrPH5yh-o5oNHRx_3Zta87f_QO">
+ <div Class="sa_mc">
+ <div class="sb_tlst">
+ <h2>
+ <a href="http://this.should.be.the.link/" h="ID=SERP,5124.1">
+ <strong>This</strong> should be the title</a>
+ </h2>
+ </div>
+ <div class="sb_meta"><cite><strong>this</strong>.meta.com</cite>
+ <span class="c_tlbxTrg">
+ <span class="c_tlbxH" H="BASE:CACHEDPAGEDEFAULT" K="SERP,5125.1">
+ </span>
+ </span>
+ </div>
+ <p><strong>This</strong> should be the content.</p>
+ </div>
+ </li>
+ """
+ response = mock.Mock(content=html)
+ results = bing.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'This should be the title')
+ self.assertEqual(results[0]['url'], 'http://this.should.be.the.link/')
+ self.assertEqual(results[0]['content'], 'This should be the content.')
diff --git a/searx/tests/engines/test_bing_images.py b/searx/tests/engines/test_bing_images.py
@@ -0,0 +1,268 @@
+# -*- coding: utf-8 -*-
+from collections import defaultdict
+import mock
+from searx.engines import bing_images
+from searx.testing import SearxTestCase
+
+
+class TestBingImagesEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ dicto['language'] = 'fr_FR'
+ params = bing_images.request(query, dicto)
+ self.assertTrue('url' in params)
+ self.assertTrue(query in params['url'])
+ self.assertTrue('bing.com' in params['url'])
+ self.assertTrue('SRCHHPGUSR' in params['cookies'])
+ self.assertTrue('fr' in params['cookies']['SRCHHPGUSR'])
+
+ dicto['language'] = 'all'
+ params = bing_images.request(query, dicto)
+ self.assertIn('SRCHHPGUSR', params['cookies'])
+ self.assertIn('en', params['cookies']['SRCHHPGUSR'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, bing_images.response, None)
+ self.assertRaises(AttributeError, bing_images.response, [])
+ self.assertRaises(AttributeError, bing_images.response, '')
+ self.assertRaises(AttributeError, bing_images.response, '[]')
+
+ response = mock.Mock(content='<html></html>')
+ self.assertEqual(bing_images.response(response), [])
+
+ response = mock.Mock(content='<html></html>')
+ self.assertEqual(bing_images.response(response), [])
+
+ html = """
+ <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+ <a href="#" ihk="HN.608003696942779811"
+ m="{ns:"images",k:"5045",
+mid:"659EB92C317974F34517A1CCAEBEF76A578E08DEE",
+surl:"http://www.page.url/",imgurl:"http://test.url/Test%20Query.jpg",
+oh:"238",tft:"0",oi:"http://www.image.url/Images/Test%20Query.jpg"}"
+ mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
+ t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
+ <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&o=4&pid=1.7"
+ style="height:144px;" width="178" height="144"/>
+ </a>
+ </div>
+ """
+ html = html.replace('\r\n', '').replace('\n', '').replace('\r', '')
+ response = mock.Mock(content=html)
+ results = bing_images.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'Test Query')
+ self.assertEqual(results[0]['url'], 'http://www.page.url/')
+ self.assertEqual(results[0]['content'], '')
+ self.assertEqual(results[0]['thumbnail_src'], 'http://ts1.mm.bing.net/th?id=HN.608003696942779811')
+ self.assertEqual(results[0]['img_src'], 'http://test.url/Test%20Query.jpg')
+
+ html = """
+ <a href="#" ihk="HN.608003696942779811"
+ m="{ns:"images",k:"5045",
+ mid:"59EB92C317974F34517A1CCAEBEF76A578E08DEE",
+ surl:"http://www.page.url/",
+ imgurl:"http://test.url/Test%20Query.jpg",oh:"238",
+ tft:"0",oi:"http://www.image.url/Images/Test%20Query.jpg"}"
+ mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
+ t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
+ <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&o=4&pid=1.7"
+ style="height:144px;" width="178" height="144"/>
+ </a>
+ """
+ response = mock.Mock(content=html)
+ results = bing_images.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
+
+ html = """
+ <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+ <a href="#" ihk="HN.608003696942779811"
+ m="{ns:"images",k:"5045",
+mid:"659EB92C317974F34517A1CCAEBEF76A578E08DEE",
+surl:"http://www.page.url/",imgurl:"http://test.url/Test%20Query.jpg",
+oh:"238",tft:"0",oi:"http://www.image.url/Images/Test%20Query.jpg"}"
+ mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
+ t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
+ <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&o=4&pid=1.7"
+ style="height:144px;" width="178" height="144"/>
+ </a>
+ </div>
+ <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+ <a href="#" ihk="HN.608003696942779811"
+ m="{ns:"images",k:"5045",
+mid:"659EB92C317974F34517A1CCAEBEF76A578E08DEE",
+surl:"http://www.page.url/",imgurl:"http://test.url/Test%20Query.jpg",
+oh:"238",tft:"0",oi:"http://www.image.url/Images/Test%20Query.jpg"}"
+ mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
+ t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
+ <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&o=4&pid=1.7"
+ style="height:144px;" width="178" height="144"/>
+ </a>
+ </div>
+ <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+ <a href="#" ihk="HN.608003696942779811"
+ m="{ns:"images",k:"5045",
+mid:"659EB92C317974F34517A1CCAEBEF76A578E08DEE",
+surl:"http://www.page.url/",imgurl:"http://test.url/Test%20Query.jpg",
+oh:"238",tft:"0",oi:"http://www.image.url/Images/Test%20Query.jpg"}"
+ mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
+ t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
+ <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&o=4&pid=1.7"
+ style="height:144px;" width="178" height="144"/>
+ </a>
+ </div>
+ <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+ <a href="#" ihk="HN.608003696942779811"
+ m="{ns:"images",k:"5045",
+mid:"659EB92C317974F34517A1CCAEBEF76A578E08DEE",
+surl:"http://www.page.url/",imgurl:"http://test.url/Test%20Query.jpg",
+oh:"238",tft:"0",oi:"http://www.image.url/Images/Test%20Query.jpg"}"
+ mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
+ t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
+ <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&o=4&pid=1.7"
+ style="height:144px;" width="178" height="144"/>
+ </a>
+ </div>
+ <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+ <a href="#" ihk="HN.608003696942779811"
+ m="{ns:"images",k:"5045",
+mid:"659EB92C317974F34517A1CCAEBEF76A578E08DEE",
+surl:"http://www.page.url/",imgurl:"http://test.url/Test%20Query.jpg",
+oh:"238",tft:"0",oi:"http://www.image.url/Images/Test%20Query.jpg"}"
+ mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
+ t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
+ <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&o=4&pid=1.7"
+ style="height:144px;" width="178" height="144"/>
+ </a>
+ </div>
+ <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+ <a href="#" ihk="HN.608003696942779811"
+ m="{ns:"images",k:"5045",
+mid:"659EB92C317974F34517A1CCAEBEF76A578E08DEE",
+surl:"http://www.page.url/",imgurl:"http://test.url/Test%20Query.jpg",
+oh:"238",tft:"0",oi:"http://www.image.url/Images/Test%20Query.jpg"}"
+ mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
+ t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
+ <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&o=4&pid=1.7"
+ style="height:144px;" width="178" height="144"/>
+ </a>
+ </div>
+ <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+ <a href="#" ihk="HN.608003696942779811"
+ m="{ns:"images",k:"5045",
+mid:"659EB92C317974F34517A1CCAEBEF76A578E08DEE",
+surl:"http://www.page.url/",imgurl:"http://test.url/Test%20Query.jpg",
+oh:"238",tft:"0",oi:"http://www.image.url/Images/Test%20Query.jpg"}"
+ mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
+ t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
+ <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&o=4&pid=1.7"
+ style="height:144px;" width="178" height="144"/>
+ </a>
+ </div>
+ <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+ <a href="#" ihk="HN.608003696942779811"
+ m="{ns:"images",k:"5045",
+mid:"659EB92C317974F34517A1CCAEBEF76A578E08DEE",
+surl:"http://www.page.url/",imgurl:"http://test.url/Test%20Query.jpg",
+oh:"238",tft:"0",oi:"http://www.image.url/Images/Test%20Query.jpg"}"
+ mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
+ t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
+ <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&o=4&pid=1.7"
+ style="height:144px;" width="178" height="144"/>
+ </a>
+ </div>
+ <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+ <a href="#" ihk="HN.608003696942779811"
+ m="{ns:"images",k:"5045",
+mid:"659EB92C317974F34517A1CCAEBEF76A578E08DEE",
+surl:"http://www.page.url/",imgurl:"http://test.url/Test%20Query.jpg",
+oh:"238",tft:"0",oi:"http://www.image.url/Images/Test%20Query.jpg"}"
+ mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
+ t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
+ <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&o=4&pid=1.7"
+ style="height:144px;" width="178" height="144"/>
+ </a>
+ </div>
+ <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+ <a href="#" ihk="HN.608003696942779811"
+ m="{ns:"images",k:"5045",
+mid:"659EB92C317974F34517A1CCAEBEF76A578E08DEE",
+surl:"http://www.page.url/",imgurl:"http://test.url/Test%20Query.jpg",
+oh:"238",tft:"0",oi:"http://www.image.url/Images/Test%20Query.jpg"}"
+ mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
+ t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
+ <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&o=4&pid=1.7"
+ style="height:144px;" width="178" height="144"/>
+ </a>
+ </div>
+ <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+ <a href="#" ihk="HN.608003696942779811"
+ m="{ns:"images",k:"5045",
+mid:"659EB92C317974F34517A1CCAEBEF76A578E08DEE",
+surl:"http://www.page.url/",imgurl:"http://test.url/Test%20Query.jpg",
+oh:"238",tft:"0",oi:"http://www.image.url/Images/Test%20Query.jpg"}"
+ mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
+ t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
+ <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&o=4&pid=1.7"
+ style="height:144px;" width="178" height="144"/>
+ </a>
+ </div>
+ <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+ <a href="#" ihk="HN.608003696942779811"
+ m="{ns:"images",k:"5045",
+mid:"659EB92C317974F34517A1CCAEBEF76A578E08DEE",
+surl:"http://www.page.url/",imgurl:"http://test.url/Test%20Query.jpg",
+oh:"238",tft:"0",oi:"http://www.image.url/Images/Test%20Query.jpg"}"
+ mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
+ t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
+ <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&o=4&pid=1.7"
+ style="height:144px;" width="178" height="144"/>
+ </a>
+ </div>
+ <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+ <a href="#" ihk="HN.608003696942779811"
+ m="{ns:"images",k:"5045",
+mid:"659EB92C317974F34517A1CCAEBEF76A578E08DEE",
+surl:"http://www.page.url/",imgurl:"http://test.url/Test%20Query.jpg",
+oh:"238",tft:"0",oi:"http://www.image.url/Images/Test%20Query.jpg"}"
+ mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
+ t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
+ <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&o=4&pid=1.7"
+ style="height:144px;" width="178" height="144"/>
+ </a>
+ </div>
+ <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+ <a href="#" ihk="HN.608003696942779811"
+ m="{ns:"images",k:"5045",
+mid:"659EB92C317974F34517A1CCAEBEF76A578E08DEE",
+surl:"http://www.page.url/",imgurl:"http://test.url/Test%20Query.jpg",
+oh:"238",tft:"0",oi:"http://www.image.url/Images/Test%20Query.jpg"}"
+ mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
+ t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
+ <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&o=4&pid=1.7"
+ style="height:144px;" width="178" height="144"/>
+ </a>
+ </div>
+ <div class="dg_u" style="width:178px;height:144px;left:17px;top:0px">
+ <a href="#" ihk="HN.608003696942779811"
+ m="{ns:"images",k:"5045",
+mid:"659EB92C317974F34517A1CCAEBEF76A578E08DEE",
+surl:"http://www.page.url/",imgurl:"http://test.url/Test%20Query.jpg",
+oh:"238",tft:"0",oi:"http://www.image.url/Images/Test%20Query.jpg"}"
+ mid="59EB92C317974F34517A1CCAEBEF76A578E08DEE" onclick="return false;"
+ t1="Test Query" t2="650 x 517 · 31 kB · jpeg" t3="www.short.url" h="ID=images,5045.1">
+ <img src="https://tse4.mm.bing.net/th?id=HN.608003696942779811&o=4&pid=1.7"
+ style="height:144px;" width="178" height="144"/>
+ </a>
+ </div>
+ """
+ html = html.replace('\r\n', '').replace('\n', '').replace('\r', '')
+ response = mock.Mock(content=html)
+ results = bing_images.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 10)
diff --git a/searx/tests/engines/test_bing_news.py b/searx/tests/engines/test_bing_news.py
@@ -0,0 +1,236 @@
+from collections import defaultdict
+import mock
+from searx.engines import bing_news
+from searx.testing import SearxTestCase
+
+
+class TestBingNewsEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ dicto['language'] = 'fr_FR'
+ params = bing_news.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('bing.com', params['url'])
+ self.assertIn('fr', params['url'])
+ self.assertIn('_FP', params['cookies'])
+ self.assertIn('en', params['cookies']['_FP'])
+
+ dicto['language'] = 'all'
+ params = bing_news.request(query, dicto)
+ self.assertIn('en', params['url'])
+ self.assertIn('_FP', params['cookies'])
+ self.assertIn('en', params['cookies']['_FP'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, bing_news.response, None)
+ self.assertRaises(AttributeError, bing_news.response, [])
+ self.assertRaises(AttributeError, bing_news.response, '')
+ self.assertRaises(AttributeError, bing_news.response, '[]')
+
+ response = mock.Mock(content='<html></html>')
+ self.assertEqual(bing_news.response(response), [])
+
+ response = mock.Mock(content='<html></html>')
+ self.assertEqual(bing_news.response(response), [])
+
+ html = """
+ <div class="sn_r">
+ <div class="newstitle">
+ <a href="http://url.of.article/" target="_blank" h="ID=news,5022.1">
+ Title
+ </a>
+ </div>
+ <div class="sn_img">
+ <a href="http://url.of.article2/" target="_blank" h="ID=news,5024.1">
+ <img class="rms_img" height="80" id="emb1" src="/image.src" title="Title" width="80" />
+ </a>
+ </div>
+ <div class="sn_txt">
+ <div class="sn_oi">
+ <span class="sn_snip">Article Content</span>
+ <span class="sn_ST">
+ <cite class="sn_src">metronews.fr</cite>
+ · 
+ <span class="sn_tm">44 minutes ago</span>
+ </span>
+ </div>
+ </div>
+ </div>
+ """
+ response = mock.Mock(content=html)
+ results = bing_news.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'Title')
+ self.assertEqual(results[0]['url'], 'http://url.of.article/')
+ self.assertEqual(results[0]['content'], 'Article Content')
+
+ html = """
+ <div class="sn_r">
+ <div class="newstitle">
+ <a href="http://url.of.article/" target="_blank" h="ID=news,5022.1">
+ Title
+ </a>
+ </div>
+ <div class="sn_img">
+ <a href="http://url.of.article2/" target="_blank" h="ID=news,5024.1">
+ <img class="rms_img" height="80" id="emb1" src="/image.src" title="Title" width="80" />
+ </a>
+ </div>
+ <div class="sn_txt">
+ <div class="sn_oi">
+ <span class="sn_snip">Article Content</span>
+ <span class="sn_ST">
+ <cite class="sn_src">metronews.fr</cite>
+ · 
+ <span class="sn_tm">44 minutes ago</span>
+ </span>
+ </div>
+ </div>
+ </div>
+ <div class="sn_r">
+ <div class="newstitle">
+ <a href="http://url.of.article/" target="_blank" h="ID=news,5022.1">
+ Title
+ </a>
+ </div>
+ <div class="sn_img">
+ <a href="http://url.of.article2/" target="_blank" h="ID=news,5024.1">
+ <img class="rms_img" height="80" id="emb1" src="/image.src" title="Title" width="80" />
+ </a>
+ </div>
+ <div class="sn_txt">
+ <div class="sn_oi">
+ <span class="sn_snip">Article Content</span>
+ <span class="sn_ST">
+ <cite class="sn_src">metronews.fr</cite>
+ · 
+ <span class="sn_tm">3 hours, 44 minutes ago</span>
+ </span>
+ </div>
+ </div>
+ </div>
+ <div class="sn_r">
+ <div class="newstitle">
+ <a href="http://url.of.article/" target="_blank" h="ID=news,5022.1">
+ Title
+ </a>
+ </div>
+ <div class="sn_img">
+ <a href="http://url.of.article2/" target="_blank" h="ID=news,5024.1">
+ <img class="rms_img" height="80" id="emb1" src="/image.src" title="Title" width="80" />
+ </a>
+ </div>
+ <div class="sn_txt">
+ <div class="sn_oi">
+ <span class="sn_snip">Article Content</span>
+ <span class="sn_ST">
+ <cite class="sn_src">metronews.fr</cite>
+ · 
+ <span class="sn_tm">44 hours ago</span>
+ </span>
+ </div>
+ </div>
+ </div>
+ <div class="sn_r">
+ <div class="newstitle">
+ <a href="http://url.of.article/" target="_blank" h="ID=news,5022.1">
+ Title
+ </a>
+ </div>
+ <div class="sn_img">
+ <a href="http://url.of.article2/" target="_blank" h="ID=news,5024.1">
+ <img class="rms_img" height="80" id="emb1" src="/image.src" title="Title" width="80" />
+ </a>
+ </div>
+ <div class="sn_txt">
+ <div class="sn_oi">
+ <span class="sn_snip">Article Content</span>
+ <span class="sn_ST">
+ <cite class="sn_src">metronews.fr</cite>
+ · 
+ <span class="sn_tm">2 days ago</span>
+ </span>
+ </div>
+ </div>
+ </div>
+ <div class="sn_r">
+ <div class="newstitle">
+ <a href="http://url.of.article/" target="_blank" h="ID=news,5022.1">
+ Title
+ </a>
+ </div>
+ <div class="sn_img">
+ <a href="http://url.of.article2/" target="_blank" h="ID=news,5024.1">
+ <img class="rms_img" height="80" id="emb1" src="/image.src" title="Title" width="80" />
+ </a>
+ </div>
+ <div class="sn_txt">
+ <div class="sn_oi">
+ <span class="sn_snip">Article Content</span>
+ <span class="sn_ST">
+ <cite class="sn_src">metronews.fr</cite>
+ · 
+ <span class="sn_tm">27/01/2015</span>
+ </span>
+ </div>
+ </div>
+ </div>
+ <div class="sn_r">
+ <div class="newstitle">
+ <a href="http://url.of.article/" target="_blank" h="ID=news,5022.1">
+ Title
+ </a>
+ </div>
+ <div class="sn_img">
+ <a href="http://url.of.article2/" target="_blank" h="ID=news,5024.1">
+ <img class="rms_img" height="80" id="emb1" src="/image.src" title="Title" width="80" />
+ </a>
+ </div>
+ <div class="sn_txt">
+ <div class="sn_oi">
+ <span class="sn_snip">Article Content</span>
+ <span class="sn_ST">
+ <cite class="sn_src">metronews.fr</cite>
+ · 
+ <span class="sn_tm">Il y a 3 heures</span>
+ </span>
+ </div>
+ </div>
+ </div>
+ """
+ response = mock.Mock(content=html)
+ results = bing_news.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 6)
+
+ html = """
+ <div class="newstitle">
+ <a href="http://url.of.article/" target="_blank" h="ID=news,5022.1">
+ Title
+ </a>
+ </div>
+ <div class="sn_img">
+ <a href="http://url.of.article2/" target="_blank" h="ID=news,5024.1">
+ <img class="rms_img" height="80" id="emb1" src="/image.src" title="Title" width="80" />
+ </a>
+ </div>
+ <div class="sn_txt">
+ <div class="sn_oi">
+ <span class="sn_snip">Article Content</span>
+ <span class="sn_ST">
+ <cite class="sn_src">metronews.fr</cite>
+ · 
+ <span class="sn_tm">44 minutes ago</span>
+ </span>
+ </div>
+ </div>
+ """
+ response = mock.Mock(content=html)
+ results = bing_news.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_btdigg.py b/searx/tests/engines/test_btdigg.py
@@ -0,0 +1,384 @@
+# -*- coding: utf-8 -*-
+from collections import defaultdict
+import mock
+from searx.engines import btdigg
+from searx.testing import SearxTestCase
+
+
+class TestBtdiggEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 0
+ params = btdigg.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('btdigg.org', params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, btdigg.response, None)
+ self.assertRaises(AttributeError, btdigg.response, [])
+ self.assertRaises(AttributeError, btdigg.response, '')
+ self.assertRaises(AttributeError, btdigg.response, '[]')
+
+ response = mock.Mock(text='<html></html>')
+ self.assertEqual(btdigg.response(response), [])
+
+ html = """
+ <div id="search_res">
+ <table>
+ <tr>
+ <td class="idx">1</td>
+ <td>
+ <table class="torrent_name_tbl">
+ <tr>
+ <td class="torrent_name">
+ <a href="/url">Should be the title</a>
+ </td>
+ </tr>
+ </table>
+ <table class="torrent_name_tbl">
+ <tr>
+ <td class="ttth">
+ <a onclick="fclck(this.href)" href="magnet:?xt=urn:btih:magnet&dn=Test"
+ title="Télécharger des liens Magnet">[magnet]</a>
+ </td>
+ <td class="ttth">
+ <a href="https://btcloud.io/manager?cmd=add&info_hash=hash"
+ target="_blank" title="Ajouter à BTCloud">[cloud]</a>
+ </td>
+ <td>
+ <span class="attr_name">Taille:</span>
+ <span class="attr_val">8 B</span>
+ </td>
+ <td>
+ <span class="attr_name">Fichiers:</span>
+ <span class="attr_val">710</span>
+ </td>
+ <td>
+ <span class="attr_name">Téléchargements:</span>
+ <span class="attr_val">5</span>
+ </td>
+ <td>
+ <span class="attr_name">Temps:</span>
+ <span class="attr_val">417.8 jours</span>
+ </td>
+ <td>
+ <span class="attr_name">Dernière mise à jour:</span>
+ <span class="attr_val">5.3 jours</span>
+ </td>
+ <td>
+ <span class="attr_name">Faux:</span>
+ <span class="attr_val">Aucun</span>
+ </td>
+ </tr>
+ </table>
+ <pre class="snippet">
+ Content
+ </pre>
+ </td>
+ </tr>
+ </table>
+ </div>
+ """
+ response = mock.Mock(text=html)
+ results = btdigg.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'Should be the title')
+ self.assertEqual(results[0]['url'], 'https://btdigg.org/url')
+ self.assertEqual(results[0]['content'], 'Content')
+ self.assertEqual(results[0]['seed'], 5)
+ self.assertEqual(results[0]['leech'], 0)
+ self.assertEqual(results[0]['filesize'], 8)
+ self.assertEqual(results[0]['files'], 710)
+ self.assertEqual(results[0]['magnetlink'], 'magnet:?xt=urn:btih:magnet&dn=Test')
+
+ html = """
+ <div id="search_res">
+ <table>
+ </table>
+ </div>
+ """
+ response = mock.Mock(text=html)
+ results = btdigg.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
+
+ html = """
+ <div id="search_res">
+ <table>
+ <tr>
+ <td class="idx">1</td>
+ <td>
+ <table class="torrent_name_tbl">
+ <tr>
+ <td class="torrent_name">
+ <a href="/url">Should be the title</a>
+ </td>
+ </tr>
+ </table>
+ <table class="torrent_name_tbl">
+ <tr>
+ <td class="ttth">
+ <a onclick="fclck(this.href)" href="magnet:?xt=urn:btih:magnet&dn=Test"
+ title="Télécharger des liens Magnet">[magnet]</a>
+ </td>
+ <td class="ttth">
+ <a href="https://btcloud.io/manager?cmd=add&info_hash=hash"
+ target="_blank" title="Ajouter à BTCloud">[cloud]</a>
+ </td>
+ <td>
+ <span class="attr_name">Taille:</span>
+ <span class="attr_val">1 KB</span>
+ </td>
+ <td>
+ <span class="attr_name">Fichiers:</span>
+ <span class="attr_val">710</span>
+ </td>
+ <td>
+ <span class="attr_name">Téléchargements:</span>
+ <span class="attr_val">5</span>
+ </td>
+ <td>
+ <span class="attr_name">Temps:</span>
+ <span class="attr_val">417.8 jours</span>
+ </td>
+ <td>
+ <span class="attr_name">Dernière mise à jour:</span>
+ <span class="attr_val">5.3 jours</span>
+ </td>
+ <td>
+ <span class="attr_name">Faux:</span>
+ <span class="attr_val">Aucun</span>
+ </td>
+ </tr>
+ </table>
+ <pre class="snippet">
+ Content
+ </pre>
+ </td>
+ </tr>
+ <tr>
+ <td class="idx">1</td>
+ <td>
+ <table class="torrent_name_tbl">
+ <tr>
+ <td class="torrent_name">
+ <a href="/url">Should be the title</a>
+ </td>
+ </tr>
+ </table>
+ <table class="torrent_name_tbl">
+ <tr>
+ <td class="ttth">
+ <a onclick="fclck(this.href)" href="magnet:?xt=urn:btih:magnet&dn=Test"
+ title="Télécharger des liens Magnet">[magnet]</a>
+ </td>
+ <td class="ttth">
+ <a href="https://btcloud.io/manager?cmd=add&info_hash=hash"
+ target="_blank" title="Ajouter à BTCloud">[cloud]</a>
+ </td>
+ <td>
+ <span class="attr_name">Taille:</span>
+ <span class="attr_val">1 MB</span>
+ </td>
+ <td>
+ <span class="attr_name">Fichiers:</span>
+ <span class="attr_val">a</span>
+ </td>
+ <td>
+ <span class="attr_name">Téléchargements:</span>
+ <span class="attr_val">4</span>
+ </td>
+ <td>
+ <span class="attr_name">Temps:</span>
+ <span class="attr_val">417.8 jours</span>
+ </td>
+ <td>
+ <span class="attr_name">Dernière mise à jour:</span>
+ <span class="attr_val">5.3 jours</span>
+ </td>
+ <td>
+ <span class="attr_name">Faux:</span>
+ <span class="attr_val">Aucun</span>
+ </td>
+ </tr>
+ </table>
+ <pre class="snippet">
+ Content
+ </pre>
+ </td>
+ </tr>
+ <tr>
+ <td class="idx">1</td>
+ <td>
+ <table class="torrent_name_tbl">
+ <tr>
+ <td class="torrent_name">
+ <a href="/url">Should be the title</a>
+ </td>
+ </tr>
+ </table>
+ <table class="torrent_name_tbl">
+ <tr>
+ <td class="ttth">
+ <a onclick="fclck(this.href)" href="magnet:?xt=urn:btih:magnet&dn=Test"
+ title="Télécharger des liens Magnet">[magnet]</a>
+ </td>
+ <td class="ttth">
+ <a href="https://btcloud.io/manager?cmd=add&info_hash=hash"
+ target="_blank" title="Ajouter à BTCloud">[cloud]</a>
+ </td>
+ <td>
+ <span class="attr_name">Taille:</span>
+ <span class="attr_val">1 GB</span>
+ </td>
+ <td>
+ <span class="attr_name">Fichiers:</span>
+ <span class="attr_val">710</span>
+ </td>
+ <td>
+ <span class="attr_name">Téléchargements:</span>
+ <span class="attr_val">3</span>
+ </td>
+ <td>
+ <span class="attr_name">Temps:</span>
+ <span class="attr_val">417.8 jours</span>
+ </td>
+ <td>
+ <span class="attr_name">Dernière mise à jour:</span>
+ <span class="attr_val">5.3 jours</span>
+ </td>
+ <td>
+ <span class="attr_name">Faux:</span>
+ <span class="attr_val">Aucun</span>
+ </td>
+ </tr>
+ </table>
+ <pre class="snippet">
+ Content
+ </pre>
+ </td>
+ </tr>
+ <tr>
+ <td class="idx">1</td>
+ <td>
+ <table class="torrent_name_tbl">
+ <tr>
+ <td class="torrent_name">
+ <a href="/url">Should be the title</a>
+ </td>
+ </tr>
+ </table>
+ <table class="torrent_name_tbl">
+ <tr>
+ <td class="ttth">
+ <a onclick="fclck(this.href)" href="magnet:?xt=urn:btih:magnet&dn=Test"
+ title="Télécharger des liens Magnet">[magnet]</a>
+ </td>
+ <td class="ttth">
+ <a href="https://btcloud.io/manager?cmd=add&info_hash=hash"
+ target="_blank" title="Ajouter à BTCloud">[cloud]</a>
+ </td>
+ <td>
+ <span class="attr_name">Taille:</span>
+ <span class="attr_val">1 TB</span>
+ </td>
+ <td>
+ <span class="attr_name">Fichiers:</span>
+ <span class="attr_val">710</span>
+ </td>
+ <td>
+ <span class="attr_name">Téléchargements:</span>
+ <span class="attr_val">2</span>
+ </td>
+ <td>
+ <span class="attr_name">Temps:</span>
+ <span class="attr_val">417.8 jours</span>
+ </td>
+ <td>
+ <span class="attr_name">Dernière mise à jour:</span>
+ <span class="attr_val">5.3 jours</span>
+ </td>
+ <td>
+ <span class="attr_name">Faux:</span>
+ <span class="attr_val">Aucun</span>
+ </td>
+ </tr>
+ </table>
+ <pre class="snippet">
+ Content
+ </pre>
+ </td>
+ </tr>
+ <tr>
+ <td class="idx">1</td>
+ <td>
+ <table class="torrent_name_tbl">
+ <tr>
+ <td class="torrent_name">
+ <a href="/url">Should be the title</a>
+ </td>
+ </tr>
+ </table>
+ <table class="torrent_name_tbl">
+ <tr>
+ <td class="ttth">
+ <a onclick="fclck(this.href)" href="magnet:?xt=urn:btih:magnet&dn=Test"
+ title="Télécharger des liens Magnet">[magnet]</a>
+ </td>
+ <td class="ttth">
+ <a href="https://btcloud.io/manager?cmd=add&info_hash=hash"
+ target="_blank" title="Ajouter à BTCloud">[cloud]</a>
+ </td>
+ <td>
+ <span class="attr_name">Taille:</span>
+ <span class="attr_val">a TB</span>
+ </td>
+ <td>
+ <span class="attr_name">Fichiers:</span>
+ <span class="attr_val">710</span>
+ </td>
+ <td>
+ <span class="attr_name">Téléchargements:</span>
+ <span class="attr_val">z</span>
+ </td>
+ <td>
+ <span class="attr_name">Temps:</span>
+ <span class="attr_val">417.8 jours</span>
+ </td>
+ <td>
+ <span class="attr_name">Dernière mise à jour:</span>
+ <span class="attr_val">5.3 jours</span>
+ </td>
+ <td>
+ <span class="attr_name">Faux:</span>
+ <span class="attr_val">Aucun</span>
+ </td>
+ </tr>
+ </table>
+ <pre class="snippet">
+ Content
+ </pre>
+ </td>
+ </tr>
+ </table>
+ </div>
+ """
+ response = mock.Mock(text=html)
+ results = btdigg.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 5)
+ self.assertEqual(results[0]['title'], 'Should be the title')
+ self.assertEqual(results[0]['url'], 'https://btdigg.org/url')
+ self.assertEqual(results[0]['content'], 'Content')
+ self.assertEqual(results[0]['seed'], 5)
+ self.assertEqual(results[0]['leech'], 0)
+ self.assertEqual(results[0]['files'], 710)
+ self.assertEqual(results[0]['magnetlink'], 'magnet:?xt=urn:btih:magnet&dn=Test')
+ self.assertEqual(results[0]['filesize'], 1024)
+ self.assertEqual(results[1]['filesize'], 1048576)
+ self.assertEqual(results[2]['filesize'], 1073741824)
+ self.assertEqual(results[3]['filesize'], 1099511627776)
diff --git a/searx/tests/engines/test_dailymotion.py b/searx/tests/engines/test_dailymotion.py
@@ -0,0 +1,74 @@
+from collections import defaultdict
+import mock
+from searx.engines import dailymotion
+from searx.testing import SearxTestCase
+
+
+class TestDailymotionEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 0
+ dicto['language'] = 'fr_FR'
+ params = dailymotion.request(query, dicto)
+ self.assertTrue('url' in params)
+ self.assertTrue(query in params['url'])
+ self.assertTrue('dailymotion.com' in params['url'])
+ self.assertTrue('fr' in params['url'])
+
+ dicto['language'] = 'all'
+ params = dailymotion.request(query, dicto)
+ self.assertTrue('en' in params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, dailymotion.response, None)
+ self.assertRaises(AttributeError, dailymotion.response, [])
+ self.assertRaises(AttributeError, dailymotion.response, '')
+ self.assertRaises(AttributeError, dailymotion.response, '[]')
+
+ response = mock.Mock(text='{}')
+ self.assertEqual(dailymotion.response(response), [])
+
+ response = mock.Mock(text='{"data": []}')
+ self.assertEqual(dailymotion.response(response), [])
+
+ json = """
+ {
+ "page": 1,
+ "limit": 5,
+ "explicit": false,
+ "total": 289487,
+ "has_more": true,
+ "list": [
+ {
+ "created_time": 1422173451,
+ "title": "Title",
+ "description": "Description",
+ "duration": 81,
+ "url": "http://www.url",
+ "thumbnail_360_url": "http://thumbnail",
+ "id": "x2fit7q"
+ }
+ ]
+ }
+ """
+ response = mock.Mock(text=json)
+ results = dailymotion.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'Title')
+ self.assertEqual(results[0]['url'], 'http://www.url')
+ self.assertEqual(results[0]['content'], 'Description')
+ self.assertIn('x2fit7q', results[0]['embedded'])
+
+ json = """
+ {"toto":[
+ {"id":200,"name":"Artist Name",
+ "link":"http:\/\/www.dailymotion.com\/artist\/1217","type":"artist"}
+ ]}
+ """
+ response = mock.Mock(text=json)
+ results = dailymotion.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_deezer.py b/searx/tests/engines/test_deezer.py
@@ -0,0 +1,57 @@
+from collections import defaultdict
+import mock
+from searx.engines import deezer
+from searx.testing import SearxTestCase
+
+
+class TestDeezerEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 0
+ params = deezer.request(query, dicto)
+ self.assertTrue('url' in params)
+ self.assertTrue(query in params['url'])
+ self.assertTrue('deezer.com' in params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, deezer.response, None)
+ self.assertRaises(AttributeError, deezer.response, [])
+ self.assertRaises(AttributeError, deezer.response, '')
+ self.assertRaises(AttributeError, deezer.response, '[]')
+
+ response = mock.Mock(text='{}')
+ self.assertEqual(deezer.response(response), [])
+
+ response = mock.Mock(text='{"data": []}')
+ self.assertEqual(deezer.response(response), [])
+
+ json = """
+ {"data":[
+ {"id":100, "title":"Title of track",
+ "link":"http:\/\/www.deezer.com\/track\/1094042","duration":232,
+ "artist":{"id":200,"name":"Artist Name",
+ "link":"http:\/\/www.deezer.com\/artist\/1217","type":"artist"},
+ "album":{"id":118106,"title":"Album Title","type":"album"},"type":"track"}
+ ]}
+ """
+ response = mock.Mock(text=json)
+ results = deezer.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'Title of track')
+ self.assertEqual(results[0]['url'], 'http://www.deezer.com/track/1094042')
+ self.assertEqual(results[0]['content'], 'Artist Name • Album Title • Title of track')
+ self.assertTrue('100' in results[0]['embedded'])
+
+ json = """
+ {"data":[
+ {"id":200,"name":"Artist Name",
+ "link":"http:\/\/www.deezer.com\/artist\/1217","type":"artist"}
+ ]}
+ """
+ response = mock.Mock(text=json)
+ results = deezer.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_deviantart.py b/searx/tests/engines/test_deviantart.py
@@ -0,0 +1,118 @@
+from collections import defaultdict
+import mock
+from searx.engines import deviantart
+from searx.testing import SearxTestCase
+
+
+class TestDeviantartEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 0
+ params = deviantart.request(query, dicto)
+ self.assertTrue('url' in params)
+ self.assertTrue(query in params['url'])
+ self.assertTrue('deviantart.com' in params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, deviantart.response, None)
+ self.assertRaises(AttributeError, deviantart.response, [])
+ self.assertRaises(AttributeError, deviantart.response, '')
+ self.assertRaises(AttributeError, deviantart.response, '[]')
+
+ response = mock.Mock(text='<html></html>')
+ self.assertEqual(deviantart.response(response), [])
+
+ response = mock.Mock(status_code=302)
+ self.assertEqual(deviantart.response(response), [])
+
+ html = """
+ <div class="tt-a tt-fh tt-boxed" collect_rid="1:149167425"
+ usericon="http://a.deviantart.net/avatars/t/e/test-0.gif" userid="233301"
+ username="test-0" symbol="~" category="digitalart/animation">
+ <span class="tt-w" style="width: auto; max-width: 277px;">
+ <span class="tt-fh-tc" style="width: 202px;">
+ <span class="tt-bb" style="width: 202px;">
+ </span>
+ <span class="shadow">
+ <a class="thumb" href="http://url.of.result/2nd.part.of.url"
+ title="Behoimi BE Animation Test by test-0, Jan 4,
+ 2010 in Digital Art > Animation"> <i></i>
+ <img width="200" height="200" alt="Test"
+ src="http://url.of.thumbnail" data-src="http://th08.deviantart.net/test.jpg">
+ </a>
+ </span>
+ <!-- ^TTT -->
+ </span>
+ <span class="details">
+ <a href="http://test-0.deviantart.com/art/Test" class="t"
+ title="Behoimi BE Animation Test by test-0, Jan 4, 2010">
+ <span class="tt-fh-oe">Title of image</span> </a>
+ <small>
+ <span class="category">
+ <span class="age">
+ 5 years ago
+ </span>
+ in <a title="Behoimi BE Animation Test by test-0, Jan 4, 2010"
+ href="http://www.deviantart.com/browse/all/digitalart/animation/">Animation</a>
+ </span>
+ <div class="commentcount">
+ <a href="http://test-0.deviantart.com/art/Test#comments">
+ <span class="iconcommentsstats"></span>9 Comments</a>
+ </div>
+ <a class="mlt-link" href="http://www.deviantart.com/morelikethis/149167425">
+ <span class="mlt-icon"></span> <span class="mlt-text">More Like This</span> </a>
+ </span>
+ </small> <!-- TTT$ -->
+ </span>
+ </div>
+ """
+ response = mock.Mock(text=html)
+ results = deviantart.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'Title of image')
+ self.assertEqual(results[0]['url'], 'http://url.of.result/2nd.part.of.url')
+ self.assertNotIn('content', results[0])
+ self.assertEqual(results[0]['thumbnail_src'], 'http://url.of.thumbnail')
+
+ html = """
+ <span class="tt-fh-tc" style="width: 202px;">
+ <span class="tt-bb" style="width: 202px;">
+ </span>
+ <span class="shadow">
+ <a class="thumb" href="http://url.of.result/2nd.part.of.url"
+ title="Behoimi BE Animation Test by test-0, Jan 4,
+ 2010 in Digital Art > Animation"> <i></i>
+ <img width="200" height="200" alt="Test"
+ src="http://url.of.thumbnail" data-src="http://th08.deviantart.net/test.jpg">
+ </a>
+ </span>
+ <!-- ^TTT -->
+ </span>
+ <span class="details">
+ <a href="http://test-0.deviantart.com/art/Test" class="t"
+ title="Behoimi BE Animation Test by test-0, Jan 4, 2010">
+ <span class="tt-fh-oe">Title of image</span> </a>
+ <small>
+ <span class="category">
+ <span class="age">
+ 5 years ago
+ </span>
+ in <a title="Behoimi BE Animation Test by test-0, Jan 4, 2010"
+ href="http://www.deviantart.com/browse/all/digitalart/animation/">Animation</a>
+ </span>
+ <div class="commentcount">
+ <a href="http://test-0.deviantart.com/art/Test#comments">
+ <span class="iconcommentsstats"></span>9 Comments</a>
+ </div>
+ <a class="mlt-link" href="http://www.deviantart.com/morelikethis/149167425">
+ <span class="mlt-icon"></span> <span class="mlt-text">More Like This</span> </a>
+ </span>
+ </small> <!-- TTT$ -->
+ """
+ response = mock.Mock(text=html)
+ results = deviantart.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_digg.py b/searx/tests/engines/test_digg.py
@@ -0,0 +1,101 @@
+from collections import defaultdict
+import mock
+from searx.engines import digg
+from searx.testing import SearxTestCase
+
+
+class TestDiggEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ params = digg.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('digg.com', params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, digg.response, None)
+ self.assertRaises(AttributeError, digg.response, [])
+ self.assertRaises(AttributeError, digg.response, '')
+ self.assertRaises(AttributeError, digg.response, '[]')
+
+ response = mock.Mock(text='{}')
+ self.assertEqual(digg.response(response), [])
+
+ response = mock.Mock(text='{"data": []}')
+ self.assertEqual(digg.response(response), [])
+
+ json = """
+ {
+ "status": "ok",
+ "num": 10,
+ "next_position": 20,
+ "html": "<article itemscope itemtype=\\"http://schema.org/Article\\"
+ class=\\"story-container digg-story-el hentry entry story-1sRANah col-1\\"
+ data-content-id=\\"1sRANah\\" data-contenturl=\\"http://url.of.link\\"
+ data-position=\\"0\\" data-diggs=\\"24\\" data-tweets=\\"69\\"
+ data-digg-score=\\"1190\\"> <div class=\\"story-image story-image-thumb\\">
+ <a data-position=\\"0\\" data-content-id=\\"1sRANah\\"
+ class=\\"story-link\\" href=\\"http://www.thedailybeast.com/\\"
+ target=\\"_blank\\"><img class=\\"story-image-img\\"
+ src=\\"http://url.of.image.jpeg\\" width=\\"312\\" height=\\"170\\"
+ alt=\\"\\" /> </a> </div> <div class=\\"story-content\\"><header
+ class=\\"story-header\\"> <div itemprop=\\"alternativeHeadline\\"
+ class=\\"story-kicker\\" >Kicker</div> <h2 itemprop=\\"headline\\"
+ class=\\"story-title entry-title\\"><a class=\\"story-title-link story-link\\"
+ rel=\\"bookmark\\" itemprop=\\"url\\" href=\\"http://www.thedailybeast.com/\\"
+ target=\\"_blank\\">Title of article</h2> <div class=\\"story-meta\\">
+ <div class=\\"story-score \\">
+ <div class=\\"story-score-diggscore diggscore-1sRANah\\">1190</div>
+ <div class=\\"story-score-details\\"> <div class=\\"arrow\\"></div>
+ <ul class=\\"story-score-details-list\\"> <li
+ class=\\"story-score-detail story-score-diggs\\"><span
+ class=\\"label\\">Diggs:</span> <span class=\\"count diggs-1sRANah\\">24</span>
+ </li> <li class=\\"story-score-detail story-score-twitter\\"><span
+ class=\\"label\\">Tweets:</span> <span class=\\"count tweets-1sRANah\\">69</span>
+ </li> <li class=\\"story-score-detail story-score-facebook\\"><span
+ class=\\"label\\">Facebook Shares:</span> <span
+ class=\\"count fb_shares-1sRANah\\">1097</span></li> </ul> </div> </div>
+ <span class=\\"story-meta-item story-source\\"> <a
+ itemprop=\\"publisher copyrightHolder sourceOrganization provider\\"
+ class=\\"story-meta-item-link story-source-link\\"
+ href=\\"/source/thedailybeast.com\\">The Daily Beast </a> </span>
+ <span class=\\"story-meta-item story-tag first-tag\\"> <a
+ itemprop=\\"keywords\\" rel=\\"tag\\"
+ class=\\"story-meta-item-link story-tag-link\\" href=\\"/tag/news\\">News</a>
+ </span> <abbr class=\\"published story-meta-item story-timestamp\\"
+ title=\\"2014-10-18 14:53:45\\"> <time datetime=\\"2014-10-18 14:53:45\\">18 Oct 2014</time>
+ </abbr> </div> </header> </div> <ul class=\\"story-actions\\"> <li
+ class=\\"story-action story-action-digg btn-story-action-container\\">
+ <a class=\\"target digg-1sRANah\\" href=\\"#\\">Digg</a></li> <li
+ class=\\"story-action story-action-save btn-story-action-container\\">
+ <a class=\\"target save-1sRANah\\" href=\\"#\\">Save</a></li> <li
+ class=\\"story-action story-action-share\\"><a
+ class=\\"target share-facebook\\" href=\\"https://www.facebook.com/\\">Facebook</a></li>
+ <li class=\\"story-action story-action-share\\"><a class=\\"target share-twitter\\"
+ href=\\"https://twitter.com/\\">Twitter</a></li> </ul> </article>"
+ }
+ """
+ json = json.replace('\r\n', '').replace('\n', '').replace('\r', '')
+ response = mock.Mock(text=json)
+ results = digg.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'Title of article')
+ self.assertEqual(results[0]['url'], 'http://url.of.link')
+ self.assertEqual(results[0]['thumbnail'], 'http://url.of.image.jpeg')
+ self.assertEqual(results[0]['content'], '')
+
+ json = """
+ {
+ "status": "error",
+ "num": 10,
+ "next_position": 20
+ }
+ """
+ response = mock.Mock(text=json)
+ results = digg.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_flickr.py b/searx/tests/engines/test_flickr.py
@@ -0,0 +1,142 @@
+from collections import defaultdict
+import mock
+from searx.engines import flickr
+from searx.testing import SearxTestCase
+
+
+class TestFlickrEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 0
+ params = flickr.request(query, dicto)
+ self.assertTrue('url' in params)
+ self.assertTrue(query in params['url'])
+ self.assertTrue('flickr.com' in params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, flickr.response, None)
+ self.assertRaises(AttributeError, flickr.response, [])
+ self.assertRaises(AttributeError, flickr.response, '')
+ self.assertRaises(AttributeError, flickr.response, '[]')
+
+ response = mock.Mock(text='{}')
+ self.assertEqual(flickr.response(response), [])
+
+ response = mock.Mock(text='{"data": []}')
+ self.assertEqual(flickr.response(response), [])
+
+ json = """
+ { "photos": { "page": 1, "pages": "41001", "perpage": 100, "total": "4100032",
+ "photo": [
+ { "id": "15751017054", "owner": "66847915@N08",
+ "secret": "69c22afc40", "server": "7285", "farm": 8,
+ "title": "Photo title", "ispublic": 1,
+ "isfriend": 0, "isfamily": 0,
+ "description": { "_content": "Description" },
+ "ownername": "Owner",
+ "url_o": "https:\/\/farm8.staticflickr.com\/7285\/15751017054_9178e0f963_o.jpg",
+ "height_o": "2100", "width_o": "2653",
+ "url_n": "https:\/\/farm8.staticflickr.com\/7285\/15751017054_69c22afc40_n.jpg",
+ "height_n": "253", "width_n": "320",
+ "url_z": "https:\/\/farm8.staticflickr.com\/7285\/15751017054_69c22afc40_z.jpg",
+ "height_z": "507", "width_z": "640" }
+ ] }, "stat": "ok" }
+ """
+ response = mock.Mock(text=json)
+ results = flickr.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'Photo title')
+ self.assertEqual(results[0]['url'], 'https://www.flickr.com/photos/66847915@N08/15751017054')
+ self.assertTrue('o.jpg' in results[0]['img_src'])
+ self.assertTrue('n.jpg' in results[0]['thumbnail_src'])
+ self.assertTrue('Owner' in results[0]['content'])
+ self.assertTrue('Description' in results[0]['content'])
+
+ json = """
+ { "photos": { "page": 1, "pages": "41001", "perpage": 100, "total": "4100032",
+ "photo": [
+ { "id": "15751017054", "owner": "66847915@N08",
+ "secret": "69c22afc40", "server": "7285", "farm": 8,
+ "title": "Photo title", "ispublic": 1,
+ "isfriend": 0, "isfamily": 0,
+ "description": { "_content": "Description" },
+ "ownername": "Owner",
+ "url_z": "https:\/\/farm8.staticflickr.com\/7285\/15751017054_69c22afc40_z.jpg",
+ "height_z": "507", "width_z": "640" }
+ ] }, "stat": "ok" }
+ """
+ response = mock.Mock(text=json)
+ results = flickr.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'Photo title')
+ self.assertEqual(results[0]['url'], 'https://www.flickr.com/photos/66847915@N08/15751017054')
+ self.assertTrue('z.jpg' in results[0]['img_src'])
+ self.assertTrue('z.jpg' in results[0]['thumbnail_src'])
+ self.assertTrue('Owner' in results[0]['content'])
+ self.assertTrue('Description' in results[0]['content'])
+
+ json = """
+ { "photos": { "page": 1, "pages": "41001", "perpage": 100, "total": "4100032",
+ "photo": [
+ { "id": "15751017054", "owner": "66847915@N08",
+ "secret": "69c22afc40", "server": "7285", "farm": 8,
+ "title": "Photo title", "ispublic": 1,
+ "isfriend": 0, "isfamily": 0,
+ "description": { "_content": "Description" },
+ "ownername": "Owner",
+ "url_o": "https:\/\/farm8.staticflickr.com\/7285\/15751017054_9178e0f963_o.jpg",
+ "height_o": "2100", "width_o": "2653" }
+ ] }, "stat": "ok" }
+ """
+ response = mock.Mock(text=json)
+ results = flickr.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'Photo title')
+ self.assertEqual(results[0]['url'], 'https://www.flickr.com/photos/66847915@N08/15751017054')
+ self.assertTrue('o.jpg' in results[0]['img_src'])
+ self.assertTrue('o.jpg' in results[0]['thumbnail_src'])
+ self.assertTrue('Owner' in results[0]['content'])
+ self.assertTrue('Description' in results[0]['content'])
+
+ json = """
+ { "photos": { "page": 1, "pages": "41001", "perpage": 100, "total": "4100032",
+ "photo": [
+ { "id": "15751017054", "owner": "66847915@N08",
+ "secret": "69c22afc40", "server": "7285", "farm": 8,
+ "title": "Photo title", "ispublic": 1,
+ "isfriend": 0, "isfamily": 0,
+ "description": { "_content": "Description" },
+ "ownername": "Owner",
+ "url_n": "https:\/\/farm8.staticflickr.com\/7285\/15751017054_69c22afc40_n.jpg",
+ "height_n": "253", "width_n": "320" }
+ ] }, "stat": "ok" }
+ """
+ response = mock.Mock(text=json)
+ results = flickr.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
+
+ json = """
+ { "photos": { "page": 1, "pages": "41001", "perpage": 100, "total": "4100032",
+ "toto": [] }, "stat": "ok" }
+ """
+ response = mock.Mock(text=json)
+ results = flickr.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
+
+ json = """
+ {"toto":[
+ {"id":200,"name":"Artist Name",
+ "link":"http:\/\/www.flickr.com\/artist\/1217","type":"artist"}
+ ]}
+ """
+ response = mock.Mock(text=json)
+ results = flickr.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_flickr_noapi.py b/searx/tests/engines/test_flickr_noapi.py
@@ -0,0 +1,442 @@
+from collections import defaultdict
+import mock
+from searx.engines import flickr_noapi
+from searx.testing import SearxTestCase
+
+
+class TestFlickrNoapiEngine(SearxTestCase):
+
+ def test_build_flickr_url(self):
+ url = flickr_noapi.build_flickr_url("uid", "pid")
+ self.assertIn("uid", url)
+ self.assertIn("pid", url)
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ params = flickr_noapi.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('flickr.com', params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, flickr_noapi.response, None)
+ self.assertRaises(AttributeError, flickr_noapi.response, [])
+ self.assertRaises(AttributeError, flickr_noapi.response, '')
+ self.assertRaises(AttributeError, flickr_noapi.response, '[]')
+
+ response = mock.Mock(text='"search-photos-models","photos":{},"totalItems":')
+ self.assertEqual(flickr_noapi.response(response), [])
+
+ response = mock.Mock(text='search-photos-models","photos":{"data": []},"totalItems":')
+ self.assertEqual(flickr_noapi.response(response), [])
+
+ json = """
+ "search-photos-models","photos":
+ {
+ "_data": [
+ {
+ "_flickrModelRegistry": "photo-models",
+ "title": "This is the title",
+ "sizes": {
+ "c": {
+ "displayUrl": "//farm8.staticflickr.com/7246/14001294434_410f653777_c.jpg",
+ "width": 541,
+ "height": 800,
+ "url": "//c4.staticflickr.com/8/7246/14001294434_410f653777_c.jpg",
+ "key": "c"
+ },
+ "h": {
+ "displayUrl": "//farm8.staticflickr.com/7246/14001294434_761d32237a_h.jpg",
+ "width": 1081,
+ "height": 1600,
+ "url": "//c4.staticflickr.com/8/7246/14001294434_761d32237a_h.jpg",
+ "key": "h"
+ },
+ "k": {
+ "displayUrl": "//farm8.staticflickr.com/7246/14001294434_f145a2c11a_k.jpg",
+ "width": 1383,
+ "height": 2048,
+ "url": "//c4.staticflickr.com/8/7246/14001294434_f145a2c11a_k.jpg",
+ "key": "k"
+ },
+ "l": {
+ "displayUrl": "//farm8.staticflickr.com/7246/14001294434_410f653777_b.jpg",
+ "width": 692,
+ "height": 1024,
+ "url": "//c4.staticflickr.com/8/7246/14001294434_410f653777_b.jpg",
+ "key": "l"
+ },
+ "m": {
+ "displayUrl": "//farm8.staticflickr.com/7246/14001294434_410f653777.jpg",
+ "width": 338,
+ "height": 500,
+ "url": "//c4.staticflickr.com/8/7246/14001294434_410f653777.jpg",
+ "key": "m"
+ },
+ "n": {
+ "displayUrl": "//farm8.staticflickr.com/7246/14001294434_410f653777_n.jpg",
+ "width": 216,
+ "height": 320,
+ "url": "//c4.staticflickr.com/8/7246/14001294434_410f653777_n.jpg",
+ "key": "n"
+ },
+ "q": {
+ "displayUrl": "//farm8.staticflickr.com/7246/14001294434_410f653777_q.jpg",
+ "width": 150,
+ "height": 150,
+ "url": "//c4.staticflickr.com/8/7246/14001294434_410f653777_q.jpg",
+ "key": "q"
+ },
+ "s": {
+ "displayUrl": "//farm8.staticflickr.com/7246/14001294434_410f653777_m.jpg",
+ "width": 162,
+ "height": 240,
+ "url": "//c4.staticflickr.com/8/7246/14001294434_410f653777_m.jpg",
+ "key": "s"
+ },
+ "sq": {
+ "displayUrl": "//farm8.staticflickr.com/7246/14001294434_410f653777_s.jpg",
+ "width": 75,
+ "height": 75,
+ "url": "//c4.staticflickr.com/8/7246/14001294434_410f653777_s.jpg",
+ "key": "sq"
+ },
+ "t": {
+ "displayUrl": "//farm8.staticflickr.com/7246/14001294434_410f653777_t.jpg",
+ "width": 68,
+ "height": 100,
+ "url": "//c4.staticflickr.com/8/7246/14001294434_410f653777_t.jpg",
+ "key": "t"
+ },
+ "z": {
+ "displayUrl": "//farm8.staticflickr.com/7246/14001294434_410f653777_z.jpg",
+ "width": 433,
+ "height": 640,
+ "url": "//c4.staticflickr.com/8/7246/14001294434_410f653777_z.jpg",
+ "key": "z"
+ }
+ },
+ "canComment": false,
+ "rotation": 0,
+ "owner": {
+ "_flickrModelRegistry": "person-models",
+ "pathAlias": "klink692",
+ "username": "Owner",
+ "buddyicon": {
+ "retina": null,
+ "large": null,
+ "medium": null,
+ "small": null,
+ "default": "//c1.staticflickr.com/9/8108/buddyicons/59729010@N00.jpg?1361642376#59729010@N00"
+ },
+ "isPro": true,
+ "id": "59729010@N00"
+ },
+ "engagement": {
+ "_flickrModelRegistry": "photo-engagement-models",
+ "ownerNsid": "59729010@N00",
+ "faveCount": 21,
+ "commentCount": 14,
+ "viewCount": 10160,
+ "id": "14001294434"
+ },
+ "description": "Description",
+ "isHD": false,
+ "secret": "410f653777",
+ "canAddMeta": false,
+ "license": 0,
+ "oWidth": 1803,
+ "oHeight": 2669,
+ "safetyLevel": 0,
+ "id": "14001294434"
+ }
+ ],
+ "fetchedStart": true,
+ "fetchedEnd": false,
+ "totalItems": "4386039"
+ },"totalItems":
+ """
+ json = json.replace('\r\n', '').replace('\n', '').replace('\r', '')
+ response = mock.Mock(text=json)
+ results = flickr_noapi.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'This is the title')
+ self.assertEqual(results[0]['url'], 'https://www.flickr.com/photos/59729010@N00/14001294434')
+ self.assertIn('k.jpg', results[0]['img_src'])
+ self.assertIn('n.jpg', results[0]['thumbnail_src'])
+ self.assertIn('Owner', results[0]['content'])
+ self.assertIn('Description', results[0]['content'])
+
+ json = """
+ "search-photos-models","photos":
+ {
+ "_data": [
+ {
+ "_flickrModelRegistry": "photo-models",
+ "title": "This is the title",
+ "sizes": {
+ "z": {
+ "displayUrl": "//farm8.staticflickr.com/7246/14001294434_410f653777_z.jpg",
+ "width": 433,
+ "height": 640,
+ "url": "//c4.staticflickr.com/8/7246/14001294434_410f653777_z.jpg",
+ "key": "z"
+ }
+ },
+ "canComment": false,
+ "rotation": 0,
+ "owner": {
+ "_flickrModelRegistry": "person-models",
+ "pathAlias": "klink692",
+ "username": "Owner",
+ "buddyicon": {
+ "retina": null,
+ "large": null,
+ "medium": null,
+ "small": null,
+ "default": "//c1.staticflickr.com/9/8108/buddyicons/59729010@N00.jpg?1361642376#59729010@N00"
+ },
+ "isPro": true,
+ "id": "59729010@N00"
+ },
+ "engagement": {
+ "_flickrModelRegistry": "photo-engagement-models",
+ "ownerNsid": "59729010@N00",
+ "faveCount": 21,
+ "commentCount": 14,
+ "viewCount": 10160,
+ "id": "14001294434"
+ },
+ "description": "Description",
+ "isHD": false,
+ "secret": "410f653777",
+ "canAddMeta": false,
+ "license": 0,
+ "oWidth": 1803,
+ "oHeight": 2669,
+ "safetyLevel": 0,
+ "id": "14001294434"
+ }
+ ],
+ "fetchedStart": true,
+ "fetchedEnd": false,
+ "totalItems": "4386039"
+ },"totalItems":
+ """
+ response = mock.Mock(text=json)
+ results = flickr_noapi.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'This is the title')
+ self.assertEqual(results[0]['url'], 'https://www.flickr.com/photos/59729010@N00/14001294434')
+ self.assertIn('z.jpg', results[0]['img_src'])
+ self.assertIn('z.jpg', results[0]['thumbnail_src'])
+ self.assertIn('Owner', results[0]['content'])
+ self.assertIn('Description', results[0]['content'])
+
+ json = """
+ "search-photos-models","photos":
+ {
+ "_data": [
+ {
+ "_flickrModelRegistry": "photo-models",
+ "title": "This is the title",
+ "sizes": {
+ "o": {
+ "displayUrl": "//farm8.staticflickr.com/7246/14001294434_410f653777_o.jpg",
+ "width": 433,
+ "height": 640,
+ "url": "//c4.staticflickr.com/8/7246/14001294434_410f653777_o.jpg",
+ "key": "o"
+ }
+ },
+ "canComment": false,
+ "rotation": 0,
+ "owner": {
+ "_flickrModelRegistry": "person-models",
+ "pathAlias": "klink692",
+ "username": "Owner",
+ "buddyicon": {
+ "retina": null,
+ "large": null,
+ "medium": null,
+ "small": null,
+ "default": "//c1.staticflickr.com/9/8108/buddyicons/59729010@N00.jpg?1361642376#59729010@N00"
+ },
+ "isPro": true,
+ "id": "59729010@N00"
+ },
+ "engagement": {
+ "_flickrModelRegistry": "photo-engagement-models",
+ "ownerNsid": "59729010@N00",
+ "faveCount": 21,
+ "commentCount": 14,
+ "viewCount": 10160,
+ "id": "14001294434"
+ },
+ "isHD": false,
+ "secret": "410f653777",
+ "canAddMeta": false,
+ "license": 0,
+ "oWidth": 1803,
+ "oHeight": 2669,
+ "safetyLevel": 0,
+ "id": "14001294434"
+ }
+ ],
+ "fetchedStart": true,
+ "fetchedEnd": false,
+ "totalItems": "4386039"
+ },"totalItems":
+ """
+ response = mock.Mock(text=json)
+ results = flickr_noapi.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'This is the title')
+ self.assertEqual(results[0]['url'], 'https://www.flickr.com/photos/59729010@N00/14001294434')
+ self.assertIn('o.jpg', results[0]['img_src'])
+ self.assertIn('o.jpg', results[0]['thumbnail_src'])
+ self.assertIn('Owner', results[0]['content'])
+
+ json = """
+ "search-photos-models","photos":
+ {
+ "_data": [
+ {
+ "_flickrModelRegistry": "photo-models",
+ "title": "This is the title",
+ "sizes": {
+ },
+ "canComment": false,
+ "rotation": 0,
+ "owner": {
+ "_flickrModelRegistry": "person-models",
+ "pathAlias": "klink692",
+ "username": "Owner",
+ "buddyicon": {
+ "retina": null,
+ "large": null,
+ "medium": null,
+ "small": null,
+ "default": "//c1.staticflickr.com/9/8108/buddyicons/59729010@N00.jpg?1361642376#59729010@N00"
+ },
+ "isPro": true,
+ "id": "59729010@N00"
+ },
+ "engagement": {
+ "_flickrModelRegistry": "photo-engagement-models",
+ "ownerNsid": "59729010@N00",
+ "faveCount": 21,
+ "commentCount": 14,
+ "viewCount": 10160,
+ "id": "14001294434"
+ },
+ "description": "Description",
+ "isHD": false,
+ "secret": "410f653777",
+ "canAddMeta": false,
+ "license": 0,
+ "oWidth": 1803,
+ "oHeight": 2669,
+ "safetyLevel": 0,
+ "id": "14001294434"
+ }
+ ],
+ "fetchedStart": true,
+ "fetchedEnd": false,
+ "totalItems": "4386039"
+ },"totalItems":
+ """
+ response = mock.Mock(text=json)
+ results = flickr_noapi.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
+
+ json = """
+ "search-photos-models","photos":
+ {
+ "_data": [null],
+ "fetchedStart": true,
+ "fetchedEnd": false,
+ "totalItems": "4386039"
+ },"totalItems":
+ """
+ response = mock.Mock(text=json)
+ results = flickr_noapi.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
+
+ json = """
+ "search-photos-models","photos":
+ {
+ "_data": [
+ {
+ "_flickrModelRegistry": "photo-models",
+ "title": "This is the title",
+ "sizes": {
+ "o": {
+ "displayUrl": "//farm8.staticflickr.com/7246/14001294434_410f653777_o.jpg",
+ "width": 433,
+ "height": 640,
+ "url": "//c4.staticflickr.com/8/7246/14001294434_410f653777_o.jpg",
+ "key": "o"
+ }
+ },
+ "canComment": false,
+ "rotation": 0,
+ "owner": {
+ "_flickrModelRegistry": "person-models",
+ "pathAlias": "klink692",
+ "username": "Owner",
+ "buddyicon": {
+ "retina": null,
+ "large": null,
+ "medium": null,
+ "small": null,
+ "default": "//c1.staticflickr.com/9/8108/buddyicons/59729010@N00.jpg?1361642376#59729010@N00"
+ },
+ "isPro": true
+ },
+ "engagement": {
+ "_flickrModelRegistry": "photo-engagement-models",
+ "ownerNsid": "59729010@N00",
+ "faveCount": 21,
+ "commentCount": 14,
+ "viewCount": 10160,
+ "id": "14001294434"
+ },
+ "description": "Description",
+ "isHD": false,
+ "secret": "410f653777",
+ "canAddMeta": false,
+ "license": 0,
+ "oWidth": 1803,
+ "oHeight": 2669,
+ "safetyLevel": 0,
+ "id": "14001294434"
+ }
+ ],
+ "fetchedStart": true,
+ "fetchedEnd": false,
+ "totalItems": "4386039"
+ },"totalItems":
+ """
+ response = mock.Mock(text=json)
+ results = flickr_noapi.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
+
+ json = """
+ {"toto":[
+ {"id":200,"name":"Artist Name",
+ "link":"http:\/\/www.flickr.com\/artist\/1217","type":"artist"}
+ ]}
+ """
+ response = mock.Mock(text=json)
+ results = flickr_noapi.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_google_images.py b/searx/tests/engines/test_google_images.py
@@ -0,0 +1,108 @@
+from collections import defaultdict
+import mock
+from searx.engines import google_images
+from searx.testing import SearxTestCase
+
+
+class TestGoogleImagesEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ params = google_images.request(query, dicto)
+ self.assertTrue('url' in params)
+ self.assertTrue(query in params['url'])
+ self.assertTrue('googleapis.com' in params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, google_images.response, None)
+ self.assertRaises(AttributeError, google_images.response, [])
+ self.assertRaises(AttributeError, google_images.response, '')
+ self.assertRaises(AttributeError, google_images.response, '[]')
+
+ response = mock.Mock(text='{}')
+ self.assertEqual(google_images.response(response), [])
+
+ response = mock.Mock(text='{"data": []}')
+ self.assertEqual(google_images.response(response), [])
+
+ json = """
+ {
+ "responseData": {
+ "results": [
+ {
+ "GsearchResultClass": "GimageSearch",
+ "width": "400",
+ "height": "400",
+ "imageId": "ANd9GcQbYb9FJuAbG_hT4i8FeC0O0x-P--EHdzgRIF9ao97nHLl7C2mREn6qTQ",
+ "tbWidth": "124",
+ "tbHeight": "124",
+ "unescapedUrl": "http://unescaped.url.jpg",
+ "url": "http://image.url.jpg",
+ "visibleUrl": "insolitebuzz.fr",
+ "title": "This is the title",
+ "titleNoFormatting": "Petit test sympa qui rend fou tout le monde ! A faire",
+ "originalContextUrl": "http://this.is.the.url",
+ "content": "<b>test</b>",
+ "contentNoFormatting": "test",
+ "tbUrl": "http://thumbnail.url"
+ }
+ ]
+ },
+ "responseDetails": null,
+ "responseStatus": 200
+ }
+ """
+ response = mock.Mock(text=json)
+ results = google_images.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'This is the title')
+ self.assertEqual(results[0]['url'], 'http://this.is.the.url')
+ self.assertEqual(results[0]['thumbnail_src'], 'http://thumbnail.url')
+ self.assertEqual(results[0]['img_src'], 'http://image.url.jpg')
+ self.assertEqual(results[0]['content'], '<b>test</b>')
+
+ json = """
+ {
+ "responseData": {
+ "results": [
+ {
+ "GsearchResultClass": "GimageSearch",
+ "width": "400",
+ "height": "400",
+ "imageId": "ANd9GcQbYb9FJuAbG_hT4i8FeC0O0x-P--EHdzgRIF9ao97nHLl7C2mREn6qTQ",
+ "tbWidth": "124",
+ "tbHeight": "124",
+ "unescapedUrl": "http://unescaped.url.jpg",
+ "visibleUrl": "insolitebuzz.fr",
+ "title": "This is the title",
+ "titleNoFormatting": "Petit test sympa qui rend fou tout le monde ! A faire",
+ "originalContextUrl": "http://this.is.the.url",
+ "content": "<b>test</b>",
+ "contentNoFormatting": "test",
+ "tbUrl": "http://thumbnail.url"
+ }
+ ]
+ },
+ "responseDetails": null,
+ "responseStatus": 200
+ }
+ """
+ response = mock.Mock(text=json)
+ results = google_images.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
+
+ json = """
+ {
+ "responseData": {},
+ "responseDetails": null,
+ "responseStatus": 200
+ }
+ """
+ response = mock.Mock(text=json)
+ results = google_images.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_google_news.py b/searx/tests/engines/test_google_news.py
@@ -0,0 +1,136 @@
+from collections import defaultdict
+import mock
+from searx.engines import google_news
+from searx.testing import SearxTestCase
+
+
+class TestGoogleNewsEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ dicto['language'] = 'fr_FR'
+ params = google_news.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('googleapis.com', params['url'])
+ self.assertIn('fr', params['url'])
+
+ dicto['language'] = 'all'
+ params = google_news.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn('en', params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, google_news.response, None)
+ self.assertRaises(AttributeError, google_news.response, [])
+ self.assertRaises(AttributeError, google_news.response, '')
+ self.assertRaises(AttributeError, google_news.response, '[]')
+
+ response = mock.Mock(text='{}')
+ self.assertEqual(google_news.response(response), [])
+
+ response = mock.Mock(text='{"data": []}')
+ self.assertEqual(google_news.response(response), [])
+
+ json = """
+ {
+ "responseData": {
+ "results": [
+ {
+ "GsearchResultClass": "GnewsSearch",
+ "clusterUrl": "http://news.google.com/news/story?ncl=d2d3t1LMDpNIj2MPPhdTT0ycN4sWM&hl=fr&ned=fr",
+ "content": "This is the content",
+ "unescapedUrl": "http://this.is.the.url",
+ "url": "http://this.is.the.url",
+ "title": "This is the title",
+ "titleNoFormatting": "This is the title",
+ "location": "",
+ "publisher": "Jeux Actu",
+ "publishedDate": "Fri, 30 Jan 2015 11:00:25 -0800",
+ "signedRedirectUrl": "http://news.google.com/",
+ "language": "fr",
+ "image": {
+ "url": "http://i.jeuxactus.com/datas/jeux/d/y/dying-light/vu/dying-light-54cc080b568fb.jpg",
+ "tbUrl": "http://t1.gstatic.com/images?q=tbn:ANd9GcSF4yYrs9Ycw23DGiOSAZ-5SEPXYwG3LNs",
+ "originalContextUrl": "http://www.jeuxactu.com/test-dying-light-sur-ps4-97208.htm",
+ "publisher": "Jeux Actu",
+ "tbWidth": 80,
+ "tbHeight": 30
+ },
+ "relatedStories": [
+ {
+ "unescapedUrl": "http://www.jeuxvideo.com/test/415823/dying-light.htm",
+ "url": "http%3A%2F%2Fwww.jeuxvideo.com%2Ftest%2F415823%2Fdying-light.htm",
+ "title": "<b>Test</b> du jeu Dying Light - jeuxvideo.com",
+ "titleNoFormatting": "Test du jeu Dying Light - jeuxvideo.com",
+ "location": "",
+ "publisher": "JeuxVideo.com",
+ "publishedDate": "Fri, 30 Jan 2015 08:52:30 -0800",
+ "signedRedirectUrl": "http://news.google.com/news/url?sa=T&",
+ "language": "fr"
+ }
+ ]
+ }
+ ]
+ },
+ "responseDetails": null,
+ "responseStatus": 200
+ }
+ """
+ response = mock.Mock(text=json)
+ results = google_news.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'This is the title')
+ self.assertEqual(results[0]['url'], 'http://this.is.the.url')
+ self.assertEqual(results[0]['content'], 'This is the content')
+
+ json = """
+ {
+ "responseData": {
+ "results": [
+ {
+ "GsearchResultClass": "GnewsSearch",
+ "clusterUrl": "http://news.google.com/news/story?ncl=d2d3t1LMDpNIj2MPPhdTT0ycN4sWM&hl=fr&ned=fr",
+ "content": "This is the content",
+ "unescapedUrl": "http://this.is.the.url",
+ "title": "This is the title",
+ "titleNoFormatting": "This is the title",
+ "location": "",
+ "publisher": "Jeux Actu",
+ "publishedDate": "Fri, 30 Jan 2015 11:00:25 -0800",
+ "signedRedirectUrl": "http://news.google.com/news/",
+ "language": "fr",
+ "image": {
+ "url": "http://i.jeuxactus.com/datas/jeux/d/y/dying-light/vu/dying-light-54cc080b568fb.jpg",
+ "tbUrl": "http://t1.gstatic.com/images?q=tbn:b_6f-OSAZ-5SEPXYwG3LNs",
+ "originalContextUrl": "http://www.jeuxactu.com/test-dying-light-sur-ps4-97208.htm",
+ "publisher": "Jeux Actu",
+ "tbWidth": 80,
+ "tbHeight": 30
+ }
+ }
+ ]
+ },
+ "responseDetails": null,
+ "responseStatus": 200
+ }
+ """
+ response = mock.Mock(text=json)
+ results = google_news.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
+
+ json = """
+ {
+ "responseData": {},
+ "responseDetails": null,
+ "responseStatus": 200
+ }
+ """
+ response = mock.Mock(text=json)
+ results = google_news.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_kickass.py b/searx/tests/engines/test_kickass.py
@@ -0,0 +1,398 @@
+# -*- coding: utf-8 -*-
+from collections import defaultdict
+import mock
+from searx.engines import kickass
+from searx.testing import SearxTestCase
+
+
+class TestKickassEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ params = kickass.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('kickass.so', params['url'])
+ self.assertIn('verify', params)
+ self.assertFalse(params['verify'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, kickass.response, None)
+ self.assertRaises(AttributeError, kickass.response, [])
+ self.assertRaises(AttributeError, kickass.response, '')
+ self.assertRaises(AttributeError, kickass.response, '[]')
+
+ response = mock.Mock(text='<html></html>')
+ self.assertEqual(kickass.response(response), [])
+
+ html = """
+ <table cellpadding="0" cellspacing="0" class="data" style="width: 100%">
+ <tr class="firstr">
+ <th class="width100perc nopad">torrent name</th>
+ <th class="center">
+ <a href="/search/test/?field=size&sorder=desc" rel="nofollow">size</a>
+ </th>
+ <th class="center"><span class="files">
+ <a href="/search/test/?field=files_count&sorder=desc" rel="nofollow">files</a></span>
+ </th>
+ <th class="center"><span>
+ <a href="/search/test/?field=time_add&sorder=desc" rel="nofollow">age</a></span>
+ </th>
+ <th class="center"><span class="seed">
+ <a href="/search/test/?field=seeders&sorder=desc" rel="nofollow">seed</a></span>
+ </th>
+ <th class="lasttd nobr center">
+ <a href="/search/test/?field=leechers&sorder=desc" rel="nofollow">leech</a>
+ </th>
+ </tr>
+ <tr class="even" id="torrent_test6478745">
+ <td>
+ <div class="iaconbox center floatright">
+ <a rel="6478745,0" class="icommentjs icon16" href="/test-t6478745.html#comment">
+ <em style="font-size: 12px; margin: 0 4px 0 4px;" class="iconvalue">3</em>
+ <i class="ka ka-comment"></i>
+ </a>
+ <a class="iverify icon16" href="/test-t6478745.html" title="Verified Torrent">
+ <i class="ka ka16 ka-verify ka-green"></i>
+ </a>
+ <a href="#" onclick="_scq.push([]); return false;" class="partner1Button idownload icon16">
+ <i class="ka ka16 ka-arrow-down partner1Button"></i>
+ </a>
+ <a title="Torrent magnet link"
+ href="magnet:?xt=urn:btih:MAGNETURL&dn=test" class="imagnet icon16">
+ <i class="ka ka16 ka-magnet"></i>
+ </a>
+ <a title="Download torrent file"
+ href="http://torcache.net/torrent/53917.torrent?title=test" class="idownload icon16">
+ <i class="ka ka16 ka-arrow-down"></i>
+ </a>
+ </div>
+ <div class="torrentname">
+ <a href="/test-t6478745.html" class="torType txtType"></a>
+ <a href="/test-t6478745.html" class="normalgrey font12px plain bold"></a>
+ <div class="markeredBlock torType txtType">
+ <a href="/url.html" class="cellMainLink">
+ <strong class="red">This should be the title</strong>
+ </a>
+ <span class="font11px lightgrey block">
+ Posted by <i class="ka ka-verify" style="font-size: 16px;color:orange;"></i>
+ <a class="plain" href="/user/riri/">riri</a> in
+ <span id="cat_6478745">
+ <strong><a href="/other/">Other</a> > <a href="/unsorted/">Unsorted</a></strong>
+ </span>
+ </span>
+ </div>
+ </td>
+ <td class="nobr center">449 <span>bytes</span></td>
+ <td class="center">4</td>
+ <td class="center">2 years</td>
+ <td class="green center">10</td>
+ <td class="red lasttd center">1</td>
+ </tr>
+ </table>
+ """
+ response = mock.Mock(text=html)
+ results = kickass.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'This should be the title')
+ self.assertEqual(results[0]['url'], 'https://kickass.so/url.html')
+ self.assertEqual(results[0]['content'], 'Posted by riri in Other > Unsorted')
+ self.assertEqual(results[0]['seed'], 10)
+ self.assertEqual(results[0]['leech'], 1)
+ self.assertEqual(results[0]['filesize'], 449)
+ self.assertEqual(results[0]['files'], 4)
+ self.assertEqual(results[0]['magnetlink'], 'magnet:?xt=urn:btih:MAGNETURL&dn=test')
+ self.assertEqual(results[0]['torrentfile'], 'http://torcache.net/torrent/53917.torrent?title=test')
+
+ html = """
+ <table cellpadding="0" cellspacing="0" class="data" style="width: 100%">
+ <tr class="firstr">
+ <th class="width100perc nopad">torrent name</th>
+ <th class="center">
+ <a href="/search/test/?field=size&sorder=desc" rel="nofollow">size</a>
+ </th>
+ <th class="center"><span class="files">
+ <a href="/search/test/?field=files_count&sorder=desc" rel="nofollow">files</a></span>
+ </th>
+ <th class="center"><span>
+ <a href="/search/test/?field=time_add&sorder=desc" rel="nofollow">age</a></span>
+ </th>
+ <th class="center"><span class="seed">
+ <a href="/search/test/?field=seeders&sorder=desc" rel="nofollow">seed</a></span>
+ </th>
+ <th class="lasttd nobr center">
+ <a href="/search/test/?field=leechers&sorder=desc" rel="nofollow">leech</a>
+ </th>
+ </tr>
+ </table>
+ """
+ response = mock.Mock(text=html)
+ results = kickass.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
+
+ html = """
+ <table cellpadding="0" cellspacing="0" class="data" style="width: 100%">
+ <tr class="firstr">
+ <th class="width100perc nopad">torrent name</th>
+ <th class="center">
+ <a href="/search/test/?field=size&sorder=desc" rel="nofollow">size</a>
+ </th>
+ <th class="center"><span class="files">
+ <a href="/search/test/?field=files_count&sorder=desc" rel="nofollow">files</a></span>
+ </th>
+ <th class="center"><span>
+ <a href="/search/test/?field=time_add&sorder=desc" rel="nofollow">age</a></span>
+ </th>
+ <th class="center"><span class="seed">
+ <a href="/search/test/?field=seeders&sorder=desc" rel="nofollow">seed</a></span>
+ </th>
+ <th class="lasttd nobr center">
+ <a href="/search/test/?field=leechers&sorder=desc" rel="nofollow">leech</a>
+ </th>
+ </tr>
+ <tr class="even" id="torrent_test6478745">
+ <td>
+ <div class="iaconbox center floatright">
+ <a rel="6478745,0" class="icommentjs icon16" href="/test-t6478745.html#comment">
+ <em style="font-size: 12px; margin: 0 4px 0 4px;" class="iconvalue">3</em>
+ <i class="ka ka-comment"></i>
+ </a>
+ <a class="iverify icon16" href="/test-t6478745.html" title="Verified Torrent">
+ <i class="ka ka16 ka-verify ka-green"></i>
+ </a>
+ <a href="#" onclick="_scq.push([]); return false;" class="partner1Button idownload icon16">
+ <i class="ka ka16 ka-arrow-down partner1Button"></i>
+ </a>
+ <a title="Torrent magnet link"
+ href="magnet:?xt=urn:btih:MAGNETURL&dn=test" class="imagnet icon16">
+ <i class="ka ka16 ka-magnet"></i>
+ </a>
+ <a title="Download torrent file"
+ href="http://torcache.net/torrent/53917.torrent?title=test" class="idownload icon16">
+ <i class="ka ka16 ka-arrow-down"></i>
+ </a>
+ </div>
+ <div class="torrentname">
+ <a href="/test-t6478745.html" class="torType txtType"></a>
+ <a href="/test-t6478745.html" class="normalgrey font12px plain bold"></a>
+ <div class="markeredBlock torType txtType">
+ <a href="/url.html" class="cellMainLink">
+ <strong class="red">This should be the title</strong>
+ </a>
+ <span class="font11px lightgrey block">
+ Posted by <i class="ka ka-verify" style="font-size: 16px;color:orange;"></i>
+ <a class="plain" href="/user/riri/">riri</a> in
+ <span id="cat_6478745">
+ <strong><a href="/other/">Other</a> > <a href="/unsorted/">Unsorted</a></strong>
+ </span>
+ </span>
+ </div>
+ </td>
+ <td class="nobr center">1 <span>KB</span></td>
+ <td class="center">4</td>
+ <td class="center">2 years</td>
+ <td class="green center">10</td>
+ <td class="red lasttd center">1</td>
+ </tr>
+ <tr class="even" id="torrent_test6478745">
+ <td>
+ <div class="iaconbox center floatright">
+ <a rel="6478745,0" class="icommentjs icon16" href="/test-t6478745.html#comment">
+ <em style="font-size: 12px; margin: 0 4px 0 4px;" class="iconvalue">3</em>
+ <i class="ka ka-comment"></i>
+ </a>
+ <a class="iverify icon16" href="/test-t6478745.html" title="Verified Torrent">
+ <i class="ka ka16 ka-verify ka-green"></i>
+ </a>
+ <a href="#" onclick="_scq.push([]); return false;" class="partner1Button idownload icon16">
+ <i class="ka ka16 ka-arrow-down partner1Button"></i>
+ </a>
+ <a title="Torrent magnet link"
+ href="magnet:?xt=urn:btih:MAGNETURL&dn=test" class="imagnet icon16">
+ <i class="ka ka16 ka-magnet"></i>
+ </a>
+ <a title="Download torrent file"
+ href="http://torcache.net/torrent/53917.torrent?title=test" class="idownload icon16">
+ <i class="ka ka16 ka-arrow-down"></i>
+ </a>
+ </div>
+ <div class="torrentname">
+ <a href="/test-t6478745.html" class="torType txtType"></a>
+ <a href="/test-t6478745.html" class="normalgrey font12px plain bold"></a>
+ <div class="markeredBlock torType txtType">
+ <a href="/url.html" class="cellMainLink">
+ <strong class="red">This should be the title</strong>
+ </a>
+ <span class="font11px lightgrey block">
+ Posted by <i class="ka ka-verify" style="font-size: 16px;color:orange;"></i>
+ <a class="plain" href="/user/riri/">riri</a> in
+ <span id="cat_6478745">
+ <strong><a href="/other/">Other</a> > <a href="/unsorted/">Unsorted</a></strong>
+ </span>
+ </span>
+ </div>
+ </td>
+ <td class="nobr center">1 <span>MB</span></td>
+ <td class="center">4</td>
+ <td class="center">2 years</td>
+ <td class="green center">9</td>
+ <td class="red lasttd center">1</td>
+ </tr>
+ <tr class="even" id="torrent_test6478745">
+ <td>
+ <div class="iaconbox center floatright">
+ <a rel="6478745,0" class="icommentjs icon16" href="/test-t6478745.html#comment">
+ <em style="font-size: 12px; margin: 0 4px 0 4px;" class="iconvalue">3</em>
+ <i class="ka ka-comment"></i>
+ </a>
+ <a class="iverify icon16" href="/test-t6478745.html" title="Verified Torrent">
+ <i class="ka ka16 ka-verify ka-green"></i>
+ </a>
+ <a href="#" onclick="_scq.push([]); return false;" class="partner1Button idownload icon16">
+ <i class="ka ka16 ka-arrow-down partner1Button"></i>
+ </a>
+ <a title="Torrent magnet link"
+ href="magnet:?xt=urn:btih:MAGNETURL&dn=test" class="imagnet icon16">
+ <i class="ka ka16 ka-magnet"></i>
+ </a>
+ <a title="Download torrent file"
+ href="http://torcache.net/torrent/53917.torrent?title=test" class="idownload icon16">
+ <i class="ka ka16 ka-arrow-down"></i>
+ </a>
+ </div>
+ <div class="torrentname">
+ <a href="/test-t6478745.html" class="torType txtType"></a>
+ <a href="/test-t6478745.html" class="normalgrey font12px plain bold"></a>
+ <div class="markeredBlock torType txtType">
+ <a href="/url.html" class="cellMainLink">
+ <strong class="red">This should be the title</strong>
+ </a>
+ <span class="font11px lightgrey block">
+ Posted by <i class="ka ka-verify" style="font-size: 16px;color:orange;"></i>
+ <a class="plain" href="/user/riri/">riri</a> in
+ <span id="cat_6478745">
+ <strong><a href="/other/">Other</a> > <a href="/unsorted/">Unsorted</a></strong>
+ </span>
+ </span>
+ </div>
+ </td>
+ <td class="nobr center">1 <span>GB</span></td>
+ <td class="center">4</td>
+ <td class="center">2 years</td>
+ <td class="green center">8</td>
+ <td class="red lasttd center">1</td>
+ </tr>
+ <tr class="even" id="torrent_test6478745">
+ <td>
+ <div class="iaconbox center floatright">
+ <a rel="6478745,0" class="icommentjs icon16" href="/test-t6478745.html#comment">
+ <em style="font-size: 12px; margin: 0 4px 0 4px;" class="iconvalue">3</em>
+ <i class="ka ka-comment"></i>
+ </a>
+ <a class="iverify icon16" href="/test-t6478745.html" title="Verified Torrent">
+ <i class="ka ka16 ka-verify ka-green"></i>
+ </a>
+ <a href="#" onclick="_scq.push([]); return false;" class="partner1Button idownload icon16">
+ <i class="ka ka16 ka-arrow-down partner1Button"></i>
+ </a>
+ <a title="Torrent magnet link"
+ href="magnet:?xt=urn:btih:MAGNETURL&dn=test" class="imagnet icon16">
+ <i class="ka ka16 ka-magnet"></i>
+ </a>
+ <a title="Download torrent file"
+ href="http://torcache.net/torrent/53917.torrent?title=test" class="idownload icon16">
+ <i class="ka ka16 ka-arrow-down"></i>
+ </a>
+ </div>
+ <div class="torrentname">
+ <a href="/test-t6478745.html" class="torType txtType"></a>
+ <a href="/test-t6478745.html" class="normalgrey font12px plain bold"></a>
+ <div class="markeredBlock torType txtType">
+ <a href="/url.html" class="cellMainLink">
+ <strong class="red">This should be the title</strong>
+ </a>
+ <span class="font11px lightgrey block">
+ Posted by <i class="ka ka-verify" style="font-size: 16px;color:orange;"></i>
+ <a class="plain" href="/user/riri/">riri</a> in
+ <span id="cat_6478745">
+ <strong><a href="/other/">Other</a> > <a href="/unsorted/">Unsorted</a></strong>
+ </span>
+ </span>
+ </div>
+ </td>
+ <td class="nobr center">1 <span>TB</span></td>
+ <td class="center">4</td>
+ <td class="center">2 years</td>
+ <td class="green center">7</td>
+ <td class="red lasttd center">1</td>
+ </tr>
+ <tr class="even" id="torrent_test6478745">
+ <td>
+ <div class="iaconbox center floatright">
+ <a rel="6478745,0" class="icommentjs icon16" href="/test-t6478745.html#comment">
+ <em style="font-size: 12px; margin: 0 4px 0 4px;" class="iconvalue">3</em>
+ <i class="ka ka-comment"></i>
+ </a>
+ <a class="iverify icon16" href="/test-t6478745.html" title="Verified Torrent">
+ <i class="ka ka16 ka-verify ka-green"></i>
+ </a>
+ <a href="#" onclick="_scq.push([]); return false;" class="partner1Button idownload icon16">
+ <i class="ka ka16 ka-arrow-down partner1Button"></i>
+ </a>
+ <a title="Torrent magnet link"
+ href="magnet:?xt=urn:btih:MAGNETURL&dn=test" class="imagnet icon16">
+ <i class="ka ka16 ka-magnet"></i>
+ </a>
+ <a title="Download torrent file"
+ href="http://torcache.net/torrent/53917.torrent?title=test" class="idownload icon16">
+ <i class="ka ka16 ka-arrow-down"></i>
+ </a>
+ </div>
+ <div class="torrentname">
+ <a href="/test-t6478745.html" class="torType txtType"></a>
+ <a href="/test-t6478745.html" class="normalgrey font12px plain bold"></a>
+ <div class="markeredBlock torType txtType">
+ <a href="/url.html" class="cellMainLink">
+ <strong class="red">This should be the title</strong>
+ </a>
+ <span class="font11px lightgrey block">
+ Posted by <i class="ka ka-verify" style="font-size: 16px;color:orange;"></i>
+ <a class="plain" href="/user/riri/">riri</a> in
+ <span id="cat_6478745">
+ <strong><a href="/other/">Other</a> > <a href="/unsorted/">Unsorted</a></strong>
+ </span>
+ </span>
+ </div>
+ </td>
+ <td class="nobr center">z <span>bytes</span></td>
+ <td class="center">r</td>
+ <td class="center">2 years</td>
+ <td class="green center">a</td>
+ <td class="red lasttd center">t</td>
+ </tr>
+ </table>
+ """
+ response = mock.Mock(text=html)
+ results = kickass.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 5)
+ self.assertEqual(results[0]['title'], 'This should be the title')
+ self.assertEqual(results[0]['url'], 'https://kickass.so/url.html')
+ self.assertEqual(results[0]['content'], 'Posted by riri in Other > Unsorted')
+ self.assertEqual(results[0]['seed'], 10)
+ self.assertEqual(results[0]['leech'], 1)
+ self.assertEqual(results[0]['files'], 4)
+ self.assertEqual(results[0]['magnetlink'], 'magnet:?xt=urn:btih:MAGNETURL&dn=test')
+ self.assertEqual(results[0]['torrentfile'], 'http://torcache.net/torrent/53917.torrent?title=test')
+ self.assertEqual(results[0]['filesize'], 1024)
+ self.assertEqual(results[1]['filesize'], 1048576)
+ self.assertEqual(results[2]['filesize'], 1073741824)
+ self.assertEqual(results[3]['filesize'], 1099511627776)
+ self.assertEqual(results[4]['seed'], 0)
+ self.assertEqual(results[4]['leech'], 0)
+ self.assertEqual(results[4]['files'], None)
+ self.assertEqual(results[4]['filesize'], None)
diff --git a/searx/tests/engines/test_mixcloud.py b/searx/tests/engines/test_mixcloud.py
@@ -0,0 +1,67 @@
+from collections import defaultdict
+import mock
+from searx.engines import mixcloud
+from searx.testing import SearxTestCase
+
+
+class TestMixcloudEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 0
+ params = mixcloud.request(query, dicto)
+ self.assertTrue('url' in params)
+ self.assertTrue(query in params['url'])
+ self.assertTrue('mixcloud.com' in params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, mixcloud.response, None)
+ self.assertRaises(AttributeError, mixcloud.response, [])
+ self.assertRaises(AttributeError, mixcloud.response, '')
+ self.assertRaises(AttributeError, mixcloud.response, '[]')
+
+ response = mock.Mock(text='{}')
+ self.assertEqual(mixcloud.response(response), [])
+
+ response = mock.Mock(text='{"data": []}')
+ self.assertEqual(mixcloud.response(response), [])
+
+ json = """
+ {"data":[
+ {
+ "user": {
+ "url": "http://www.mixcloud.com/user/",
+ "username": "user",
+ "name": "User",
+ "key": "/user/"
+ },
+ "key": "/user/this-is-the-url/",
+ "created_time": "2014-11-14T13:30:02Z",
+ "audio_length": 3728,
+ "slug": "this-is-the-url",
+ "name": "Title of track",
+ "url": "http://www.mixcloud.com/user/this-is-the-url/",
+ "updated_time": "2014-11-14T13:14:10Z"
+ }
+ ]}
+ """
+ response = mock.Mock(text=json)
+ results = mixcloud.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'Title of track')
+ self.assertEqual(results[0]['url'], 'http://www.mixcloud.com/user/this-is-the-url/')
+ self.assertEqual(results[0]['content'], 'User')
+ self.assertTrue('http://www.mixcloud.com/user/this-is-the-url/' in results[0]['embedded'])
+
+ json = """
+ {"toto":[
+ {"id":200,"name":"Artist Name",
+ "link":"http:\/\/www.mixcloud.com\/artist\/1217","type":"artist"}
+ ]}
+ """
+ response = mock.Mock(text=json)
+ results = mixcloud.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_piratebay.py b/searx/tests/engines/test_piratebay.py
@@ -0,0 +1,137 @@
+# -*- coding: utf-8 -*-
+from collections import defaultdict
+import mock
+from searx.engines import piratebay
+from searx.testing import SearxTestCase
+
+
+class TestPiratebayEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ dicto['category'] = 'Toto'
+ params = piratebay.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('piratebay.cr', params['url'])
+ self.assertIn('0', params['url'])
+
+ dicto['category'] = 'music'
+ params = piratebay.request(query, dicto)
+ self.assertIn('100', params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, piratebay.response, None)
+ self.assertRaises(AttributeError, piratebay.response, [])
+ self.assertRaises(AttributeError, piratebay.response, '')
+ self.assertRaises(AttributeError, piratebay.response, '[]')
+
+ response = mock.Mock(text='<html></html>')
+ self.assertEqual(piratebay.response(response), [])
+
+ html = """
+ <table id="searchResult">
+ <tr>
+ </tr>
+ <tr>
+ <td class="vertTh">
+ <center>
+ <a href="#" title="More from this category">Anime</a><br/>
+ (<a href="#" title="More from this category">Anime</a>)
+ </center>
+ </td>
+ <td>
+ <div class="detName">
+ <a href="/this.is.the.link" class="detLink" title="Title">
+ This is the title
+ </a>
+ </div>
+ <a href="magnet:?xt=urn:btih:MAGNETLINK" title="Download this torrent using magnet">
+ <img src="/static/img/icon-magnet.gif" alt="Magnet link"/>
+ </a>
+ <a href="http://torcache.net/torrent/TORRENTFILE.torrent" title="Download this torrent">
+ <img src="/static/img/dl.gif" class="dl" alt="Download"/>
+ </a>
+ <a href="/user/HorribleSubs">
+ <img src="/static/img/vip.gif" alt="VIP" title="VIP" style="width:11px;" border='0'/>
+ </a>
+ <img src="/static/img/11x11p.png"/>
+ <font class="detDesc">
+ This is the content <span>and should be</span> OK
+ </font>
+ </td>
+ <td align="right">13</td>
+ <td align="right">334</td>
+ </tr>
+ </table>
+ """
+ response = mock.Mock(text=html)
+ results = piratebay.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'This is the title')
+ self.assertEqual(results[0]['url'], 'https://thepiratebay.cr/this.is.the.link')
+ self.assertEqual(results[0]['content'], 'This is the content and should be OK')
+ self.assertEqual(results[0]['seed'], 13)
+ self.assertEqual(results[0]['leech'], 334)
+ self.assertEqual(results[0]['magnetlink'], 'magnet:?xt=urn:btih:MAGNETLINK')
+ self.assertEqual(results[0]['torrentfile'], 'http://torcache.net/torrent/TORRENTFILE.torrent')
+
+ html = """
+ <table id="searchResult">
+ <tr>
+ </tr>
+ <tr>
+ <td class="vertTh">
+ <center>
+ <a href="#" title="More from this category">Anime</a><br/>
+ (<a href="#" title="More from this category">Anime</a>)
+ </center>
+ </td>
+ <td>
+ <div class="detName">
+ <a href="/this.is.the.link" class="detLink" title="Title">
+ This is the title
+ </a>
+ </div>
+ <a href="magnet:?xt=urn:btih:MAGNETLINK" title="Download this torrent using magnet">
+ <img src="/static/img/icon-magnet.gif" alt="Magnet link"/>
+ </a>
+ <a href="http://torcache.net/torrent/TORRENTFILE.torrent" title="Download this torrent">
+ <img src="/static/img/dl.gif" class="dl" alt="Download"/>
+ </a>
+ <a href="/user/HorribleSubs">
+ <img src="/static/img/vip.gif" alt="VIP" title="VIP" style="width:11px;" border='0'/>
+ </a>
+ <img src="/static/img/11x11p.png"/>
+ <font class="detDesc">
+ This is the content <span>and should be</span> OK
+ </font>
+ </td>
+ <td align="right">s</td>
+ <td align="right">d</td>
+ </tr>
+ </table>
+ """
+ response = mock.Mock(text=html)
+ results = piratebay.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'This is the title')
+ self.assertEqual(results[0]['url'], 'https://thepiratebay.cr/this.is.the.link')
+ self.assertEqual(results[0]['content'], 'This is the content and should be OK')
+ self.assertEqual(results[0]['seed'], 0)
+ self.assertEqual(results[0]['leech'], 0)
+ self.assertEqual(results[0]['magnetlink'], 'magnet:?xt=urn:btih:MAGNETLINK')
+ self.assertEqual(results[0]['torrentfile'], 'http://torcache.net/torrent/TORRENTFILE.torrent')
+
+ html = """
+ <table id="searchResult">
+ </table>
+ """
+ response = mock.Mock(text=html)
+ results = piratebay.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_searchcode_code.py b/searx/tests/engines/test_searchcode_code.py
@@ -0,0 +1,75 @@
+from collections import defaultdict
+import mock
+from searx.engines import searchcode_code
+from searx.testing import SearxTestCase
+
+
+class TestSearchcodeCodeEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 0
+ params = searchcode_code.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('searchcode.com', params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, searchcode_code.response, None)
+ self.assertRaises(AttributeError, searchcode_code.response, [])
+ self.assertRaises(AttributeError, searchcode_code.response, '')
+ self.assertRaises(AttributeError, searchcode_code.response, '[]')
+
+ response = mock.Mock(text='{}')
+ self.assertEqual(searchcode_code.response(response), [])
+
+ response = mock.Mock(text='{"data": []}')
+ self.assertEqual(searchcode_code.response(response), [])
+
+ json = """
+ {
+ "matchterm": "test",
+ "previouspage": null,
+ "searchterm": "test",
+ "query": "test",
+ "total": 1000,
+ "page": 0,
+ "nextpage": 1,
+ "results": [
+ {
+ "repo": "https://repo",
+ "linescount": 1044,
+ "location": "/tests",
+ "name": "Name",
+ "url": "https://url",
+ "md5hash": "ecac6e479edd2b9406c9e08603cec655",
+ "lines": {
+ "1": "// Test 011",
+ "2": "// Source: "
+ },
+ "id": 51223527,
+ "filename": "File.CPP"
+ }
+ ]
+ }
+ """
+ response = mock.Mock(text=json)
+ results = searchcode_code.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'Name - File.CPP')
+ self.assertEqual(results[0]['url'], 'https://url')
+ self.assertEqual(results[0]['repository'], 'https://repo')
+ self.assertEqual(results[0]['code_language'], 'cpp')
+
+ json = """
+ {"toto":[
+ {"id":200,"name":"Artist Name",
+ "link":"http:\/\/www.searchcode_code.com\/artist\/1217","type":"artist"}
+ ]}
+ """
+ response = mock.Mock(text=json)
+ results = searchcode_code.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_searchcode_doc.py b/searx/tests/engines/test_searchcode_doc.py
@@ -0,0 +1,73 @@
+from collections import defaultdict
+import mock
+from searx.engines import searchcode_doc
+from searx.testing import SearxTestCase
+
+
+class TestSearchcodeDocEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 0
+ params = searchcode_doc.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('searchcode.com', params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, searchcode_doc.response, None)
+ self.assertRaises(AttributeError, searchcode_doc.response, [])
+ self.assertRaises(AttributeError, searchcode_doc.response, '')
+ self.assertRaises(AttributeError, searchcode_doc.response, '[]')
+
+ response = mock.Mock(text='{}')
+ self.assertEqual(searchcode_doc.response(response), [])
+
+ response = mock.Mock(text='{"data": []}')
+ self.assertEqual(searchcode_doc.response(response), [])
+
+ json = """
+ {
+ "matchterm": "test",
+ "previouspage": null,
+ "searchterm": "test",
+ "query": "test",
+ "total": 60,
+ "page": 0,
+ "nextpage": 1,
+ "results": [
+ {
+ "synopsis": "Synopsis",
+ "displayname": null,
+ "name": "test",
+ "url": "http://url",
+ "type": "Type",
+ "icon": null,
+ "namespace": "Namespace",
+ "description": "Description"
+ }
+ ]
+ }
+ """
+ response = mock.Mock(text=json)
+ results = searchcode_doc.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], '[Type] Namespace test')
+ self.assertEqual(results[0]['url'], 'http://url')
+ self.assertIn('Synopsis', results[0]['content'])
+ self.assertIn('Type', results[0]['content'])
+ self.assertIn('test', results[0]['content'])
+ self.assertIn('Description', results[0]['content'])
+
+ json = """
+ {"toto":[
+ {"id":200,"name":"Artist Name",
+ "link":"http:\/\/www.searchcode_doc.com\/artist\/1217","type":"artist"}
+ ]}
+ """
+ response = mock.Mock(text=json)
+ results = searchcode_doc.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_soundcloud.py b/searx/tests/engines/test_soundcloud.py
@@ -0,0 +1,192 @@
+from collections import defaultdict
+import mock
+from searx.engines import soundcloud
+from searx.testing import SearxTestCase
+from urllib import quote_plus
+
+
+class TestSoundcloudEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ params = soundcloud.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('soundcloud.com', params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, soundcloud.response, None)
+ self.assertRaises(AttributeError, soundcloud.response, [])
+ self.assertRaises(AttributeError, soundcloud.response, '')
+ self.assertRaises(AttributeError, soundcloud.response, '[]')
+
+ response = mock.Mock(text='{}')
+ self.assertEqual(soundcloud.response(response), [])
+
+ response = mock.Mock(text='{"data": []}')
+ self.assertEqual(soundcloud.response(response), [])
+
+ json = """
+ {
+ "collection": [
+ {
+ "kind": "track",
+ "id": 159723640,
+ "created_at": "2014/07/22 00:51:21 +0000",
+ "user_id": 2976616,
+ "duration": 303780,
+ "commentable": true,
+ "state": "finished",
+ "original_content_size": 13236349,
+ "last_modified": "2015/01/31 15:14:50 +0000",
+ "sharing": "public",
+ "tag_list": "seekae flume",
+ "permalink": "seekae-test-recognise-flume-re-work",
+ "streamable": true,
+ "embeddable_by": "all",
+ "downloadable": true,
+ "purchase_url": "http://www.facebook.com/seekaemusic",
+ "label_id": null,
+ "purchase_title": "Seekae",
+ "genre": "freedownload",
+ "title": "This is the title",
+ "description": "This is the content",
+ "label_name": "Future Classic",
+ "release": "",
+ "track_type": "remix",
+ "key_signature": "",
+ "isrc": "",
+ "video_url": null,
+ "bpm": null,
+ "release_year": 2014,
+ "release_month": 7,
+ "release_day": 22,
+ "original_format": "mp3",
+ "license": "all-rights-reserved",
+ "uri": "https://api.soundcloud.com/tracks/159723640",
+ "user": {
+ "id": 2976616,
+ "kind": "user",
+ "permalink": "flume",
+ "username": "Flume",
+ "last_modified": "2014/11/24 19:21:29 +0000",
+ "uri": "https://api.soundcloud.com/users/2976616",
+ "permalink_url": "http://soundcloud.com/flume",
+ "avatar_url": "https://i1.sndcdn.com/avatars-000044475439-4zi7ii-large.jpg"
+ },
+ "permalink_url": "http://soundcloud.com/this.is.the.url",
+ "artwork_url": "https://i1.sndcdn.com/artworks-000085857162-xdxy5c-large.jpg",
+ "waveform_url": "https://w1.sndcdn.com/DWrL1lAN8BkP_m.png",
+ "stream_url": "https://api.soundcloud.com/tracks/159723640/stream",
+ "download_url": "https://api.soundcloud.com/tracks/159723640/download",
+ "playback_count": 2190687,
+ "download_count": 54856,
+ "favoritings_count": 49061,
+ "comment_count": 826,
+ "likes_count": 49061,
+ "reposts_count": 15910,
+ "attachments_uri": "https://api.soundcloud.com/tracks/159723640/attachments",
+ "policy": "ALLOW"
+ }
+ ],
+ "total_results": 375750,
+ "next_href": "https://api.soundcloud.com/search?&q=test",
+ "tx_id": ""
+ }
+ """
+ response = mock.Mock(text=json)
+ results = soundcloud.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'This is the title')
+ self.assertEqual(results[0]['url'], 'http://soundcloud.com/this.is.the.url')
+ self.assertEqual(results[0]['content'], 'This is the content')
+ self.assertIn(quote_plus('https://api.soundcloud.com/tracks/159723640'), results[0]['embedded'])
+
+ json = """
+ {
+ "collection": [
+ {
+ "kind": "user",
+ "id": 159723640,
+ "created_at": "2014/07/22 00:51:21 +0000",
+ "user_id": 2976616,
+ "duration": 303780,
+ "commentable": true,
+ "state": "finished",
+ "original_content_size": 13236349,
+ "last_modified": "2015/01/31 15:14:50 +0000",
+ "sharing": "public",
+ "tag_list": "seekae flume",
+ "permalink": "seekae-test-recognise-flume-re-work",
+ "streamable": true,
+ "embeddable_by": "all",
+ "downloadable": true,
+ "purchase_url": "http://www.facebook.com/seekaemusic",
+ "label_id": null,
+ "purchase_title": "Seekae",
+ "genre": "freedownload",
+ "title": "This is the title",
+ "description": "This is the content",
+ "label_name": "Future Classic",
+ "release": "",
+ "track_type": "remix",
+ "key_signature": "",
+ "isrc": "",
+ "video_url": null,
+ "bpm": null,
+ "release_year": 2014,
+ "release_month": 7,
+ "release_day": 22,
+ "original_format": "mp3",
+ "license": "all-rights-reserved",
+ "uri": "https://api.soundcloud.com/tracks/159723640",
+ "user": {
+ "id": 2976616,
+ "kind": "user",
+ "permalink": "flume",
+ "username": "Flume",
+ "last_modified": "2014/11/24 19:21:29 +0000",
+ "uri": "https://api.soundcloud.com/users/2976616",
+ "permalink_url": "http://soundcloud.com/flume",
+ "avatar_url": "https://i1.sndcdn.com/avatars-000044475439-4zi7ii-large.jpg"
+ },
+ "permalink_url": "http://soundcloud.com/this.is.the.url",
+ "artwork_url": "https://i1.sndcdn.com/artworks-000085857162-xdxy5c-large.jpg",
+ "waveform_url": "https://w1.sndcdn.com/DWrL1lAN8BkP_m.png",
+ "stream_url": "https://api.soundcloud.com/tracks/159723640/stream",
+ "download_url": "https://api.soundcloud.com/tracks/159723640/download",
+ "playback_count": 2190687,
+ "download_count": 54856,
+ "favoritings_count": 49061,
+ "comment_count": 826,
+ "likes_count": 49061,
+ "reposts_count": 15910,
+ "attachments_uri": "https://api.soundcloud.com/tracks/159723640/attachments",
+ "policy": "ALLOW"
+ }
+ ],
+ "total_results": 375750,
+ "next_href": "https://api.soundcloud.com/search?&q=test",
+ "tx_id": ""
+ }
+ """
+ response = mock.Mock(text=json)
+ results = soundcloud.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
+
+ json = """
+ {
+ "collection": [],
+ "total_results": 375750,
+ "next_href": "https://api.soundcloud.com/search?&q=test",
+ "tx_id": ""
+ }
+ """
+ response = mock.Mock(text=json)
+ results = soundcloud.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_stackoverflow.py b/searx/tests/engines/test_stackoverflow.py
@@ -0,0 +1,106 @@
+from collections import defaultdict
+import mock
+from searx.engines import stackoverflow
+from searx.testing import SearxTestCase
+
+
+class TestStackoverflowEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 0
+ params = stackoverflow.request(query, dicto)
+ self.assertTrue('url' in params)
+ self.assertTrue(query in params['url'])
+ self.assertTrue('stackoverflow.com' in params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, stackoverflow.response, None)
+ self.assertRaises(AttributeError, stackoverflow.response, [])
+ self.assertRaises(AttributeError, stackoverflow.response, '')
+ self.assertRaises(AttributeError, stackoverflow.response, '[]')
+
+ response = mock.Mock(text='<html></html>')
+ self.assertEqual(stackoverflow.response(response), [])
+
+ html = """
+ <div class="question-summary search-result" id="answer-id-1783426">
+ <div class="statscontainer">
+ <div class="statsarrow"></div>
+ <div class="stats">
+ <div class="vote">
+ <div class="votes answered">
+ <span class="vote-count-post "><strong>2583</strong></span>
+ <div class="viewcount">votes</div>
+ </div>
+ </div>
+ </div>
+ </div>
+ <div class="summary">
+ <div class="result-link">
+ <span>
+ <a href="/questions/this.is.the.url"
+ data-searchsession="/questions"
+ title="Checkout remote Git branch">
+ This is the title
+ </a>
+ </span>
+ </div>
+ <div class="excerpt">
+ This is the content
+ </div>
+ <div class="tags user-tags t-git t-git-checkout t-remote-branch">
+ </div>
+ <div class="started fr">
+ answered <span title="2009-11-23 14:26:08Z" class="relativetime">nov 23 '09</span> by
+ <a href="/users/214090/hallski">hallski</a>
+ </div>
+ </div>
+ </div>
+ """
+ response = mock.Mock(text=html)
+ results = stackoverflow.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'This is the title')
+ self.assertEqual(results[0]['url'], 'http://stackoverflow.com/questions/this.is.the.url')
+ self.assertEqual(results[0]['content'], 'This is the content')
+
+ html = """
+ <div class="statscontainer">
+ <div class="statsarrow"></div>
+ <div class="stats">
+ <div class="vote">
+ <div class="votes answered">
+ <span class="vote-count-post "><strong>2583</strong></span>
+ <div class="viewcount">votes</div>
+ </div>
+ </div>
+ </div>
+ </div>
+ <div class="summary">
+ <div class="result-link">
+ <span>
+ <a href="/questions/this.is.the.url"
+ data-searchsession="/questions"
+ title="Checkout remote Git branch">
+ This is the title
+ </a>
+ </span>
+ </div>
+ <div class="excerpt">
+ This is the content
+ </div>
+ <div class="tags user-tags t-git t-git-checkout t-remote-branch">
+ </div>
+ <div class="started fr">
+ answered <span title="2009-11-23 14:26:08Z" class="relativetime">nov 23 '09</span> by
+ <a href="/users/214090/hallski">hallski</a>
+ </div>
+ </div>
+ """
+ response = mock.Mock(text=html)
+ results = stackoverflow.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_vimeo.py b/searx/tests/engines/test_vimeo.py
@@ -0,0 +1,84 @@
+from collections import defaultdict
+import mock
+from searx.engines import vimeo
+from searx.testing import SearxTestCase
+
+
+class TestVimeoEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 0
+ params = vimeo.request(query, dicto)
+ self.assertTrue('url' in params)
+ self.assertTrue(query in params['url'])
+ self.assertTrue('vimeo.com' in params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, vimeo.response, None)
+ self.assertRaises(AttributeError, vimeo.response, [])
+ self.assertRaises(AttributeError, vimeo.response, '')
+ self.assertRaises(AttributeError, vimeo.response, '[]')
+
+ response = mock.Mock(text='<html></html>')
+ self.assertEqual(vimeo.response(response), [])
+
+ html = """
+ <div id="browse_content" class="" data-search-id="696d5f8366914ec4ffec33cf7652de384976d4f4">
+ <ol class="js-browse_list clearfix browse browse_videos browse_videos_thumbnails kane"
+ data-stream="c2VhcmNoOjo6ZGVzYzp7InF1ZXJ5IjoidGVzdCJ9">
+ <li id="clip_100785455" data-start-page="/search/page:1/sort:relevant/" data-position="1">
+ <a href="/videoid" title="Futurama 3d (test shot)">
+ <img src="http://image.url.webp"
+ srcset="http://i.vimeocdn.com/video/482375085_590x332.webp 2x" alt=""
+ class="thumbnail thumbnail_lg_wide">
+ <div class="data">
+ <p class="title">
+ This is the title
+ </p>
+ <p class="meta">
+ <time datetime="2014-07-15T04:16:27-04:00"
+ title="mardi 15 juillet 2014 04:16">Il y a 6 mois</time>
+ </p>
+ </div>
+ </a>
+ </li>
+ </ol>
+ </div>
+ """
+ response = mock.Mock(text=html)
+ results = vimeo.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'This is the title')
+ self.assertEqual(results[0]['url'], 'http://vimeo.com/videoid')
+ self.assertEqual(results[0]['content'], '')
+ self.assertEqual(results[0]['thumbnail'], 'http://image.url.webp')
+ self.assertIn('/videoid', results[0]['embedded'])
+
+ html = """
+ <ol class="js-browse_list clearfix browse browse_videos browse_videos_thumbnails kane"
+ data-stream="c2VhcmNoOjo6ZGVzYzp7InF1ZXJ5IjoidGVzdCJ9">
+ <li id="clip_100785455" data-start-page="/search/page:1/sort:relevant/" data-position="1">
+ <a href="/videoid" title="Futurama 3d (test shot)">
+ <img src="http://image.url.webp"
+ srcset="http://i.vimeocdn.com/video/482375085_590x332.webp 2x" alt=""
+ class="thumbnail thumbnail_lg_wide">
+ <div class="data">
+ <p class="title">
+ This is the title
+ </p>
+ <p class="meta">
+ <time datetime="2014-07-15T04:16:27-04:00"
+ title="mardi 15 juillet 2014 04:16">Il y a 6 mois</time>
+ </p>
+ </div>
+ </a>
+ </li>
+ </ol>
+ """
+ response = mock.Mock(text=html)
+ results = vimeo.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_www500px.py b/searx/tests/engines/test_www500px.py
@@ -0,0 +1,83 @@
+# -*- coding: utf-8 -*-
+from collections import defaultdict
+import mock
+from searx.engines import www500px
+from searx.testing import SearxTestCase
+
+
+class TestWww500pxImagesEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ params = www500px.request(query, dicto)
+ self.assertTrue('url' in params)
+ self.assertTrue(query in params['url'])
+ self.assertTrue('500px.com' in params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, www500px.response, None)
+ self.assertRaises(AttributeError, www500px.response, [])
+ self.assertRaises(AttributeError, www500px.response, '')
+ self.assertRaises(AttributeError, www500px.response, '[]')
+
+ response = mock.Mock(text='<html></html>')
+ self.assertEqual(www500px.response(response), [])
+
+ html = """
+ <div class="photo">
+ <a href="/this.should.be.the.url" data-ga-category="Photo Thumbnail" data-ga-action="Title">
+ <img src="https://image.url/3.jpg?v=0" />
+ </a>
+ <div class="details">
+ <div class="inside">
+ <div class="title">
+ <a href="/photo/64312705/branch-out-by-oliver-turpin?feature=">
+ This is the title
+ </a>
+ </div>
+ <div class="info">
+ <a href="/ChronicleUK" data-ga-action="Image" data-ga-category="Photo Thumbnail">
+ This is the content
+ </a>
+ </div>
+ <div class="rating">44.8</div>
+ </div>
+ </div>
+ </div>
+ """
+ response = mock.Mock(text=html)
+ results = www500px.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'This is the title')
+ self.assertEqual(results[0]['url'], 'https://500px.com/this.should.be.the.url')
+ self.assertEqual(results[0]['content'], 'This is the content')
+ self.assertEqual(results[0]['thumbnail_src'], 'https://image.url/3.jpg?v=0')
+ self.assertEqual(results[0]['img_src'], 'https://image.url/2048.jpg')
+
+ html = """
+ <a href="/this.should.be.the.url" data-ga-category="Photo Thumbnail" data-ga-action="Title">
+ <img src="https://image.url/3.jpg?v=0" />
+ </a>
+ <div class="details">
+ <div class="inside">
+ <div class="title">
+ <a href="/photo/64312705/branch-out-by-oliver-turpin?feature=">
+ This is the title
+ </a>
+ </div>
+ <div class="info">
+ <a href="/ChronicleUK" data-ga-action="Image" data-ga-category="Photo Thumbnail">
+ Oliver Turpin
+ </a>
+ </div>
+ <div class="rating">44.8</div>
+ </div>
+ </div>
+ """
+ response = mock.Mock(text=html)
+ results = www500px.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_youtube.py b/searx/tests/engines/test_youtube.py
@@ -0,0 +1,204 @@
+from collections import defaultdict
+import mock
+from searx.engines import youtube
+from searx.testing import SearxTestCase
+
+
+class TestYoutubeEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 0
+ dicto['language'] = 'fr_FR'
+ params = youtube.request(query, dicto)
+ self.assertTrue('url' in params)
+ self.assertTrue(query in params['url'])
+ self.assertTrue('youtube.com' in params['url'])
+ self.assertTrue('fr' in params['url'])
+
+ dicto['language'] = 'all'
+ params = youtube.request(query, dicto)
+ self.assertFalse('fr' in params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, youtube.response, None)
+ self.assertRaises(AttributeError, youtube.response, [])
+ self.assertRaises(AttributeError, youtube.response, '')
+ self.assertRaises(AttributeError, youtube.response, '[]')
+
+ response = mock.Mock(text='{}')
+ self.assertEqual(youtube.response(response), [])
+
+ response = mock.Mock(text='{"data": []}')
+ self.assertEqual(youtube.response(response), [])
+
+ json = """
+ {"feed":{"entry":[{
+ "id":{"$t":"http://gdata.youtube.com/feeds/api/videos/DIVZCPfAOeM"},
+ "published":{"$t":"2015-01-23T21:25:00.000Z"},
+ "updated":{"$t":"2015-01-26T14:38:15.000Z"},
+ "title":{"$t":"Title",
+ "type":"text"},"content":{"$t":"Description","type":"text"},
+ "link":[{"rel":"alternate","type":"text/html",
+ "href":"https://www.youtube.com/watch?v=DIVZCPfAOeM&feature=youtube_gdata"},
+ {"rel":"http://gdata.youtube.com/schemas/2007#video.related",
+ "type":"application/atom+xml",
+ "href":"https://gdata.youtube.com/feeds/api/videos/DIVZCPfAOeM/related"},
+ {"rel":"http://gdata.youtube.com/schemas/2007#mobile","type":"text/html",
+ "href":"https://m.youtube.com/details?v=DIVZCPfAOeM"},
+ {"rel":"self","type":"application/atom+xml",
+ "href":"https://gdata.youtube.com/feeds/api/videos/DIVZCPfAOeM"}],
+ "author":[{"name":{"$t":"Cauet"},
+ "uri":{"$t":"https://gdata.youtube.com/feeds/api/users/cauetofficiel"} }],
+ "gd$comments":{"gd$feedLink":{"rel":"http://gdata.youtube.com/schemas/2007#comments",
+ "href":"https://gdata.youtube.com/feeds/api/videos/DIVZCPfAOeM/comments",
+ "countHint":8} },
+ "media$group":{"media$category":[{"$t":"Comedy","label":"Comedy",
+ "scheme":"http://gdata.youtube.com/schemas/2007/categories.cat"}],
+ "media$content":[{"url":"https://www.youtube.com/v/DIVZCPfAOeM?version=3&f=videos&app=youtube_gdata",
+ "type":"application/x-shockwave-flash","medium":"video",
+ "isDefault":"true","expression":"full","duration":354,"yt$format":5},
+ {"url":"rtsp://r1---sn-cg07luel.c.youtube.com/CiILENy73wIaGQnjOcD3CFmFDBMYDSANFEgGUgZ2aWRlb3MM/0/0/0/video.3gp",
+ "type":"video/3gpp","medium":"video","expression":"full","duration":354,
+ "yt$format":1},
+ {"url":"rtsp://r1---sn-cg07luel.c.youtube.com/CiILENy73wIaGQnjOcD3CFmFDBMYESARFEgGUgZ2aWRlb3MM/0/0/0/video.3gp",
+ "type":"video/3gpp","medium":"video","expression":"full","duration":354,"yt$format":6}],
+ "media$description":{"$t":"Desc","type":"plain"},
+ "media$keywords":{},
+ "media$player":[{"url":"https://www.youtube.com/watch?v=DIVZCPfAOeM&feature=youtube_gdata_player"}],
+ "media$thumbnail":[{"url":"https://i.ytimg.com/vi/DIVZCPfAOeM/0.jpg",
+ "height":360,"width":480,"time":"00:02:57"},
+ {"url":"https://i.ytimg.com/vi/DIVZCPfAOeM/1.jpg","height":90,"width":120,"time":"00:01:28.500"},
+ {"url":"https://i.ytimg.com/vi/DIVZCPfAOeM/2.jpg","height":90,"width":120,"time":"00:02:57"},
+ {"url":"https://i.ytimg.com/vi/DIVZCPfAOeM/3.jpg","height":90,"width":120,"time":"00:04:25.500"}],
+ "media$title":{"$t":"Title","type":"plain"},
+ "yt$duration":{"seconds":"354"} },
+ "gd$rating":{"average":4.932159,"max":5,"min":1,"numRaters":1533,
+ "rel":"http://schemas.google.com/g/2005#overall"},
+ "yt$statistics":{"favoriteCount":"0","viewCount":"92464"} }
+ ]
+ }
+ }
+ """
+ response = mock.Mock(text=json)
+ results = youtube.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'Title')
+ self.assertEqual(results[0]['url'], 'https://www.youtube.com/watch?v=DIVZCPfAOeM')
+ self.assertEqual(results[0]['content'], 'Description')
+ self.assertEqual(results[0]['thumbnail'], 'https://i.ytimg.com/vi/DIVZCPfAOeM/0.jpg')
+ self.assertTrue('DIVZCPfAOeM' in results[0]['embedded'])
+
+ json = """
+ {"feed":{"entry":[{
+ "id":{"$t":"http://gdata.youtube.com/feeds/api/videos/DIVZCPfAOeM"},
+ "published":{"$t":"2015-01-23T21:25:00.000Z"},
+ "updated":{"$t":"2015-01-26T14:38:15.000Z"},
+ "title":{"$t":"Title",
+ "type":"text"},"content":{"$t":"Description","type":"text"},
+ "link":[{"rel":"http://gdata.youtube.com/schemas/2007#video.related",
+ "type":"application/atom+xml",
+ "href":"https://gdata.youtube.com/feeds/api/videos/DIVZCPfAOeM/related"},
+ {"rel":"self","type":"application/atom+xml",
+ "href":"https://gdata.youtube.com/feeds/api/videos/DIVZCPfAOeM"}],
+ "author":[{"name":{"$t":"Cauet"},
+ "uri":{"$t":"https://gdata.youtube.com/feeds/api/users/cauetofficiel"} }],
+ "gd$comments":{"gd$feedLink":{"rel":"http://gdata.youtube.com/schemas/2007#comments",
+ "href":"https://gdata.youtube.com/feeds/api/videos/DIVZCPfAOeM/comments",
+ "countHint":8} },
+ "media$group":{"media$category":[{"$t":"Comedy","label":"Comedy",
+ "scheme":"http://gdata.youtube.com/schemas/2007/categories.cat"}],
+ "media$content":[{"url":"https://www.youtube.com/v/DIVZCPfAOeM?version=3&f=videos&app=youtube_gdata",
+ "type":"application/x-shockwave-flash","medium":"video",
+ "isDefault":"true","expression":"full","duration":354,"yt$format":5},
+ {"url":"rtsp://r1---sn-cg07luel.c.youtube.com/CiILENy73wIaGQnjOcD3CFmFDBMYDSANFEgGUgZ2aWRlb3MM/0/0/0/video.3gp",
+ "type":"video/3gpp","medium":"video","expression":"full","duration":354,
+ "yt$format":1},
+ {"url":"rtsp://r1---sn-cg07luel.c.youtube.com/CiILENy73wIaGQnjOcD3CFmFDBMYESARFEgGUgZ2aWRlb3MM/0/0/0/video.3gp",
+ "type":"video/3gpp","medium":"video","expression":"full","duration":354,"yt$format":6}],
+ "media$description":{"$t":"Desc","type":"plain"},
+ "media$keywords":{},
+ "media$player":[{"url":"https://www.youtube.com/watch?v=DIVZCPfAOeM&feature=youtube_gdata_player"}],
+ "media$thumbnail":[{"url":"https://i.ytimg.com/vi/DIVZCPfAOeM/0.jpg",
+ "height":360,"width":480,"time":"00:02:57"},
+ {"url":"https://i.ytimg.com/vi/DIVZCPfAOeM/1.jpg","height":90,"width":120,"time":"00:01:28.500"},
+ {"url":"https://i.ytimg.com/vi/DIVZCPfAOeM/2.jpg","height":90,"width":120,"time":"00:02:57"},
+ {"url":"https://i.ytimg.com/vi/DIVZCPfAOeM/3.jpg","height":90,"width":120,"time":"00:04:25.500"}],
+ "media$title":{"$t":"Title","type":"plain"},
+ "yt$duration":{"seconds":"354"} },
+ "gd$rating":{"average":4.932159,"max":5,"min":1,"numRaters":1533,
+ "rel":"http://schemas.google.com/g/2005#overall"},
+ "yt$statistics":{"favoriteCount":"0","viewCount":"92464"} }
+ ]
+ }
+ }
+ """
+ response = mock.Mock(text=json)
+ results = youtube.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
+
+ json = """
+ {"feed":{"entry":[{
+ "id":{"$t":"http://gdata.youtube.com/feeds/api/videos/DIVZCPfAOeM"},
+ "published":{"$t":"2015-01-23T21:25:00.000Z"},
+ "updated":{"$t":"2015-01-26T14:38:15.000Z"},
+ "title":{"$t":"Title",
+ "type":"text"},"content":{"$t":"Description","type":"text"},
+ "link":[{"rel":"alternate","type":"text/html",
+ "href":"https://www.youtube.com/watch?v=DIVZCPfAOeM"},
+ {"rel":"http://gdata.youtube.com/schemas/2007#video.related",
+ "type":"application/atom+xml",
+ "href":"https://gdata.youtube.com/feeds/api/videos/DIVZCPfAOeM/related"},
+ {"rel":"http://gdata.youtube.com/schemas/2007#mobile","type":"text/html",
+ "href":"https://m.youtube.com/details?v=DIVZCPfAOeM"},
+ {"rel":"self","type":"application/atom+xml",
+ "href":"https://gdata.youtube.com/feeds/api/videos/DIVZCPfAOeM"}],
+ "author":[{"name":{"$t":"Cauet"},
+ "uri":{"$t":"https://gdata.youtube.com/feeds/api/users/cauetofficiel"} }],
+ "gd$comments":{"gd$feedLink":{"rel":"http://gdata.youtube.com/schemas/2007#comments",
+ "href":"https://gdata.youtube.com/feeds/api/videos/DIVZCPfAOeM/comments",
+ "countHint":8} },
+ "media$group":{"media$category":[{"$t":"Comedy","label":"Comedy",
+ "scheme":"http://gdata.youtube.com/schemas/2007/categories.cat"}],
+ "media$content":[{"url":"https://www.youtube.com/v/DIVZCPfAOeM?version=3&f=videos&app=youtube_gdata",
+ "type":"application/x-shockwave-flash","medium":"video",
+ "isDefault":"true","expression":"full","duration":354,"yt$format":5},
+ {"url":"rtsp://r1---sn-cg07luel.c.youtube.com/CiILENy73wIaGQnjOcD3CFmFDBMYDSANFEgGUgZ2aWRlb3MM/0/0/0/video.3gp",
+ "type":"video/3gpp","medium":"video","expression":"full","duration":354,
+ "yt$format":1},
+ {"url":"rtsp://r1---sn-cg07luel.c.youtube.com/CiILENy73wIaGQnjOcD3CFmFDBMYESARFEgGUgZ2aWRlb3MM/0/0/0/video.3gp",
+ "type":"video/3gpp","medium":"video","expression":"full","duration":354,"yt$format":6}],
+ "media$description":{"$t":"Desc","type":"plain"},
+ "media$keywords":{},
+ "media$player":[{"url":"https://www.youtube.com/watch?v=DIVZCPfAOeM&feature=youtube_gdata_player"}],
+ "media$title":{"$t":"Title","type":"plain"},
+ "yt$duration":{"seconds":"354"} },
+ "gd$rating":{"average":4.932159,"max":5,"min":1,"numRaters":1533,
+ "rel":"http://schemas.google.com/g/2005#overall"},
+ "yt$statistics":{"favoriteCount":"0","viewCount":"92464"} }
+ ]
+ }
+ }
+ """
+ response = mock.Mock(text=json)
+ results = youtube.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], 'Title')
+ self.assertEqual(results[0]['url'], 'https://www.youtube.com/watch?v=DIVZCPfAOeM')
+ self.assertEqual(results[0]['content'], 'Description')
+ self.assertEqual(results[0]['thumbnail'], '')
+ self.assertTrue('DIVZCPfAOeM' in results[0]['embedded'])
+
+ json = """
+ {"toto":{"entry":[]
+ }
+ }
+ """
+ response = mock.Mock(text=json)
+ results = youtube.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/test_engines.py b/searx/tests/test_engines.py
@@ -1,3 +1,25 @@
+from searx.tests.engines.test_bing import * # noqa
+from searx.tests.engines.test_bing_images import * # noqa
+from searx.tests.engines.test_bing_news import * # noqa
+from searx.tests.engines.test_btdigg import * # noqa
+from searx.tests.engines.test_dailymotion import * # noqa
+from searx.tests.engines.test_deezer import * # noqa
+from searx.tests.engines.test_deviantart import * # noqa
+from searx.tests.engines.test_digg import * # noqa
from searx.tests.engines.test_dummy import * # noqa
+from searx.tests.engines.test_flickr import * # noqa
+from searx.tests.engines.test_flickr_noapi import * # noqa
from searx.tests.engines.test_github import * # noqa
from searx.tests.engines.test_www1x import * # noqa
+from searx.tests.engines.test_google_images import * # noqa
+from searx.tests.engines.test_google_news import * # noqa
+from searx.tests.engines.test_kickass import * # noqa
+from searx.tests.engines.test_mixcloud import * # noqa
+from searx.tests.engines.test_piratebay import * # noqa
+from searx.tests.engines.test_searchcode_code import * # noqa
+from searx.tests.engines.test_searchcode_doc import * # noqa
+from searx.tests.engines.test_soundcloud import * # noqa
+from searx.tests.engines.test_stackoverflow import * # noqa
+from searx.tests.engines.test_vimeo import * # noqa
+from searx.tests.engines.test_www500px import * # noqa
+from searx.tests.engines.test_youtube import * # noqa
diff --git a/searx/tests/test_utils.py b/searx/tests/test_utils.py
@@ -10,6 +10,11 @@ class TestUtils(SearxTestCase):
self.assertIsNotNone(utils.gen_useragent())
self.assertTrue(utils.gen_useragent().startswith('Mozilla'))
+ def test_searx_useragent(self):
+ self.assertIsInstance(utils.searx_useragent(), str)
+ self.assertIsNotNone(utils.searx_useragent())
+ self.assertTrue(utils.searx_useragent().startswith('searx'))
+
def test_highlight_content(self):
self.assertEqual(utils.highlight_content(0, None), None)
self.assertEqual(utils.highlight_content(None, None), None)
@@ -29,6 +34,23 @@ class TestUtils(SearxTestCase):
query = 'a test'
self.assertEqual(utils.highlight_content(content, query), content)
+ def test_html_to_text(self):
+ html = """
+ <a href="/testlink" class="link_access_account">
+ <span class="toto">
+ <span>
+ <img src="test.jpg" />
+ </span>
+ </span>
+ <span class="titi">
+ Test text
+ </span>
+ </a>
+ """
+ self.assertIsInstance(utils.html_to_text(html), unicode)
+ self.assertIsNotNone(utils.html_to_text(html))
+ self.assertEqual(utils.html_to_text(html), "Test text")
+
class TestHTMLTextExtractor(SearxTestCase):
diff --git a/searx/utils.py b/searx/utils.py
@@ -115,10 +115,12 @@ class HTMLTextExtractor(HTMLParser):
self.result.append(name)
def get_text(self):
- return u''.join(self.result)
+ return u''.join(self.result).strip()
def html_to_text(html):
+ html = html.replace('\n', ' ')
+ html = ' '.join(html.split())
s = HTMLTextExtractor()
s.feed(html)
return s.get_text()
