Commit ffe0972f authored by Dalf's avatar Dalf

Remove some engines : subtitleseeker, seedpeer, swisscows

http://www.subtitleseeker.com and http://www.seedpeer.eu don't exist anymore.
https://swisscows.ch/ has change : the engine needs to be updated
parent 6c95ebcf
# Seedpeer (Videos, Music, Files)
#
# @website http://seedpeer.eu
# @provide-api no (nothing found)
#
# @using-api no
# @results HTML (using search portal)
# @stable yes (HTML can change)
# @parse url, title, content, seed, leech, magnetlink
from lxml import html
from operator import itemgetter
from searx.url_utils import quote, urljoin
url = 'http://www.seedpeer.eu/'
search_url = url + 'search/{search_term}/7/{page_no}.html'
# specific xpath variables
torrent_xpath = '//*[@id="body"]/center/center/table[2]/tr/td/a'
alternative_torrent_xpath = '//*[@id="body"]/center/center/table[1]/tr/td/a'
title_xpath = '//*[@id="body"]/center/center/table[2]/tr/td/a/text()'
alternative_title_xpath = '//*[@id="body"]/center/center/table/tr/td/a'
seeds_xpath = '//*[@id="body"]/center/center/table[2]/tr/td[4]/font/text()'
alternative_seeds_xpath = '//*[@id="body"]/center/center/table/tr/td[4]/font/text()'
peers_xpath = '//*[@id="body"]/center/center/table[2]/tr/td[5]/font/text()'
alternative_peers_xpath = '//*[@id="body"]/center/center/table/tr/td[5]/font/text()'
age_xpath = '//*[@id="body"]/center/center/table[2]/tr/td[2]/text()'
alternative_age_xpath = '//*[@id="body"]/center/center/table/tr/td[2]/text()'
size_xpath = '//*[@id="body"]/center/center/table[2]/tr/td[3]/text()'
alternative_size_xpath = '//*[@id="body"]/center/center/table/tr/td[3]/text()'
# do search-request
def request(query, params):
params['url'] = search_url.format(search_term=quote(query),
page_no=params['pageno'] - 1)
return params
# get response from search-request
def response(resp):
results = []
dom = html.fromstring(resp.text)
torrent_links = dom.xpath(torrent_xpath)
if len(torrent_links) > 0:
seeds = dom.xpath(seeds_xpath)
peers = dom.xpath(peers_xpath)
titles = dom.xpath(title_xpath)
sizes = dom.xpath(size_xpath)
ages = dom.xpath(age_xpath)
else: # under ~5 results uses a different xpath
torrent_links = dom.xpath(alternative_torrent_xpath)
seeds = dom.xpath(alternative_seeds_xpath)
peers = dom.xpath(alternative_peers_xpath)
titles = dom.xpath(alternative_title_xpath)
sizes = dom.xpath(alternative_size_xpath)
ages = dom.xpath(alternative_age_xpath)
# return empty array if nothing is found
if not torrent_links:
return []
# parse results
for index, result in enumerate(torrent_links):
link = result.attrib.get('href')
href = urljoin(url, link)
results.append({'url': href,
'title': titles[index].text_content(),
'content': '{}, {}'.format(sizes[index], ages[index]),
'seed': seeds[index],
'leech': peers[index],
'template': 'torrent.html'})
# return results sorted by seeder
return sorted(results, key=itemgetter('seed'), reverse=True)
"""
Subtitleseeker (Video)
@website http://www.subtitleseeker.com
@provide-api no
@using-api no
@results HTML
@stable no (HTML can change)
@parse url, title, content
"""
from lxml import html
from searx.languages import language_codes
from searx.engines.xpath import extract_text
from searx.url_utils import quote_plus
# engine dependent config
categories = ['videos']
paging = True
language = ""
# search-url
url = 'http://www.subtitleseeker.com/'
search_url = url + 'search/TITLES/{query}?p={pageno}'
# specific xpath variables
results_xpath = '//div[@class="boxRows"]'
# do search-request
def request(query, params):
params['url'] = search_url.format(query=quote_plus(query),
pageno=params['pageno'])
return params
# get response from search-request
def response(resp):
results = []
dom = html.fromstring(resp.text)
search_lang = ""
# dirty fix for languages named differenly in their site
if resp.search_params['language'][:2] == 'fa':
search_lang = 'Farsi'
elif resp.search_params['language'] == 'pt-BR':
search_lang = 'Brazilian'
elif resp.search_params['language'] != 'all':
search_lang = [lc[3]
for lc in language_codes
if lc[0].split('-')[0] == resp.search_params['language'].split('-')[0]]
search_lang = search_lang[0].split(' (')[0]
# parse results
for result in dom.xpath(results_xpath):
link = result.xpath(".//a")[0]
href = link.attrib.get('href')
if language is not "":
href = href + language + '/'
elif search_lang:
href = href + search_lang + '/'
title = extract_text(link)
content = extract_text(result.xpath('.//div[contains(@class,"red")]'))
content = content + " - "
text = extract_text(result.xpath('.//div[contains(@class,"grey-web")]')[0])
content = content + text
if result.xpath(".//span") != []:
content = content +\
" - (" +\
extract_text(result.xpath(".//span")) +\
")"
# append result
results.append({'url': href,
'title': title,
'content': content})
# return results
return results
"""
Swisscows (Web, Images)
@website https://swisscows.ch
@provide-api no
@using-api no
@results HTML (using search portal)
@stable no (HTML can change)
@parse url, title, content
"""
from json import loads
import re
from lxml.html import fromstring
from searx.url_utils import unquote, urlencode
from searx.utils import match_language
# engine dependent config
categories = ['general', 'images']
paging = True
language_support = True
# search-url
base_url = 'https://swisscows.ch/'
search_string = '?{query}&page={page}'
supported_languages_url = base_url
# regex
regex_json = re.compile(b'initialData: {"Request":(.|\n)*},\s*environment')
regex_json_remove_start = re.compile(b'^initialData:\s*')
regex_json_remove_end = re.compile(b',\s*environment$')
regex_img_url_remove_start = re.compile(b'^https?://i\.swisscows\.ch/\?link=')
# do search-request
def request(query, params):
if params['language'] == 'all':
ui_language = 'browser'
region = 'browser'
else:
region = match_language(params['language'], supported_languages, language_aliases)
ui_language = region.split('-')[0]
search_path = search_string.format(
query=urlencode({'query': query, 'uiLanguage': ui_language, 'region': region}),
page=params['pageno']
)
# image search query is something like 'image?{query}&page={page}'
if params['category'] == 'images':
search_path = 'image' + search_path
params['url'] = base_url + search_path
return params
# get response from search-request
def response(resp):
results = []
json_regex = regex_json.search(resp.text)
# check if results are returned
if not json_regex:
return []
json_raw = regex_json_remove_end.sub(b'', regex_json_remove_start.sub(b'', json_regex.group()))
json = loads(json_raw.decode('utf-8'))
# parse results
for result in json['Results'].get('items', []):
result_title = result['Title'].replace(u'\uE000', '').replace(u'\uE001', '')
# parse image results
if result.get('ContentType', '').startswith('image'):
img_url = unquote(regex_img_url_remove_start.sub(b'', result['Url'].encode('utf-8')).decode('utf-8'))
# append result
results.append({'url': result['SourceUrl'],
'title': result['Title'],
'content': '',
'img_src': img_url,
'template': 'images.html'})
# parse general results
else:
result_url = result['Url'].replace(u'\uE000', '').replace(u'\uE001', '')
result_content = result['Description'].replace(u'\uE000', '').replace(u'\uE001', '')
# append result
results.append({'url': result_url,
'title': result_title,
'content': result_content})
# parse images
for result in json.get('Images', []):
# decode image url
img_url = unquote(regex_img_url_remove_start.sub(b'', result['Url'].encode('utf-8')).decode('utf-8'))
# append result
results.append({'url': result['SourceUrl'],
'title': result['Title'],
'content': '',
'img_src': img_url,
'template': 'images.html'})
# return results
return results
# get supported languages from their site
def _fetch_supported_languages(resp):
supported_languages = []
dom = fromstring(resp.text)
options = dom.xpath('//div[@id="regions-popup"]//ul/li/a')
for option in options:
code = option.xpath('./@data-search-language')[0]
if code.startswith('nb-'):
code = code.replace('nb', 'no', 1)
supported_languages.append(code)
return supported_languages
......@@ -568,24 +568,12 @@ engines:
engine : spotify
shortcut : stf
- name : subtitleseeker
engine : subtitleseeker
shortcut : ss
# The language is an option. You can put any language written in english
# Examples : English, French, German, Hungarian, Chinese...
# language : English
- name : startpage
engine : startpage
shortcut : sp
timeout : 6.0
disabled : True
- name : swisscows
engine : swisscows
shortcut : sw
disabled : True
- name : tokyotoshokan
engine : tokyotoshokan
shortcut : tt
......@@ -664,12 +652,6 @@ engines:
timeout: 6.0
categories : science
- name : seedpeer
engine : seedpeer
shortcut: speu
categories: files, music, videos
disabled: True
- name : dictzone
engine : dictzone
shortcut : dc
......
import mock
from collections import defaultdict
from searx.engines import seedpeer
from searx.testing import SearxTestCase
from datetime import datetime
class TestSeedPeerEngine(SearxTestCase):
html = ''
with open('./tests/unit/engines/seedpeer_fixture.html') as fixture:
html += fixture.read()
def test_request(self):
query = 'test_query'
dicto = defaultdict(dict)
dicto['pageno'] = 1
params = seedpeer.request(query, dicto)
self.assertIn('url', params)
self.assertIn(query, params['url'])
self.assertIn('seedpeer.eu', params['url'])
def test_response_raises_attr_error_on_empty_response(self):
self.assertRaises(AttributeError, seedpeer.response, None)
self.assertRaises(AttributeError, seedpeer.response, [])
self.assertRaises(AttributeError, seedpeer.response, '')
self.assertRaises(AttributeError, seedpeer.response, '[]')
def test_response_returns_empty_list(self):
response = mock.Mock(text='<html></html>')
self.assertEqual(seedpeer.response(response), [])
def test_response_returns_all_results(self):
response = mock.Mock(text=self.html)
results = seedpeer.response(response)
self.assertTrue(isinstance(results, list))
self.assertEqual(len(results), 2)
def test_response_returns_correct_results(self):
response = mock.Mock(text=self.html)
results = seedpeer.response(response)
self.assertEqual(
results[0]['title'], 'Narcos - Season 2 - 720p WEBRiP - x265 HEVC - ShAaNiG '
)
self.assertEqual(
results[0]['url'],
'http://www.seedpeer.eu/details/11685972/Narcos---Season-2---720p-WEBRiP---x265-HEVC---ShAaNiG.html'
)
self.assertEqual(results[0]['content'], '2.48 GB, 1 day')
self.assertEqual(results[0]['seed'], '861')
self.assertEqual(results[0]['leech'], '332')
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
dicto['language'] = 'fr-FR'
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='<html></html>', search_params=dicto)
self.assertEqual(subtitleseeker.response(response), [])
html = """
<div class="boxRows">
<div class="boxRowsInner" style="width:600px;">
<img src="http://static.subtitleseeker.com/images/movie.gif"
style="width:16px; height:16px;" class="icon">
<a href="http://this.is.the.url/"
class="blue" title="Title subtitle" >
This is the Title
</a>
<br><br>
<span class="f10b grey-dark arial" style="padding:0px 0px 5px 20px">
"Alternative Title"
</span>
</div>
<div class="boxRowsInner f12b red" style="width:70px;">
1998
</div>
<div class="boxRowsInner grey-web f12" style="width:120px;">
<img src="http://static.subtitleseeker.com/images/basket_put.png"
style="width:16px; height:16px;" class="icon">
1039 Subs
</div>
<div class="boxRowsInner grey-web f10" style="width:130px;">
<img src="http://static.subtitleseeker.com/images/arrow_refresh_small.png"
style="width:16px; height:16px;" class="icon">
1 hours ago
</div>
<div class="clear"></div>
</div>
"""
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'])
dicto['language'] = 'pt-BR'
results = subtitleseeker.response(response)
self.assertEqual(results[0]['url'], 'http://this.is.the.url/Brazilian/')
html = """
<div class="boxRows">
<div class="boxRowsInner" style="width:600px;">
<img src="http://static.subtitleseeker.com/images/movie.gif"
style="width:16px; height:16px;" class="icon">
<a href="http://this.is.the.url/"
class="blue" title="Title subtitle" >
This is the Title
</a>
</div>
<div class="boxRowsInner f12b red" style="width:70px;">
1998
</div>
<div class="boxRowsInner grey-web f12" style="width:120px;">
<img src="http://static.subtitleseeker.com/images/basket_put.png"
style="width:16px; height:16px;" class="icon">
1039 Subs
</div>
<div class="boxRowsInner grey-web f10" style="width:130px;">
<img src="http://static.subtitleseeker.com/images/arrow_refresh_small.png"
style="width:16px; height:16px;" class="icon">
1 hours ago
</div>
<div class="clear"></div>
</div>
"""
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 = """
<div class="boxRows">
<div class="boxRowsInner" style="width:600px;">
<img src="http://static.subtitleseeker.com/images/movie.gif"
style="width:16px; height:16px;" class="icon">
<a href="http://this.is.the.url/"
class="blue" title="Title subtitle" >
This is the Title
</a>
</div>
<div class="boxRowsInner f12b red" style="width:70px;">
1998
</div>
<div class="boxRowsInner grey-web f12" style="width:120px;">
<img src="http://static.subtitleseeker.com/images/basket_put.png"
style="width:16px; height:16px;" class="icon">
1039 Subs
</div>
<div class="boxRowsInner grey-web f10" style="width:130px;">
<img src="http://static.subtitleseeker.com/images/arrow_refresh_small.png"
style="width:16px; height:16px;" class="icon">
1 hours ago
</div>
<div class="clear"></div>
</div>
"""
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 = """
<div class="boxRowsInner" style="width:600px;">
<img src="http://static.subtitleseeker.com/images/movie.gif"
style="width:16px; height:16px;" class="icon">
<a href="http://this.is.the.url/"
class="blue" title="Title subtitle" >
This is the Title
</a>
</div>
<div class="boxRowsInner f12b red" style="width:70px;">
1998
</div>
<div class="boxRowsInner grey-web f12" style="width:120px;">
<img src="http://static.subtitleseeker.com/images/basket_put.png"
style="width:16px; height:16px;" class="icon">
1039 Subs
</div>
<div class="boxRowsInner grey-web f10" style="width:130px;">
<img src="http://static.subtitleseeker.com/images/arrow_refresh_small.png"
style="width:16px; height:16px;" class="icon">
1 hours ago
</div>
"""
response = mock.Mock(text=html, search_params=dicto)
results = subtitleseeker.response(response)
self.assertEqual(type(results), list)
self.assertEqual(len(results), 0)
from collections import defaultdict
import mock
from searx.engines import swisscows
from searx.testing import SearxTestCase
class TestSwisscowsEngine(SearxTestCase):
def test_request(self):
swisscows.supported_languages = ['de-AT', 'de-DE']
swisscows.language_aliases = {}
query = 'test_query'
dicto = defaultdict(dict)
dicto['pageno'] = 1
dicto['language'] = 'de-DE'
params = swisscows.request(query, dicto)
self.assertTrue('url' in params)
self.assertTrue(query in params['url'])
self.assertTrue('swisscows.ch' in params['url'])
self.assertTrue('uiLanguage=de' in params['url'])
self.assertTrue('region=de-DE' in params['url'])
dicto['language'] = 'all'
params = swisscows.request(query, dicto)
self.assertTrue('uiLanguage=browser' in params['url'])
self.assertTrue('region=browser' in params['url'])
dicto['category'] = 'images'
params = swisscows.request(query, dicto)
self.assertIn('image', params['url'])
def test_response(self):
self.assertRaises(AttributeError, swisscows.response, None)
self.assertRaises(AttributeError, swisscows.response, [])
self.assertRaises(AttributeError, swisscows.response, '')
self.assertRaises(AttributeError, swisscows.response, '[]')
response = mock.Mock(text=b'<html></html>')
self.assertEqual(swisscows.response(response), [])
response = mock.Mock(text=b'<html></html>')
self.assertEqual(swisscows.response(response), [])
html = b"""
<script>
App.Dispatcher.dispatch("initialize", {
html5history: true,
initialData: {"Request":
{"Page":1,
"ItemsCount":1,
"Query":"This should ",
"NormalizedQuery":"This should ",
"Region":"de-AT",
"UILanguage":"de"},
"Results":{"items":[
{"Title":"\uE000This should\uE001 be the title",
"Description":"\uE000This should\uE001 be the content.",
"Url":"http://this.should.be.the.link/",
"DisplayUrl":"www.\uE000this.should.be.the\uE001.link",
"Id":"782ef287-e439-451c-b380-6ebc14ba033d"},
{"Title":"Datei:This should1.svg",
"Url":"https://i.swisscows.ch/?link=http%3a%2f%2fts2.mm.This/should1.png",
"SourceUrl":"http://de.wikipedia.org/wiki/Datei:This should1.svg",
"DisplayUrl":"de.wikipedia.org/wiki/Datei:This should1.svg",
"Width":950,
"Height":534,
"FileSize":92100,
"ContentType":"image/jpeg",
"Thumbnail":{
"Url":"https://i.swisscows.ch/?link=http%3a%2f%2fts2.mm.This/should1.png",
"ContentType":"image/jpeg",
"Width":300,
"Height":168,
"FileSize":9134},
"Id":"6a97a542-8f65-425f-b7f6-1178c3aba7be"
}
],"TotalCount":55300,
"Query":"This should "
},
"Images":[{"Title":"Datei:This should.svg",
"Url":"https://i.swisscows.ch/?link=http%3a%2f%2fts2.mm.This/should.png",
"SourceUrl":"http://de.wikipedia.org/wiki/Datei:This should.svg",
"DisplayUrl":"de.wikipedia.org/wiki/Datei:This should.svg",
"Width":1280,
"Height":677,
"FileSize":50053,
"ContentType":"image/png",
"Thumbnail":{"Url":"https://i.swisscows.ch/?link=http%3a%2f%2fts2.mm.This/should.png",
"ContentType":"image/png",
"Width":300,
"Height":158,
"FileSize":8023},
"Id":"ae230fd8-a06a-47d6-99d5-e74766d8143a"}]},
environment: "production"
}).then(function (options) {
$('#Search_Form').on('submit', function (e) {
if (!Modernizr.history) return;
e.preventDefault();
var $form = $(this),
$query = $('#Query'),
query = $.trim($query.val()),
path = App.Router.makePath($form.attr('action'), null, $form.serializeObject())
if (query.length) {
options.html5history ?
ReactRouter.HistoryLocation.push(path) :
ReactRouter.RefreshLocation.push(path);
}
else $('#Query').trigger('blur');
});
});
</script>
"""
response = mock.Mock(text=html)
results = swisscows.response(response)
self.assertEqual(type(results), list)
self.assertEqual(len(results), 3)
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.')
self.assertEqual(results[1]['title'], 'Datei:This should1.svg')
self.assertEqual(results[1]['url'], 'http://de.wikipedia.org/wiki/Datei:This should1.svg')
self.assertEqual(results[1]['img_src'], 'http://ts2.mm.This/should1.png')
self.assertEqual(results[1]['template'], 'images.html')
self.assertEqual(results[2]['title'], 'Datei:This should.svg')
self.assertEqual(results[2]['url'], 'http://de.wikipedia.org/wiki/Datei:This should.svg')
self.assertEqual(results[2]['img_src'], 'http://ts2.mm.This/should.png')
self.assertEqual(results[2]['template'], 'images.html')
def test_fetch_supported_languages(self):
html = """<html></html>"""
response = mock.Mock(text=html)
languages = swisscows._fetch_supported_languages(response)
self.assertEqual(type(languages), list)
self.assertEqual(len(languages), 0)
html = """
<html>
<div id="regions-popup">
<div>
<ul>
<li><a data-search-language="browser"></a></li>
<li><a data-search-language="de-CH"></a></li>
<li><a data-search-language="fr-CH"></a></li>
</ul>
</div>
</div>
</html>
"""
response = mock.Mock(text=html)
languages = swisscows._fetch_supported_languages(response)
self.assertEqual(type(languages), list)
self.assertEqual(len(languages), 3)
self.assertIn('de-CH', languages)
self.assertIn('fr-CH', languages)
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment