diff --git a/searx/engines/currency_convert.py b/searx/engines/currency_convert.py
index d8841c1d..4618c82b 100644
--- a/searx/engines/currency_convert.py
+++ b/searx/engines/currency_convert.py
@@ -13,12 +13,9 @@ def request(query, params):
if not m:
# wrong query
return params
- try:
- ammount, from_currency, to_currency = m.groups()
- ammount = float(ammount)
- except:
- # wrong params
- return params
+
+ ammount, from_currency, to_currency = m.groups()
+ ammount = float(ammount)
q = (from_currency + to_currency).upper()
diff --git a/searx/engines/duckduckgo.py b/searx/engines/duckduckgo.py
index 583e33f7..e35a6334 100644
--- a/searx/engines/duckduckgo.py
+++ b/searx/engines/duckduckgo.py
@@ -15,7 +15,7 @@
from urllib import urlencode
from lxml.html import fromstring
-from searx.utils import html_to_text
+from searx.engines.xpath import extract_text
# engine dependent config
categories = ['general']
@@ -28,8 +28,8 @@ url = 'https://duckduckgo.com/html?{query}&s={offset}'
# specific xpath variables
result_xpath = '//div[@class="results_links results_links_deep web-result"]' # noqa
url_xpath = './/a[@class="large"]/@href'
-title_xpath = './/a[@class="large"]//text()'
-content_xpath = './/div[@class="snippet"]//text()'
+title_xpath = './/a[@class="large"]'
+content_xpath = './/div[@class="snippet"]'
# do search-request
@@ -64,8 +64,8 @@ def response(resp):
if not res_url:
continue
- title = html_to_text(''.join(r.xpath(title_xpath)))
- content = html_to_text(''.join(r.xpath(content_xpath)))
+ title = extract_text(r.xpath(title_xpath))
+ content = extract_text(r.xpath(content_xpath))
# append result
results.append({'title': title,
diff --git a/searx/engines/duckduckgo_definitions.py b/searx/engines/duckduckgo_definitions.py
index b66d6c0f..793e97d2 100644
--- a/searx/engines/duckduckgo_definitions.py
+++ b/searx/engines/duckduckgo_definitions.py
@@ -25,9 +25,10 @@ def request(query, params):
def response(resp):
- search_res = json.loads(resp.text)
results = []
+ search_res = json.loads(resp.text)
+
content = ''
heading = search_res.get('Heading', '')
attributes = []
@@ -68,7 +69,7 @@ def response(resp):
results.append({'title': heading, 'url': firstURL})
# related topics
- for ddg_result in search_res.get('RelatedTopics', None):
+ for ddg_result in search_res.get('RelatedTopics', []):
if 'FirstURL' in ddg_result:
suggestion = result_to_text(ddg_result.get('FirstURL', None),
ddg_result.get('Text', None),
diff --git a/searx/engines/faroo.py b/searx/engines/faroo.py
index 5360ea15..4a5e60a6 100644
--- a/searx/engines/faroo.py
+++ b/searx/engines/faroo.py
@@ -37,7 +37,7 @@ search_category = {'general': 'web',
# do search-request
def request(query, params):
- offset = (params['pageno']-1) * number_of_results + 1
+ offset = (params['pageno'] - 1) * number_of_results + 1
categorie = search_category.get(params['category'], 'web')
if params['language'] == 'all':
@@ -45,11 +45,11 @@ def request(query, params):
else:
language = params['language'].split('_')[0]
- # skip, if language is not supported
+ # if language is not supported, put it in english
if language != 'en' and\
language != 'de' and\
language != 'zh':
- return params
+ language = 'en'
params['url'] = search_url.format(offset=offset,
number_of_results=number_of_results,
@@ -69,12 +69,10 @@ def response(resp):
# HTTP-Code 401: api-key is not valide
if resp.status_code == 401:
raise Exception("API key is not valide")
- return []
# HTTP-Code 429: rate limit exceeded
if resp.status_code == 429:
raise Exception("rate limit has been exceeded!")
- return []
results = []
diff --git a/searx/engines/openstreetmap.py b/searx/engines/openstreetmap.py
index 68446ef5..60c3c13c 100644
--- a/searx/engines/openstreetmap.py
+++ b/searx/engines/openstreetmap.py
@@ -38,6 +38,9 @@ def response(resp):
# parse results
for r in json:
+ if 'display_name' not in r:
+ continue
+
title = r['display_name']
osm_type = r.get('osm_type', r.get('type'))
url = result_base_url.format(osm_type=osm_type,
@@ -49,10 +52,8 @@ def response(resp):
geojson = r.get('geojson')
# if no geojson is found and osm_type is a node, add geojson Point
- if not geojson and\
- osm_type == 'node':
- geojson = {u'type': u'Point',
- u'coordinates': [r['lon'], r['lat']]}
+ if not geojson and osm_type == 'node':
+ geojson = {u'type': u'Point', u'coordinates': [r['lon'], r['lat']]}
address_raw = r.get('address')
address = {}
diff --git a/searx/engines/photon.py b/searx/engines/photon.py
index 16340d24..a9c558c4 100644
--- a/searx/engines/photon.py
+++ b/searx/engines/photon.py
@@ -61,7 +61,7 @@ def response(resp):
continue
# get title
- title = properties['name']
+ title = properties.get('name')
# get osm-type
if properties.get('osm_type') == 'N':
diff --git a/searx/engines/startpage.py b/searx/engines/startpage.py
index d60ecd97..9d5b4bef 100644
--- a/searx/engines/startpage.py
+++ b/searx/engines/startpage.py
@@ -13,6 +13,7 @@
from lxml import html
from cgi import escape
import re
+from searx.engines.xpath import extract_text
# engine dependent config
categories = ['general']
@@ -45,8 +46,7 @@ def request(query, params):
# set language if specified
if params['language'] != 'all':
- params['data']['with_language'] = ('lang_' +
- params['language'].split('_')[0])
+ params['data']['with_language'] = ('lang_' + params['language'].split('_')[0])
return params
@@ -64,18 +64,15 @@ def response(resp):
continue
link = links[0]
url = link.attrib.get('href')
- try:
- title = escape(link.text_content())
- except UnicodeDecodeError:
- continue
# block google-ad url's
if re.match("^http(s|)://www.google.[a-z]+/aclk.*$", url):
continue
+ title = escape(extract_text(link))
+
if result.xpath('./p[@class="desc"]'):
- content = escape(result.xpath('./p[@class="desc"]')[0]
- .text_content())
+ content = escape(extract_text(result.xpath('./p[@class="desc"]')))
else:
content = ''
diff --git a/searx/engines/subtitleseeker.py b/searx/engines/subtitleseeker.py
index 9aaf1947..acefe30e 100644
--- a/searx/engines/subtitleseeker.py
+++ b/searx/engines/subtitleseeker.py
@@ -12,6 +12,7 @@ from cgi import escape
from urllib import quote_plus
from lxml import html
from searx.languages import language_codes
+from searx.engines.xpath import extract_text
# engine dependent config
categories = ['videos']
@@ -20,7 +21,7 @@ language = ""
# search-url
url = 'http://www.subtitleseeker.com/'
-search_url = url+'search/TITLES/{query}&p={pageno}'
+search_url = url + 'search/TITLES/{query}&p={pageno}'
# specific xpath variables
results_xpath = '//div[@class="boxRows"]'
@@ -44,7 +45,7 @@ def response(resp):
if resp.search_params['language'] != 'all':
search_lang = [lc[1]
for lc in language_codes
- if lc[0][:2] == resp.search_params['language']][0]
+ if lc[0][:2] == resp.search_params['language'].split('_')[0]][0]
# parse results
for result in dom.xpath(results_xpath):
@@ -56,17 +57,17 @@ def response(resp):
elif search_lang:
href = href + search_lang + '/'
- title = escape(link.xpath(".//text()")[0])
+ title = escape(extract_text(link))
- content = result.xpath('.//div[contains(@class,"red")]//text()')[0]
+ content = extract_text(result.xpath('.//div[contains(@class,"red")]'))
content = content + " - "
- text = result.xpath('.//div[contains(@class,"grey-web")]')[0]
- content = content + html.tostring(text, method='text')
+ text = extract_text(result.xpath('.//div[contains(@class,"grey-web")]')[0])
+ content = content + text
if result.xpath(".//span") != []:
content = content +\
" - (" +\
- result.xpath(".//span//text()")[0].strip() +\
+ extract_text(result.xpath(".//span")) +\
")"
# append result
diff --git a/searx/engines/twitter.py b/searx/engines/twitter.py
index bd9a8c2f..0e35e618 100644
--- a/searx/engines/twitter.py
+++ b/searx/engines/twitter.py
@@ -13,8 +13,8 @@
from urlparse import urljoin
from urllib import urlencode
from lxml import html
-from cgi import escape
from datetime import datetime
+from searx.engines.xpath import extract_text
# engine dependent config
categories = ['social media']
@@ -22,12 +22,12 @@ language_support = True
# search-url
base_url = 'https://twitter.com/'
-search_url = base_url+'search?'
+search_url = base_url + 'search?'
# specific xpath variables
results_xpath = '//li[@data-item-type="tweet"]'
link_xpath = './/small[@class="time"]//a'
-title_xpath = './/span[@class="username js-action-profile-name"]//text()'
+title_xpath = './/span[@class="username js-action-profile-name"]'
content_xpath = './/p[@class="js-tweet-text tweet-text"]'
timestamp_xpath = './/span[contains(@class,"_timestamp")]'
@@ -39,6 +39,8 @@ def request(query, params):
# set language if specified
if params['language'] != 'all':
params['cookies']['lang'] = params['language'].split('_')[0]
+ else:
+ params['cookies']['lang'] = 'en'
return params
@@ -53,8 +55,9 @@ def response(resp):
for tweet in dom.xpath(results_xpath):
link = tweet.xpath(link_xpath)[0]
url = urljoin(base_url, link.attrib.get('href'))
- title = ''.join(tweet.xpath(title_xpath))
- content = escape(html.tostring(tweet.xpath(content_xpath)[0], method='text', encoding='UTF-8').decode("utf-8"))
+ title = extract_text(tweet.xpath(title_xpath))
+ content = extract_text(tweet.xpath(content_xpath)[0])
+
pubdate = tweet.xpath(timestamp_xpath)
if len(pubdate) > 0:
timestamp = float(pubdate[0].attrib.get('data-time'))
diff --git a/searx/engines/yacy.py b/searx/engines/yacy.py
index 17e2a7aa..3d26c9cc 100644
--- a/searx/engines/yacy.py
+++ b/searx/engines/yacy.py
@@ -25,10 +25,10 @@ number_of_results = 5
# search-url
base_url = 'http://localhost:8090'
search_url = '/yacysearch.json?{query}'\
- '&startRecord={offset}'\
- '&maximumRecords={limit}'\
- '&contentdom={search_type}'\
- '&resource=global' # noqa
+ '&startRecord={offset}'\
+ '&maximumRecords={limit}'\
+ '&contentdom={search_type}'\
+ '&resource=global'
# yacy specific type-definitions
search_types = {'general': 'text',
@@ -41,7 +41,7 @@ search_types = {'general': 'text',
# do search-request
def request(query, params):
offset = (params['pageno'] - 1) * number_of_results
- search_type = search_types.get(params['category'], '0')
+ search_type = search_types.get(params.get('category'), '0')
params['url'] = base_url +\
search_url.format(query=urlencode({'query': query}),
@@ -66,9 +66,12 @@ def response(resp):
if not raw_search_results:
return []
- search_results = raw_search_results.get('channels', {})[0].get('items', [])
+ search_results = raw_search_results.get('channels', [])
- for result in search_results:
+ if len(search_results) == 0:
+ return []
+
+ for result in search_results[0].get('items', []):
# parse image results
if result.get('image'):
# append result
@@ -88,7 +91,7 @@ def response(resp):
'content': result['description'],
'publishedDate': publishedDate})
- #TODO parse video, audio and file results
+ # TODO parse video, audio and file results
# return results
return results
diff --git a/searx/engines/yahoo.py b/searx/engines/yahoo.py
index c6c5b0d0..161f7513 100644
--- a/searx/engines/yahoo.py
+++ b/searx/engines/yahoo.py
@@ -35,7 +35,7 @@ suggestion_xpath = '//div[@id="satat"]//a'
def parse_url(url_string):
endings = ['/RS', '/RK']
endpositions = []
- start = url_string.find('http', url_string.find('/RU=')+1)
+ start = url_string.find('http', url_string.find('/RU=') + 1)
for ending in endings:
endpos = url_string.rfind(ending)
@@ -91,7 +91,7 @@ def response(resp):
'content': content})
# if no suggestion found, return results
- if not suggestion_xpath:
+ if not dom.xpath(suggestion_xpath):
return results
# parse suggestion
diff --git a/searx/tests/engines/test_currency_convert.py b/searx/tests/engines/test_currency_convert.py
new file mode 100644
index 00000000..271ed03a
--- /dev/null
+++ b/searx/tests/engines/test_currency_convert.py
@@ -0,0 +1,44 @@
+from collections import defaultdict
+from datetime import datetime
+import mock
+from searx.engines import currency_convert
+from searx.testing import SearxTestCase
+
+
+class TestCurrencyConvertEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ params = currency_convert.request(query, dicto)
+ self.assertNotIn('url', params)
+
+ query = '1.1.1 EUR in USD'
+ params = currency_convert.request(query, dicto)
+ self.assertNotIn('url', params)
+
+ query = '10 eur in usd'
+ params = currency_convert.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn('finance.yahoo.com', params['url'])
+ self.assertIn('EUR', params['url'])
+ self.assertIn('USD', params['url'])
+
+ def test_response(self):
+ dicto = defaultdict(dict)
+ dicto['ammount'] = 10
+ dicto['from'] = "EUR"
+ dicto['to'] = "USD"
+ response = mock.Mock(text='a,b,c,d', search_params=dicto)
+ self.assertEqual(currency_convert.response(response), [])
+
+ csv = "2,0.5,1"
+ response = mock.Mock(text=csv, search_params=dicto)
+ results = currency_convert.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['answer'], '10 EUR = 5.0 USD (1 EUR = 0.5 USD)')
+ now_date = datetime.now().strftime('%Y%m%d')
+ self.assertEqual(results[0]['url'], 'http://finance.yahoo.com/currency/converter-results/' +
+ now_date + '/10-eur-to-usd.html')
diff --git a/searx/tests/engines/test_duckduckgo.py b/searx/tests/engines/test_duckduckgo.py
new file mode 100644
index 00000000..6f085cbc
--- /dev/null
+++ b/searx/tests/engines/test_duckduckgo.py
@@ -0,0 +1,90 @@
+from collections import defaultdict
+import mock
+from searx.engines import duckduckgo
+from searx.testing import SearxTestCase
+
+
+class TestDuckduckgoEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ dicto['language'] = 'fr_FR'
+ params = duckduckgo.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('duckduckgo.com', params['url'])
+ self.assertIn('fr-fr', params['url'])
+
+ dicto['language'] = 'all'
+ params = duckduckgo.request(query, dicto)
+ self.assertIn('en-us', params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, duckduckgo.response, None)
+ self.assertRaises(AttributeError, duckduckgo.response, [])
+ self.assertRaises(AttributeError, duckduckgo.response, '')
+ self.assertRaises(AttributeError, duckduckgo.response, '[]')
+
+ response = mock.Mock(text='')
+ self.assertEqual(duckduckgo.response(response), [])
+
+ html = """
+
+ """
+ response = mock.Mock(text=html)
+ results = duckduckgo.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.should.be.the.link/')
+ self.assertEqual(results[0]['content'], 'This should be the content.')
+
+ html = """
+
+
+
+
+
This should be the content.
+
+ http://this.should.be.the.link/
+
+
+
+
+ """
+ response = mock.Mock(text=html)
+ results = duckduckgo.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_duckduckgo_definitions.py b/searx/tests/engines/test_duckduckgo_definitions.py
new file mode 100644
index 00000000..71c84235
--- /dev/null
+++ b/searx/tests/engines/test_duckduckgo_definitions.py
@@ -0,0 +1,250 @@
+from collections import defaultdict
+import mock
+from searx.engines import duckduckgo_definitions
+from searx.testing import SearxTestCase
+
+
+class TestDDGDefinitionsEngine(SearxTestCase):
+
+ def test_result_to_text(self):
+ url = ''
+ text = 'Text'
+ html_result = 'Html'
+ result = duckduckgo_definitions.result_to_text(url, text, html_result)
+ self.assertEqual(result, text)
+
+ html_result = 'Text in link'
+ result = duckduckgo_definitions.result_to_text(url, text, html_result)
+ self.assertEqual(result, 'Text in link')
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ params = duckduckgo_definitions.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('duckduckgo.com', params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, duckduckgo_definitions.response, None)
+ self.assertRaises(AttributeError, duckduckgo_definitions.response, [])
+ self.assertRaises(AttributeError, duckduckgo_definitions.response, '')
+ self.assertRaises(AttributeError, duckduckgo_definitions.response, '[]')
+
+ response = mock.Mock(text='{}')
+ self.assertEqual(duckduckgo_definitions.response(response), [])
+
+ response = mock.Mock(text='{"data": []}')
+ self.assertEqual(duckduckgo_definitions.response(response), [])
+
+ json = """
+ {
+ "DefinitionSource": "definition source",
+ "Heading": "heading",
+ "ImageWidth": 0,
+ "RelatedTopics": [
+ {
+ "Result": "Top-level domains",
+ "Icon": {
+ "URL": "",
+ "Height": "",
+ "Width": ""
+ },
+ "FirstURL": "https://first.url",
+ "Text": "text"
+ },
+ {
+ "Topics": [
+ {
+ "Result": "result topic",
+ "Icon": {
+ "URL": "",
+ "Height": "",
+ "Width": ""
+ },
+ "FirstURL": "https://duckduckgo.com/?q=2%2F2",
+ "Text": "result topic text"
+ }
+ ],
+ "Name": "name"
+ }
+ ],
+ "Entity": "Entity",
+ "Type": "A",
+ "Redirect": "",
+ "DefinitionURL": "http://definition.url",
+ "AbstractURL": "https://abstract.url",
+ "Definition": "this is the definition",
+ "AbstractSource": "abstract source",
+ "Infobox": {
+ "content": [
+ {
+ "data_type": "string",
+ "value": "1999",
+ "label": "Introduced",
+ "wiki_order": 0
+ }
+ ],
+ "meta": [
+ {
+ "data_type": "string",
+ "value": ".test",
+ "label": "article_title"
+ }
+ ]
+ },
+ "Image": "image.png",
+ "ImageIsLogo": 0,
+ "Abstract": "abstract",
+ "AbstractText": "abstract text",
+ "AnswerType": "",
+ "ImageHeight": 0,
+ "Results": [{
+ "Result" : "result title",
+ "Icon" : {
+ "URL" : "result url",
+ "Height" : 16,
+ "Width" : 16
+ },
+ "FirstURL" : "result first url",
+ "Text" : "result text"
+ }
+ ],
+ "Answer": "answer"
+ }
+ """
+ response = mock.Mock(text=json)
+ results = duckduckgo_definitions.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 4)
+ self.assertEqual(results[0]['answer'], 'answer')
+ self.assertEqual(results[1]['title'], 'heading')
+ self.assertEqual(results[1]['url'], 'result first url')
+ self.assertEqual(results[2]['suggestion'], 'text')
+ self.assertEqual(results[3]['infobox'], 'heading')
+ self.assertEqual(results[3]['id'], 'http://definition.url')
+ self.assertEqual(results[3]['entity'], 'Entity')
+ self.assertIn('abstract', results[3]['content'])
+ self.assertIn('this is the definition', results[3]['content'])
+ self.assertEqual(results[3]['img_src'], 'image.png')
+ self.assertIn('Introduced', results[3]['attributes'][0]['label'])
+ self.assertIn('1999', results[3]['attributes'][0]['value'])
+ self.assertIn({'url': 'https://abstract.url', 'title': 'abstract source'}, results[3]['urls'])
+ self.assertIn({'url': 'http://definition.url', 'title': 'definition source'}, results[3]['urls'])
+ self.assertIn({'name': 'name', 'suggestions': ['result topic text']}, results[3]['relatedTopics'])
+
+ json = """
+ {
+ "DefinitionSource": "definition source",
+ "Heading": "heading",
+ "ImageWidth": 0,
+ "RelatedTopics": [],
+ "Entity": "Entity",
+ "Type": "A",
+ "Redirect": "",
+ "DefinitionURL": "",
+ "AbstractURL": "https://abstract.url",
+ "Definition": "",
+ "AbstractSource": "abstract source",
+ "Image": "",
+ "ImageIsLogo": 0,
+ "Abstract": "",
+ "AbstractText": "abstract text",
+ "AnswerType": "",
+ "ImageHeight": 0,
+ "Results": [],
+ "Answer": ""
+ }
+ """
+ response = mock.Mock(text=json)
+ results = duckduckgo_definitions.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['url'], 'https://abstract.url')
+ self.assertEqual(results[0]['title'], 'heading')
+ self.assertEqual(results[0]['content'], '')
+
+ json = """
+ {
+ "DefinitionSource": "definition source",
+ "Heading": "heading",
+ "ImageWidth": 0,
+ "RelatedTopics": [
+ {
+ "Result": "Top-level domains",
+ "Icon": {
+ "URL": "",
+ "Height": "",
+ "Width": ""
+ },
+ "FirstURL": "https://first.url",
+ "Text": "heading"
+ },
+ {
+ "Name": "name"
+ },
+ {
+ "Topics": [
+ {
+ "Result": "result topic",
+ "Icon": {
+ "URL": "",
+ "Height": "",
+ "Width": ""
+ },
+ "FirstURL": "https://duckduckgo.com/?q=2%2F2",
+ "Text": "heading"
+ }
+ ],
+ "Name": "name"
+ }
+ ],
+ "Entity": "Entity",
+ "Type": "A",
+ "Redirect": "",
+ "DefinitionURL": "http://definition.url",
+ "AbstractURL": "https://abstract.url",
+ "Definition": "this is the definition",
+ "AbstractSource": "abstract source",
+ "Infobox": {
+ "meta": [
+ {
+ "data_type": "string",
+ "value": ".test",
+ "label": "article_title"
+ }
+ ]
+ },
+ "Image": "image.png",
+ "ImageIsLogo": 0,
+ "Abstract": "abstract",
+ "AbstractText": "abstract text",
+ "AnswerType": "",
+ "ImageHeight": 0,
+ "Results": [{
+ "Result" : "result title",
+ "Icon" : {
+ "URL" : "result url",
+ "Height" : 16,
+ "Width" : 16
+ },
+ "Text" : "result text"
+ }
+ ],
+ "Answer": ""
+ }
+ """
+ response = mock.Mock(text=json)
+ results = duckduckgo_definitions.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['infobox'], 'heading')
+ self.assertEqual(results[0]['id'], 'http://definition.url')
+ self.assertEqual(results[0]['entity'], 'Entity')
+ self.assertIn('abstract', results[0]['content'])
+ self.assertIn('this is the definition', results[0]['content'])
+ self.assertEqual(results[0]['img_src'], 'image.png')
+ self.assertIn({'url': 'https://abstract.url', 'title': 'abstract source'}, results[0]['urls'])
+ self.assertIn({'url': 'http://definition.url', 'title': 'definition source'}, results[0]['urls'])
+ self.assertIn({'name': 'name', 'suggestions': []}, results[0]['relatedTopics'])
diff --git a/searx/tests/engines/test_faroo.py b/searx/tests/engines/test_faroo.py
new file mode 100644
index 00000000..acebdda8
--- /dev/null
+++ b/searx/tests/engines/test_faroo.py
@@ -0,0 +1,116 @@
+# -*- coding: utf-8 -*-
+from collections import defaultdict
+import mock
+from searx.engines import faroo
+from searx.testing import SearxTestCase
+
+
+class TestFarooEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ dicto['language'] = 'fr_FR'
+ dicto['category'] = 'general'
+ params = faroo.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('faroo.com', params['url'])
+ self.assertIn('en', params['url'])
+ self.assertIn('web', params['url'])
+
+ dicto['language'] = 'all'
+ params = faroo.request(query, dicto)
+ self.assertIn('en', params['url'])
+
+ dicto['language'] = 'de_DE'
+ params = faroo.request(query, dicto)
+ self.assertIn('de', params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, faroo.response, None)
+ self.assertRaises(AttributeError, faroo.response, [])
+ self.assertRaises(AttributeError, faroo.response, '')
+ self.assertRaises(AttributeError, faroo.response, '[]')
+
+ response = mock.Mock(text='{}')
+ self.assertEqual(faroo.response(response), [])
+
+ response = mock.Mock(text='{"data": []}')
+ self.assertEqual(faroo.response(response), [])
+
+ response = mock.Mock(text='{"data": []}', status_code=401)
+ self.assertRaises(Exception, faroo.response, response)
+
+ response = mock.Mock(text='{"data": []}', status_code=429)
+ self.assertRaises(Exception, faroo.response, response)
+
+ json = """
+ {
+ "results": [
+ {
+ "title": "This is the title",
+ "kwic": "This is the content",
+ "content": "",
+ "url": "http://this.is.the.url/",
+ "iurl": "",
+ "domain": "css3test.com",
+ "author": "Jim Dalrymple",
+ "news": true,
+ "votes": "10",
+ "date": 1360622563000,
+ "related": []
+ },
+ {
+ "title": "This is the title2",
+ "kwic": "This is the content2",
+ "content": "",
+ "url": "http://this.is.the.url2/",
+ "iurl": "",
+ "domain": "css3test.com",
+ "author": "Jim Dalrymple",
+ "news": false,
+ "votes": "10",
+ "related": []
+ },
+ {
+ "title": "This is the title3",
+ "kwic": "This is the content3",
+ "content": "",
+ "url": "http://this.is.the.url3/",
+ "iurl": "http://upload.wikimedia.org/optimized.jpg",
+ "domain": "css3test.com",
+ "author": "Jim Dalrymple",
+ "news": false,
+ "votes": "10",
+ "related": []
+ }
+ ],
+ "query": "test",
+ "suggestions": [],
+ "count": 100,
+ "start": 1,
+ "length": 10,
+ "time": "15"
+ }
+ """
+ response = mock.Mock(text=json)
+ results = faroo.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 4)
+ 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')
+ self.assertEqual(results[1]['title'], 'This is the title2')
+ self.assertEqual(results[1]['url'], 'http://this.is.the.url2/')
+ self.assertEqual(results[1]['content'], 'This is the content2')
+ self.assertEqual(results[3]['img_src'], 'http://upload.wikimedia.org/optimized.jpg')
+
+ json = """
+ {}
+ """
+ response = mock.Mock(text=json)
+ results = faroo.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_google.py b/searx/tests/engines/test_google.py
new file mode 100644
index 00000000..2c3d8e5f
--- /dev/null
+++ b/searx/tests/engines/test_google.py
@@ -0,0 +1,162 @@
+# -*- coding: utf-8 -*-
+from collections import defaultdict
+import mock
+import lxml
+from searx.engines import google
+from searx.testing import SearxTestCase
+
+
+class TestGoogleEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ dicto['language'] = 'fr_FR'
+ params = google.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('google.com', params['url'])
+ self.assertIn('PREF', params['cookies'])
+ self.assertIn('fr', params['headers']['Accept-Language'])
+
+ dicto['language'] = 'all'
+ params = google.request(query, dicto)
+ self.assertIn('en', params['headers']['Accept-Language'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, google.response, None)
+ self.assertRaises(AttributeError, google.response, [])
+ self.assertRaises(AttributeError, google.response, '')
+ self.assertRaises(AttributeError, google.response, '[]')
+
+ response = mock.Mock(text='')
+ self.assertEqual(google.response(response), [])
+
+ html = """
+
+
+
+
+
+ test.psychologies.com/
+
+
+
+
+ This should be the content.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ suggestion title
+
+
+ """
+ response = mock.Mock(text=html)
+ results = google.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 2)
+ self.assertEqual(results[0]['title'], 'This is the title')
+ self.assertEqual(results[0]['url'], 'http://this.should.be.the.link/')
+ self.assertEqual(results[0]['content'], 'This should be the content.')
+ self.assertEqual(results[1]['suggestion'], 'suggestion title')
+
+ html = """
+
+
+ """
+ response = mock.Mock(text=html)
+ results = google.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
+
+ def test_parse_images(self):
+ html = """
+
+
+
+ """
+ dom = lxml.html.fromstring(html)
+ results = google.parse_images(dom)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['url'], 'http://this.is.the.url/')
+ self.assertEqual(results[0]['title'], '')
+ self.assertEqual(results[0]['content'], '')
+ self.assertEqual(results[0]['img_src'], 'https://this.is.the.image/image.jpg')
diff --git a/searx/tests/engines/test_mediawiki.py b/searx/tests/engines/test_mediawiki.py
new file mode 100644
index 00000000..63f7da6b
--- /dev/null
+++ b/searx/tests/engines/test_mediawiki.py
@@ -0,0 +1,130 @@
+# -*- coding: utf-8 -*-
+from collections import defaultdict
+import mock
+from searx.engines import mediawiki
+from searx.testing import SearxTestCase
+
+
+class TestMediawikiEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ dicto['language'] = 'fr_FR'
+ params = mediawiki.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('wikipedia.org', params['url'])
+ self.assertIn('fr', params['url'])
+
+ dicto['language'] = 'all'
+ params = mediawiki.request(query, dicto)
+ self.assertIn('en', params['url'])
+
+ mediawiki.base_url = "http://test.url/"
+ mediawiki.search_url = mediawiki.base_url +\
+ 'w/api.php?action=query'\
+ '&list=search'\
+ '&{query}'\
+ '&srprop=timestamp'\
+ '&format=json'\
+ '&sroffset={offset}'\
+ '&srlimit={limit}' # noqa
+ params = mediawiki.request(query, dicto)
+ self.assertIn('test.url', params['url'])
+
+ def test_response(self):
+ dicto = defaultdict(dict)
+ dicto['language'] = 'fr'
+ mediawiki.base_url = "https://{language}.wikipedia.org/"
+
+ self.assertRaises(AttributeError, mediawiki.response, None)
+ self.assertRaises(AttributeError, mediawiki.response, [])
+ self.assertRaises(AttributeError, mediawiki.response, '')
+ self.assertRaises(AttributeError, mediawiki.response, '[]')
+
+ response = mock.Mock(text='{}', search_params=dicto)
+ self.assertEqual(mediawiki.response(response), [])
+
+ response = mock.Mock(text='{"data": []}', search_params=dicto)
+ self.assertEqual(mediawiki.response(response), [])
+
+ json = """
+ {
+ "query-continue": {
+ "search": {
+ "sroffset": 1
+ }
+ },
+ "query": {
+ "searchinfo": {
+ "totalhits": 29721
+ },
+ "search": [
+ {
+ "ns": 0,
+ "title": "This is the title étude",
+ "timestamp": "2014-12-19T17:42:52Z"
+ }
+ ]
+ }
+ }
+ """
+ response = mock.Mock(text=json, search_params=dicto)
+ results = mediawiki.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], u'This is the title étude')
+ self.assertIn('fr.wikipedia.org', results[0]['url'])
+ self.assertIn('This_is_the_title', results[0]['url'])
+ self.assertIn('%C3%A9tude', results[0]['url'])
+ self.assertEqual(results[0]['content'], '')
+
+ json = """
+ {
+ "query-continue": {
+ "search": {
+ "sroffset": 1
+ }
+ },
+ "query": {
+ "searchinfo": {
+ "totalhits": 29721
+ },
+ "search": [
+ ]
+ }
+ }
+ """
+ response = mock.Mock(text=json, search_params=dicto)
+ results = mediawiki.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
+
+ json = """
+ {
+ "query-continue": {
+ "search": {
+ "sroffset": 1
+ }
+ },
+ "query": {
+ }
+ }
+ """
+ response = mock.Mock(text=json, search_params=dicto)
+ results = mediawiki.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
+
+ json = """
+ {"toto":[
+ {"id":200,"name":"Artist Name",
+ "link":"http:\/\/www.mediawiki.com\/artist\/1217","type":"artist"}
+ ]}
+ """
+ response = mock.Mock(text=json, search_params=dicto)
+ results = mediawiki.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_openstreetmap.py b/searx/tests/engines/test_openstreetmap.py
new file mode 100644
index 00000000..7b7783f0
--- /dev/null
+++ b/searx/tests/engines/test_openstreetmap.py
@@ -0,0 +1,199 @@
+# -*- coding: utf-8 -*-
+from collections import defaultdict
+import mock
+from searx.engines import openstreetmap
+from searx.testing import SearxTestCase
+
+
+class TestOpenstreetmapEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ params = openstreetmap.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('openstreetmap.org', params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, openstreetmap.response, None)
+ self.assertRaises(AttributeError, openstreetmap.response, [])
+ self.assertRaises(AttributeError, openstreetmap.response, '')
+ self.assertRaises(AttributeError, openstreetmap.response, '[]')
+
+ response = mock.Mock(text='{}')
+ self.assertEqual(openstreetmap.response(response), [])
+
+ response = mock.Mock(text='{"data": []}')
+ self.assertEqual(openstreetmap.response(response), [])
+
+ json = """
+ [
+ {
+ "place_id": "127732055",
+ "licence": "Data © OpenStreetMap contributors, ODbL 1.0. http://www.openstreetmap.org/copyright",
+ "osm_type": "relation",
+ "osm_id": "7444",
+ "boundingbox": [
+ "48.8155755",
+ "48.902156",
+ "2.224122",
+ "2.4697602"
+ ],
+ "lat": "48.8565056",
+ "lon": "2.3521334",
+ "display_name": "This is the title",
+ "class": "place",
+ "type": "city",
+ "importance": 0.96893459932191,
+ "icon": "https://nominatim.openstreetmap.org/images/mapicons/poi_place_city.p.20.png",
+ "address": {
+ "city": "Paris",
+ "county": "Paris",
+ "state": "Île-de-France",
+ "country": "France",
+ "country_code": "fr"
+ },
+ "geojson": {
+ "type": "Polygon",
+ "coordinates": [
+ [
+ [
+ 2.224122,
+ 48.854199
+ ]
+ ]
+ ]
+ }
+ }
+ ]
+ """
+ response = mock.Mock(text=json)
+ results = openstreetmap.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://openstreetmap.org/relation/7444')
+ self.assertIn('coordinates', results[0]['geojson'])
+ self.assertEqual(results[0]['geojson']['coordinates'][0][0][0], 2.224122)
+ self.assertEqual(results[0]['geojson']['coordinates'][0][0][1], 48.854199)
+ self.assertEqual(results[0]['address'], None)
+ self.assertIn('48.8155755', results[0]['boundingbox'])
+ self.assertIn('48.902156', results[0]['boundingbox'])
+ self.assertIn('2.224122', results[0]['boundingbox'])
+ self.assertIn('2.4697602', results[0]['boundingbox'])
+
+ json = """
+ [
+ {
+ "place_id": "127732055",
+ "licence": "Data © OpenStreetMap contributors, ODbL 1.0. http://www.openstreetmap.org/copyright",
+ "osm_type": "relation",
+ "osm_id": "7444",
+ "boundingbox": [
+ "48.8155755",
+ "48.902156",
+ "2.224122",
+ "2.4697602"
+ ],
+ "lat": "48.8565056",
+ "lon": "2.3521334",
+ "display_name": "This is the title",
+ "class": "tourism",
+ "type": "city",
+ "importance": 0.96893459932191,
+ "icon": "https://nominatim.openstreetmap.org/images/mapicons/poi_place_city.p.20.png",
+ "address": {
+ "city": "Paris",
+ "county": "Paris",
+ "state": "Île-de-France",
+ "country": "France",
+ "country_code": "fr",
+ "address29": "Address"
+ },
+ "geojson": {
+ "type": "Polygon",
+ "coordinates": [
+ [
+ [
+ 2.224122,
+ 48.854199
+ ]
+ ]
+ ]
+ }
+ },
+ {
+ "place_id": "127732055",
+ "licence": "Data © OpenStreetMap contributors, ODbL 1.0. http://www.openstreetmap.org/copyright",
+ "osm_type": "relation",
+ "osm_id": "7444",
+ "boundingbox": [
+ "48.8155755",
+ "48.902156",
+ "2.224122",
+ "2.4697602"
+ ],
+ "lat": "48.8565056",
+ "lon": "2.3521334",
+ "display_name": "This is the title",
+ "class": "tourism",
+ "type": "city",
+ "importance": 0.96893459932191,
+ "icon": "https://nominatim.openstreetmap.org/images/mapicons/poi_place_city.p.20.png",
+ "address": {
+ "city": "Paris",
+ "county": "Paris",
+ "state": "Île-de-France",
+ "country": "France",
+ "postcode": 75000,
+ "country_code": "fr"
+ },
+ "geojson": {
+ "type": "Polygon",
+ "coordinates": [
+ [
+ [
+ 2.224122,
+ 48.854199
+ ]
+ ]
+ ]
+ }
+ },
+ {
+ "place_id": "127732055",
+ "licence": "Data © OpenStreetMap contributors, ODbL 1.0. http://www.openstreetmap.org/copyright",
+ "osm_type": "node",
+ "osm_id": "7444",
+ "boundingbox": [
+ "48.8155755",
+ "48.902156",
+ "2.224122",
+ "2.4697602"
+ ],
+ "lat": "48.8565056",
+ "lon": "2.3521334",
+ "display_name": "This is the title",
+ "class": "tourism",
+ "type": "city",
+ "importance": 0.96893459932191,
+ "icon": "https://nominatim.openstreetmap.org/images/mapicons/poi_place_city.p.20.png",
+ "address": {
+ "city": "Paris",
+ "county": "Paris",
+ "state": "Île-de-France",
+ "country": "France",
+ "country_code": "fr",
+ "address29": "Address"
+ }
+ }
+ ]
+ """
+ response = mock.Mock(text=json)
+ results = openstreetmap.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 3)
+ self.assertIn('48.8565056', results[2]['geojson']['coordinates'])
+ self.assertIn('2.3521334', results[2]['geojson']['coordinates'])
diff --git a/searx/tests/engines/test_photon.py b/searx/tests/engines/test_photon.py
new file mode 100644
index 00000000..73449788
--- /dev/null
+++ b/searx/tests/engines/test_photon.py
@@ -0,0 +1,166 @@
+# -*- coding: utf-8 -*-
+from collections import defaultdict
+import mock
+from searx.engines import photon
+from searx.testing import SearxTestCase
+
+
+class TestPhotonEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ dicto['language'] = 'all'
+ params = photon.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('photon.komoot.de', params['url'])
+
+ dicto['language'] = 'all'
+ params = photon.request(query, dicto)
+ self.assertNotIn('lang', params['url'])
+
+ dicto['language'] = 'al'
+ params = photon.request(query, dicto)
+ self.assertNotIn('lang', params['url'])
+
+ dicto['language'] = 'fr'
+ params = photon.request(query, dicto)
+ self.assertIn('fr', params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, photon.response, None)
+ self.assertRaises(AttributeError, photon.response, [])
+ self.assertRaises(AttributeError, photon.response, '')
+ self.assertRaises(AttributeError, photon.response, '[]')
+
+ response = mock.Mock(text='{}')
+ self.assertEqual(photon.response(response), [])
+
+ response = mock.Mock(text='{"data": []}')
+ self.assertEqual(photon.response(response), [])
+
+ json = """
+ {
+ "features": [
+ {
+ "properties": {
+ "osm_key": "waterway",
+ "extent": [
+ -1.4508446,
+ 51.1614997,
+ -1.4408036,
+ 51.1525635
+ ],
+ "name": "This is the title",
+ "state": "England",
+ "osm_id": 114823817,
+ "osm_type": "W",
+ "osm_value": "river",
+ "city": "Test Valley",
+ "country": "United Kingdom"
+ },
+ "type": "Feature",
+ "geometry": {
+ "type": "Point",
+ "coordinates": [
+ -1.4458571,
+ 51.1576661
+ ]
+ }
+ },
+ {
+ "properties": {
+ "osm_key": "place",
+ "street": "Rue",
+ "state": "Ile-de-France",
+ "osm_id": 129211377,
+ "osm_type": "R",
+ "housenumber": "10",
+ "postcode": "75011",
+ "osm_value": "house",
+ "city": "Paris",
+ "country": "France"
+ },
+ "type": "Feature",
+ "geometry": {
+ "type": "Point",
+ "coordinates": [
+ 2.3725025,
+ 48.8654481
+ ]
+ }
+ },
+ {
+ "properties": {
+ "osm_key": "amenity",
+ "street": "Allée",
+ "name": "Bibliothèque",
+ "state": "Ile-de-France",
+ "osm_id": 1028573132,
+ "osm_type": "N",
+ "postcode": "75001",
+ "osm_value": "library",
+ "city": "Paris",
+ "country": "France"
+ },
+ "type": "Feature",
+ "geometry": {
+ "type": "Point",
+ "coordinates": [
+ 2.3445634,
+ 48.862494
+ ]
+ }
+ },
+ {
+ "properties": {
+ "osm_key": "amenity",
+ "osm_id": 1028573132,
+ "osm_type": "Y",
+ "postcode": "75001",
+ "osm_value": "library",
+ "city": "Paris",
+ "country": "France"
+ },
+ "type": "Feature",
+ "geometry": {
+ "type": "Point",
+ "coordinates": [
+ 2.3445634,
+ 48.862494
+ ]
+ }
+ },
+ {
+ }
+ ],
+ "type": "FeatureCollection"
+ }
+ """
+ response = mock.Mock(text=json)
+ results = photon.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 3)
+ self.assertEqual(results[0]['title'], 'This is the title')
+ self.assertEqual(results[0]['content'], '')
+ self.assertEqual(results[0]['longitude'], -1.4458571)
+ self.assertEqual(results[0]['latitude'], 51.1576661)
+ self.assertIn(-1.4508446, results[0]['boundingbox'])
+ self.assertIn(51.1614997, results[0]['boundingbox'])
+ self.assertIn(-1.4408036, results[0]['boundingbox'])
+ self.assertIn(51.1525635, results[0]['boundingbox'])
+ self.assertIn('type', results[0]['geojson'])
+ self.assertEqual(results[0]['geojson']['type'], 'Point')
+ self.assertEqual(results[0]['address'], None)
+ self.assertEqual(results[0]['osm']['type'], 'way')
+ self.assertEqual(results[0]['osm']['id'], 114823817)
+ self.assertEqual(results[0]['url'], 'https://openstreetmap.org/way/114823817')
+ self.assertEqual(results[1]['osm']['type'], 'relation')
+ self.assertEqual(results[2]['address']['name'], u'Bibliothèque')
+ self.assertEqual(results[2]['address']['house_number'], None)
+ self.assertEqual(results[2]['address']['locality'], 'Paris')
+ self.assertEqual(results[2]['address']['postcode'], '75001')
+ self.assertEqual(results[2]['address']['country'], 'France')
+ self.assertEqual(results[2]['osm']['type'], 'node')
diff --git a/searx/tests/engines/test_startpage.py b/searx/tests/engines/test_startpage.py
new file mode 100644
index 00000000..07f13ee2
--- /dev/null
+++ b/searx/tests/engines/test_startpage.py
@@ -0,0 +1,140 @@
+# -*- coding: utf-8 -*-
+from collections import defaultdict
+import mock
+from searx.engines import startpage
+from searx.testing import SearxTestCase
+
+
+class TestStartpageEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ dicto['language'] = 'fr_FR'
+ params = startpage.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn('startpage.com', params['url'])
+ self.assertIn('data', params)
+ self.assertIn('query', params['data'])
+ self.assertIn(query, params['data']['query'])
+ self.assertIn('with_language', params['data'])
+ self.assertIn('lang_fr', params['data']['with_language'])
+
+ dicto['language'] = 'all'
+ params = startpage.request(query, dicto)
+ self.assertNotIn('with_language', params['data'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, startpage.response, None)
+ self.assertRaises(AttributeError, startpage.response, [])
+ self.assertRaises(AttributeError, startpage.response, '')
+ self.assertRaises(AttributeError, startpage.response, '[]')
+
+ response = mock.Mock(content='')
+ self.assertEqual(startpage.response(response), [])
+
+ html = """
+
+ """
+ response = mock.Mock(content=html)
+ results = startpage.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 = """
+
+
+
+
+
+
+ This should be the content.
+
+
+ www.speedtest.net/fr/
+
+
+
+
+ """
+ response = mock.Mock(content=html)
+ results = startpage.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['content'], '')
diff --git a/searx/tests/engines/test_subtitleseeker.py b/searx/tests/engines/test_subtitleseeker.py
new file mode 100644
index 00000000..a641601b
--- /dev/null
+++ b/searx/tests/engines/test_subtitleseeker.py
@@ -0,0 +1,169 @@
+from collections import defaultdict
+import mock
+from searx.engines import subtitleseeker
+from searx.testing import SearxTestCase
+
+
+class TestSubtitleseekerEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ params = subtitleseeker.request(query, dicto)
+ self.assertTrue('url' in params)
+ self.assertTrue(query in params['url'])
+ self.assertTrue('subtitleseeker.com' in params['url'])
+
+ def test_response(self):
+ dicto = defaultdict(dict)
+ dicto['language'] = 'fr_FR'
+ response = mock.Mock(search_params=dicto)
+
+ self.assertRaises(AttributeError, subtitleseeker.response, None)
+ self.assertRaises(AttributeError, subtitleseeker.response, [])
+ self.assertRaises(AttributeError, subtitleseeker.response, '')
+ self.assertRaises(AttributeError, subtitleseeker.response, '[]')
+
+ response = mock.Mock(text='', search_params=dicto)
+ self.assertEqual(subtitleseeker.response(response), [])
+
+ html = """
+
+
+
+ 1998
+
+
+
+ 1039 Subs
+
+
+
+ 1 hours ago
+
+
+
+ """
+ response = mock.Mock(text=html, search_params=dicto)
+ results = subtitleseeker.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/French/')
+ self.assertIn('1998', results[0]['content'])
+ self.assertIn('1039 Subs', results[0]['content'])
+ self.assertIn('Alternative Title', results[0]['content'])
+
+ html = """
+
+
+
+ 1998
+
+
+
+ 1039 Subs
+
+
+
+ 1 hours ago
+
+
+
+ """
+ dicto['language'] = 'all'
+ response = mock.Mock(text=html, search_params=dicto)
+ results = subtitleseeker.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.assertIn('1998', results[0]['content'])
+ self.assertIn('1039 Subs', results[0]['content'])
+
+ html = """
+
+
+
+ 1998
+
+
+
+ 1039 Subs
+
+
+
+ 1 hours ago
+
+
+
+ """
+ subtitleseeker.language = 'English'
+ response = mock.Mock(text=html, search_params=dicto)
+ results = subtitleseeker.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/English/')
+ self.assertIn('1998', results[0]['content'])
+ self.assertIn('1039 Subs', results[0]['content'])
+
+ html = """
+
+
+ 1998
+
+
+
+ 1039 Subs
+
+
+
+ 1 hours ago
+
+ """
+ response = mock.Mock(text=html, search_params=dicto)
+ results = subtitleseeker.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_twitter.py b/searx/tests/engines/test_twitter.py
new file mode 100644
index 00000000..b444b48e
--- /dev/null
+++ b/searx/tests/engines/test_twitter.py
@@ -0,0 +1,502 @@
+# -*- coding: utf-8 -*-
+from collections import defaultdict
+import mock
+from searx.engines import twitter
+from searx.testing import SearxTestCase
+
+
+class TestTwitterEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 0
+ dicto['language'] = 'fr_FR'
+ params = twitter.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('twitter.com', params['url'])
+ self.assertIn('cookies', params)
+ self.assertIn('lang', params['cookies'])
+ self.assertIn('fr', params['cookies']['lang'])
+
+ dicto['language'] = 'all'
+ params = twitter.request(query, dicto)
+ self.assertIn('cookies', params)
+ self.assertIn('lang', params['cookies'])
+ self.assertIn('en', params['cookies']['lang'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, twitter.response, None)
+ self.assertRaises(AttributeError, twitter.response, [])
+ self.assertRaises(AttributeError, twitter.response, '')
+ self.assertRaises(AttributeError, twitter.response, '[]')
+
+ response = mock.Mock(text='')
+ self.assertEqual(twitter.response(response), [])
+
+ html = """
+
+
+
+ """
+ response = mock.Mock(text=html)
+ results = twitter.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], '@TitleName')
+ self.assertEqual(results[0]['url'], 'https://twitter.com/this.is.the.url')
+ self.assertIn(u'This is the content', results[0]['content'])
+ # self.assertIn(u'This is the content étude à€', results[0]['content'])
+
+ html = """
+
+
+
+ """
+ response = mock.Mock(text=html)
+ results = twitter.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 1)
+ self.assertEqual(results[0]['title'], '@TitleName')
+ self.assertEqual(results[0]['url'], 'https://twitter.com/this.is.the.url')
+ self.assertIn(u'This is the content', results[0]['content'])
+
+ html = """
+
+
+
+
+
+ this.meta.com
+
+
+
+
+
+
+ This should be the content.
+
+
+ """
+ response = mock.Mock(text=html)
+ results = twitter.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_yacy.py b/searx/tests/engines/test_yacy.py
new file mode 100644
index 00000000..f49532cf
--- /dev/null
+++ b/searx/tests/engines/test_yacy.py
@@ -0,0 +1,96 @@
+from collections import defaultdict
+import mock
+from searx.engines import yacy
+from searx.testing import SearxTestCase
+
+
+class TestYacyEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ dicto['language'] = 'fr_FR'
+ params = yacy.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('localhost', params['url'])
+ self.assertIn('fr', params['url'])
+
+ dicto['language'] = 'all'
+ params = yacy.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertNotIn('lr=lang_', params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, yacy.response, None)
+ self.assertRaises(AttributeError, yacy.response, [])
+ self.assertRaises(AttributeError, yacy.response, '')
+ self.assertRaises(AttributeError, yacy.response, '[]')
+
+ response = mock.Mock(text='{}')
+ self.assertEqual(yacy.response(response), [])
+
+ response = mock.Mock(text='{"data": []}')
+ self.assertEqual(yacy.response(response), [])
+
+ json = """
+ {
+ "channels": [
+ {
+ "title": "YaCy P2P-Search for test",
+ "description": "Search for test",
+ "link": "http://search.yacy.de:7001/yacysearch.html?query=test&resource=global&contentdom=0",
+ "image": {
+ "url": "http://search.yacy.de:7001/env/grafics/yacy.png",
+ "title": "Search for test",
+ "link": "http://search.yacy.de:7001/yacysearch.html?query=test&resource=global&contentdom=0"
+ },
+ "totalResults": "249",
+ "startIndex": "0",
+ "itemsPerPage": "5",
+ "searchTerms": "test",
+ "items": [
+ {
+ "title": "This is the title",
+ "link": "http://this.is.the.url",
+ "code": "",
+ "description": "This should be the content",
+ "pubDate": "Sat, 08 Jun 2013 02:00:00 +0200",
+ "size": "44213",
+ "sizename": "43 kbyte",
+ "guid": "lzh_1T_5FP-A",
+ "faviconCode": "XTS4uQ_5FP-A",
+ "host": "www.gamestar.de",
+ "path": "/spiele/city-of-heroes-freedom/47019.html",
+ "file": "47019.html",
+ "urlhash": "lzh_1T_5FP-A",
+ "ranking": "0.20106804"
+ },
+ {
+ "title": "This is the title2",
+ "icon": "/ViewImage.png?maxwidth=96&maxheight=96&code=7EbAbW6BpPOA",
+ "image": "http://image.url/image.png",
+ "cache": "/ViewImage.png?quadratic=&url=http://golem.ivwbox.de/cgi-bin/ivw/CP/G_INET?d=14071378",
+ "url": "http://this.is.the.url",
+ "urlhash": "7EbAbW6BpPOA",
+ "host": "www.golem.de",
+ "width": "-1",
+ "height": "-1"
+ }
+ ]
+ }
+ ]
+ }
+ """
+ response = mock.Mock(text=json)
+ results = yacy.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 2)
+ 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 should be the content')
+ self.assertEqual(results[1]['img_src'], 'http://image.url/image.png')
+ self.assertEqual(results[1]['content'], '')
+ self.assertEqual(results[1]['url'], 'http://this.is.the.url')
+ self.assertEqual(results[1]['title'], 'This is the title2')
diff --git a/searx/tests/engines/test_yahoo.py b/searx/tests/engines/test_yahoo.py
new file mode 100644
index 00000000..e5c78701
--- /dev/null
+++ b/searx/tests/engines/test_yahoo.py
@@ -0,0 +1,154 @@
+# -*- coding: utf-8 -*-
+from collections import defaultdict
+import mock
+from searx.engines import yahoo
+from searx.testing import SearxTestCase
+
+
+class TestYahooEngine(SearxTestCase):
+
+ def test_parse_url(self):
+ test_url = 'http://r.search.yahoo.com/_ylt=A0LEb9JUSKcAEGRXNyoA;_ylu=X3oDMTEzZm1qazYwBHNlYwNzcgRwb3MDMQRjb' +\
+ '2xvA2Jm2dGlkA1NNRTcwM18x/RV=2/RE=1423106085/RO=10/RU=https%3a%2f%2fthis.is.the.url%2f/RK=0/RS=' +\
+ 'dtcJsfP4mEeBOjnVfUQ-'
+ url = yahoo.parse_url(test_url)
+ self.assertEqual('https://this.is.the.url/', url)
+
+ test_url = 'http://r.search.yahoo.com/_ylt=A0LElb9JUSKcAEGRXNyoA;_ylu=X3oDMTEzZm1qazYwBHNlYwNzcgRwb3MDMQRjb' +\
+ '2xvA2Jm2dGlkA1NNRTcwM18x/RV=2/RE=1423106085/RO=10/RU=https%3a%2f%2fthis.is.the.url%2f/RS=' +\
+ 'dtcJsfP4mEeBOjnVfUQ-'
+ url = yahoo.parse_url(test_url)
+ self.assertEqual('https://this.is.the.url/', url)
+
+ test_url = 'https://this.is.the.url/'
+ url = yahoo.parse_url(test_url)
+ self.assertEqual('https://this.is.the.url/', url)
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ dicto['language'] = 'fr_FR'
+ params = yahoo.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('search.yahoo.com', params['url'])
+ self.assertIn('fr', params['url'])
+ self.assertIn('cookies', params)
+ self.assertIn('sB', params['cookies'])
+ self.assertIn('fr', params['cookies']['sB'])
+
+ dicto['language'] = 'all'
+ params = yahoo.request(query, dicto)
+ self.assertIn('cookies', params)
+ self.assertIn('sB', params['cookies'])
+ self.assertIn('en', params['cookies']['sB'])
+ self.assertIn('en', params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, yahoo.response, None)
+ self.assertRaises(AttributeError, yahoo.response, [])
+ self.assertRaises(AttributeError, yahoo.response, '')
+ self.assertRaises(AttributeError, yahoo.response, '[]')
+
+ response = mock.Mock(text='')
+ self.assertEqual(yahoo.response(response), [])
+
+ html = """
+
+
+
www.test.com
+
+ This is the content
+
+
+
+ """
+ response = mock.Mock(text=html)
+ results = yahoo.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 2)
+ self.assertEqual(results[0]['title'], 'This is the title')
+ self.assertEqual(results[0]['url'], 'https://this.is.the.url/')
+ self.assertEqual(results[0]['content'], 'This is the content')
+ self.assertEqual(results[1]['suggestion'], 'This is the suggestion')
+
+ html = """
+
+
+
www.test.com
+
+ This is the content
+
+
+
+
+
www.test.com
+
+ This is the content
+
+
+
+
+
+
+
+
www.test.com
+
+ This is the content
+
+
+ """
+ response = mock.Mock(text=html)
+ results = yahoo.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://this.is.the.url/')
+ self.assertEqual(results[0]['content'], 'This is the content')
+
+ html = """
+
+
+ """
+ response = mock.Mock(text=html)
+ results = yahoo.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 0)
diff --git a/searx/tests/engines/test_yahoo_news.py b/searx/tests/engines/test_yahoo_news.py
new file mode 100644
index 00000000..797dc11b
--- /dev/null
+++ b/searx/tests/engines/test_yahoo_news.py
@@ -0,0 +1,143 @@
+# -*- coding: utf-8 -*-
+from collections import defaultdict
+from datetime import datetime
+import mock
+from searx.engines import yahoo_news
+from searx.testing import SearxTestCase
+
+
+class TestYahooNewsEngine(SearxTestCase):
+
+ def test_request(self):
+ query = 'test_query'
+ dicto = defaultdict(dict)
+ dicto['pageno'] = 1
+ dicto['language'] = 'fr_FR'
+ params = yahoo_news.request(query, dicto)
+ self.assertIn('url', params)
+ self.assertIn(query, params['url'])
+ self.assertIn('news.search.yahoo.com', params['url'])
+ self.assertIn('fr', params['url'])
+ self.assertIn('cookies', params)
+ self.assertIn('sB', params['cookies'])
+ self.assertIn('fr', params['cookies']['sB'])
+
+ dicto['language'] = 'all'
+ params = yahoo_news.request(query, dicto)
+ self.assertIn('cookies', params)
+ self.assertIn('sB', params['cookies'])
+ self.assertIn('en', params['cookies']['sB'])
+ self.assertIn('en', params['url'])
+
+ def test_response(self):
+ self.assertRaises(AttributeError, yahoo_news.response, None)
+ self.assertRaises(AttributeError, yahoo_news.response, [])
+ self.assertRaises(AttributeError, yahoo_news.response, '')
+ self.assertRaises(AttributeError, yahoo_news.response, '[]')
+
+ response = mock.Mock(text='')
+ self.assertEqual(yahoo_news.response(response), [])
+
+ html = """
+
+
+
Business via Yahoo! Finance Feb 03 09:45am
+
+ This is the content
+
+
+ """
+ response = mock.Mock(text=html)
+ results = yahoo_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')
+
+ html = """
+
+
+
Business via Yahoo! 2 hours, 22 minutes ago
+
+ This is the content
+
+
+
+
+
Business via Yahoo! 22 minutes ago
+
+ This is the content
+
+
+
+
+
Business via Yahoo! Feb 03 09:45am 1900
+
+ This is the content
+
+
+ """
+ response = mock.Mock(text=html)
+ results = yahoo_news.response(response)
+ self.assertEqual(type(results), list)
+ self.assertEqual(len(results), 3)
+ 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')
+ self.assertEqual(results[2]['publishedDate'].year, datetime.now().year)
+
+ html = """
+
+
+
+
+
+ this.meta.com
+
+
+
+
+
+
+ This should be the content.
+
+
+ """
+ response = mock.Mock(text=html)
+ results = yahoo_news.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
index 651da6dc..9b1c12cb 100644
--- a/searx/tests/test_engines.py
+++ b/searx/tests/test_engines.py
@@ -3,25 +3,39 @@ from searx.tests.engines.test_bing_images import * # noqa
from searx.tests.engines.test_bing_news import * # noqa
from searx.tests.engines.test_blekko_images import * # noqa
from searx.tests.engines.test_btdigg import * # noqa
+from searx.tests.engines.test_currency_convert 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_duckduckgo import * # noqa
+from searx.tests.engines.test_duckduckgo_definitions import * # noqa
from searx.tests.engines.test_dummy import * # noqa
+from searx.tests.engines.test_faroo import * # noqa
from searx.tests.engines.test_flickr import * # noqa
from searx.tests.engines.test_flickr_noapi import * # noqa
from searx.tests.engines.test_gigablast import * # noqa
from searx.tests.engines.test_github import * # noqa
-from searx.tests.engines.test_www1x import * # noqa
+from searx.tests.engines.test_google 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_mediawiki import * # noqa
from searx.tests.engines.test_mixcloud import * # noqa
+from searx.tests.engines.test_openstreetmap import * # noqa
+from searx.tests.engines.test_photon 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_startpage import * # noqa
+from searx.tests.engines.test_subtitleseeker import * # noqa
+from searx.tests.engines.test_twitter import * # noqa
from searx.tests.engines.test_vimeo import * # noqa
+from searx.tests.engines.test_www1x import * # noqa
from searx.tests.engines.test_www500px import * # noqa
+from searx.tests.engines.test_yacy import * # noqa
+from searx.tests.engines.test_yahoo import * # noqa
from searx.tests.engines.test_youtube import * # noqa
+from searx.tests.engines.test_yahoo_news import * # noqa