Merge branch 'master' into setup-no-tests

AUTHORS.rst

@@ -83,3 +83,18 @@ generally made searx better:
 - Joseph Nuthalapati @josephkiranbabu
 - @maiki
 - Richard Didier @zeph33
+- Michael Vieria @Themimitoof
+- Richard Nespithal @rndevfx
+- Stanislas @angristan
+- @rinpatch
+- g. s. @usernameisntallowed
+- Léo Bourrel @bourrel
+- @cy8aer
+- @Popolon
+- Alice Ferrazzi @aliceinwire
+- @LiquidLemon
+- @dadosch
+- @Venca24
+- @ZEROF
+- Ivan Skytte Jørgensen @isj-privacore
+- @miicha

CHANGELOG.rst

+0.15.0 2019.01.06
+=================
+
+- New engines
+
+  - Acgsou (files, images, videos, music)
+  - Duden.de (general)
+  - Seznam (general)
+  - Mojeek (general)
+- New languages
+
+  - Catalan
+  - Welsh
+  - Basque
+  - Persian (Iran)
+  - Galician
+  - Dutch (Belgium)
+  - Telugu
+  - Vietnamese
+- New random answerers
+
+  - sha256
+  - uuidv4
+- New DOI resolsvers
+
+  - sci-hub.tw
+- Fix Vim mode on Firefox
+- Fix custom select in Oscar theme
+- Engine fixes (duckduckgo, google news, currency convert, gigablast, google scholar, wikidata image, etymonline, google videos, startpage, bing image)
+- Minor simple theme fixes
+
+- New Youtube icon in Oscar theme
+- Get DOI rewriters from settings.yml
+- Hide page buttons when infinite scrolling is enabled
+- Update user agent versions
+- Make Oscar style configurable
+- Make suspend times of errored engines configurable
+
 0.14.0 2018.02.19
 =================
 

Dockerfile

@@ -32,6 +32,7 @@ RUN echo "@commuedge http://nl.alpinelinux.org/alpine/edge/community" >> /etc/ap
     openssl-dev \
     ca-certificates \
     tini@commuedge \
+ && pip install --upgrade pip \
  && pip install --no-cache -r requirements.txt \
  && apk del \
     build-base \

searx/engines/__init__.py

@@ -113,8 +113,7 @@ def load_engine(engine_data):
                iso_lang not in getattr(engine, 'supported_languages'):
                 language_aliases[iso_lang] = engine_lang
 
-        if language_aliases:
-            setattr(engine, 'language_aliases', language_aliases)
+        setattr(engine, 'language_aliases', language_aliases)
 
     # assign language fetching method if auxiliary method exists
     if hasattr(engine, '_fetch_supported_languages'):

searx/engines/archlinux.py

@@ -36,7 +36,7 @@ def locale_to_lang_code(locale):
 # wikis for some languages were moved off from the main site, we need to make
 # requests to correct URLs to be able to get results in those languages
 lang_urls = {
-    'en': {
+    'all': {
         'base': 'https://wiki.archlinux.org',
         'search': '/index.php?title=Special:Search&offset={offset}&{query}'
     },
@@ -67,7 +67,7 @@ lang_urls = {
 def get_lang_urls(language):
     if language in lang_urls:
         return lang_urls[language]
-    return lang_urls['en']
+    return lang_urls['all']
 
 
 # Language names to build search requests for

searx/engines/bing.py

@@ -34,7 +34,10 @@ search_string = 'search?{query}&first={offset}'
 def request(query, params):
     offset = (params['pageno'] - 1) * 10 + 1
 
-    lang = match_language(params['language'], supported_languages, language_aliases)
+    if params['language'] == 'all':
+        lang = 'EN'
+    else:
+        lang = match_language(params['language'], supported_languages, language_aliases)
 
     query = u'language:{} {}'.format(lang.split('-')[0].upper(), query.decode('utf-8')).encode('utf-8')
 

searx/engines/bing_images.py

@@ -55,7 +55,7 @@ def request(query, params):
         query=urlencode({'q': query}),
         offset=offset)
 
-    language = match_language(params['language'], supported_languages).lower()
+    language = match_language(params['language'], supported_languages, language_aliases).lower()
 
     params['cookies']['SRCHHPGUSR'] = \
         'ADLT=' + safesearch_types.get(params['safesearch'], 'DEMOTE')
@@ -88,9 +88,7 @@ def response(resp):
 
         url = json_data.get('purl')
         img_src = json_data.get('murl')
-
-        thumb_json_data = loads(_quote_keys_regex.sub(r'\1"\2": \3', link.attrib.get('mad')))
-        thumbnail = thumb_json_data.get('turl')
+        thumbnail = json_data.get('turl')
 
         # append result
         results.append({'template': 'images.html',

searx/engines/bing_news.py

@@ -71,7 +71,10 @@ def request(query, params):
 
     offset = (params['pageno'] - 1) * 10 + 1
 
-    language = match_language(params['language'], supported_languages, language_aliases)
+    if params['language'] == 'all':
+        language = 'en-US'
+    else:
+        language = match_language(params['language'], supported_languages, language_aliases)
 
     params['url'] = _get_url(query, language, offset, params['time_range'])
 

searx/engines/bing_videos.py

@@ -48,7 +48,7 @@ def request(query, params):
         'ADLT=' + safesearch_types.get(params['safesearch'], 'DEMOTE')
 
     # language cookie
-    language = match_language(params['language'], supported_languages).lower()
+    language = match_language(params['language'], supported_languages, language_aliases).lower()
     params['cookies']['_EDGE_S'] = 'mkt=' + language + '&F=1'
 
     # query and paging

searx/engines/dailymotion.py

@@ -33,7 +33,10 @@ supported_languages_url = 'https://api.dailymotion.com/languages'
 
 # do search-request
 def request(query, params):
-    locale = match_language(params['language'], supported_languages)
+    if params['language'] == 'all':
+        locale = 'en-US'
+    else:
+        locale = match_language(params['language'], supported_languages)
 
     params['url'] = search_url.format(
         query=urlencode({'search': query, 'localization': locale}),

searx/engines/duckduckgo.py

@@ -54,6 +54,9 @@ content_xpath = './/a[@class="result__snippet"]'
 
 # match query's language to a region code that duckduckgo will accept
 def get_region_code(lang, lang_list=[]):
+    if lang == 'all':
+        return None
+
     lang_code = match_language(lang, lang_list, language_aliases, 'wt-WT')
     lang_parts = lang_code.split('-')
 
@@ -61,7 +64,6 @@ def get_region_code(lang, lang_list=[]):
     return lang_parts[1].lower() + '-' + lang_parts[0].lower()
 
 
-# do search-request
 def request(query, params):
     if params['time_range'] and params['time_range'] not in time_range_dict:
         return params
@@ -69,8 +71,12 @@ def request(query, params):
     offset = (params['pageno'] - 1) * 30
 
     region_code = get_region_code(params['language'], supported_languages)
-    params['url'] = url.format(
-        query=urlencode({'q': query, 'kl': region_code}), offset=offset, dc_param=offset)
+    if region_code:
+        params['url'] = url.format(
+            query=urlencode({'q': query, 'kl': region_code}), offset=offset, dc_param=offset)
+    else:
+        params['url'] = url.format(
+            query=urlencode({'q': query}), offset=offset, dc_param=offset)
 
     if params['time_range'] in time_range_dict:
         params['url'] += time_range_url.format(range=time_range_dict[params['time_range']])

searx/engines/duckduckgo_images.py

@@ -56,8 +56,12 @@ def request(query, params):
     safesearch = params['safesearch'] - 1
 
     region_code = get_region_code(params['language'], lang_list=supported_languages)
-    params['url'] = images_url.format(
-        query=urlencode({'q': query, 'l': region_code}), offset=offset, safesearch=safesearch, vqd=vqd)
+    if region_code:
+        params['url'] = images_url.format(
+            query=urlencode({'q': query, 'l': region_code}), offset=offset, safesearch=safesearch, vqd=vqd)
+    else:
+        params['url'] = images_url.format(
+            query=urlencode({'q': query}), offset=offset, safesearch=safesearch, vqd=vqd)
 
     return params
 

searx/engines/faroo.py

@@ -40,7 +40,10 @@ def request(query, params):
     offset = (params['pageno'] - 1) * number_of_results + 1
     categorie = search_category.get(params['category'], 'web')
 
-    language = params['language'].split('-')[0]
+    if params['language'] == 'all':
+        language = 'en'
+    else:
+        language = params['language'].split('-')[0]
 
     # if language is not supported, put it in english
     if language != 'en' and\

searx/engines/findx.py

-"""
-FindX (General, Images, Videos)
-
-@website     https://www.findx.com
-@provide-api no
-@using-api   no
-@results     HTML
-@stable      no
-@parse       url, title, content, embedded, img_src, thumbnail_src
-"""
-
-from dateutil import parser
-from json import loads
-import re
-
-from lxml import html
-
-from searx import logger
-from searx.engines.xpath import extract_text
-from searx.engines.youtube_noapi import base_youtube_url, embedded_url
-from searx.url_utils import urlencode
-
-
-paging = True
-results_xpath = '//script[@id="initial-state"]'
-search_url = 'https://www.findx.com/{category}?{q}'
-type_map = {
-    'none': 'web',
-    'general': 'web',
-    'images': 'images',
-    'videos': 'videos',
-}
-
-
-def request(query, params):
-    params['url'] = search_url.format(
-        category=type_map[params['category']],
-        q=urlencode({
-            'q': query,
-            'page': params['pageno']
-        })
-    )
-    return params
-
-
-def response(resp):
-    dom = html.fromstring(resp.text)
-    results_raw_json = dom.xpath(results_xpath)
-    results_json = loads(extract_text(results_raw_json))
-
-    if len(results_json['web']['results']) > 0:
-        return _general_results(results_json['web']['results']['webSearch']['results'])
-
-    if len(results_json['images']['results']) > 0:
-        return _images_results(results_json['images']['results'])
-
-    if len(results_json['video']['results']) > 0:
-        return _videos_results(results_json['video']['results'])
-
-    return []
-
-
-def _general_results(general_results):
-    results = []
-    for result in general_results:
-        results.append({
-            'url': result['url'],
-            'title': result['title'],
-            'content': result['sum'],
-        })
-    return results
-
-
-def _images_results(image_results):
-    results = []
-    for result in image_results:
-        results.append({
-            'url': result['sourceURL'],
-            'title': result['title'],
-            'content': result['source'],
-            'thumbnail_src': _extract_url(result['assets']['thumb']['url']),
-            'img_src': _extract_url(result['assets']['file']['url']),
-            'template': 'images.html',
-        })
-    return results
-
-
-def _videos_results(video_results):
-    results = []
-    for result in video_results:
-        if not result['kind'].startswith('youtube'):
-            logger.warn('Unknown video kind in findx: {}'.format(result['kind']))
-            continue
-
-        description = result['snippet']['description']
-        if len(description) > 300:
-            description = description[:300] + '...'
-
-        results.append({
-            'url': base_youtube_url + result['id'],
-            'title': result['snippet']['title'],
-            'content': description,
-            'thumbnail': _extract_url(result['snippet']['thumbnails']['default']['url']),
-            'publishedDate': parser.parse(result['snippet']['publishedAt']),
-            'embedded': embedded_url.format(videoid=result['id']),
-            'template': 'videos.html',
-        })
-    return results
-
-
-def _extract_url(url):
-    matching = re.search('(/https?://[^)]+)', url)
-    if matching:
-        return matching.group(0)[1:]
-    return ''

searx/engines/gigablast.py

@@ -50,9 +50,12 @@ supported_languages_url = 'https://gigablast.com/search?&rxikd=1'
 def request(query, params):
     offset = (params['pageno'] - 1) * number_of_results
 
-    language = params['language'].replace('-', '_').lower()
-    if language.split('-')[0] != 'zh':
-        language = language.split('-')[0]
+    if params['language'] == 'all':
+        language = 'xx'
+    else:
+        language = params['language'].replace('-', '_').lower()
+        if language.split('-')[0] != 'zh':
+            language = language.split('-')[0]
 
     if params['safesearch'] >= 1:
         safesearch = 1

searx/engines/google.py

@@ -166,7 +166,11 @@ def extract_text_from_dom(result, xpath):
 def request(query, params):
     offset = (params['pageno'] - 1) * 10
 
-    language = match_language(params['language'], supported_languages)
+    if params['language'] == 'all' or params['language'] == 'en-US':
+        language = 'en-GB'
+    else:
+        language = match_language(params['language'], supported_languages, language_aliases)
+
     language_array = language.split('-')
     if params['language'].find('-') > 0:
         country = params['language'].split('-')[1]
@@ -381,10 +385,10 @@ def attributes_to_html(attributes):
 def _fetch_supported_languages(resp):
     supported_languages = {}
     dom = html.fromstring(resp.text)
-    options = dom.xpath('//table//td/font/label/span')
+    options = dom.xpath('//*[@id="langSec"]//input[@name="lr"]')
     for option in options:
-        code = option.xpath('./@id')[0][1:]
-        name = option.text.title()
+        code = option.xpath('./@value')[0].split('_')[-1]
+        name = option.xpath('./@data-name')[0].title()
         supported_languages[code] = {"name": name}
 
     return supported_languages

searx/engines/google_news.py

@@ -51,9 +51,10 @@ def request(query, params):
     params['url'] = search_url.format(query=urlencode({'q': query}),
                                       search_options=urlencode(search_options))
 
-    language = match_language(params['language'], supported_languages).split('-')[0]
-    if language:
-        params['url'] += '&lr=lang_' + language
+    if params['language'] != 'all':
+        language = match_language(params['language'], supported_languages, language_aliases).split('-')[0]
+        if language:
+            params['url'] += '&lr=lang_' + language
 
     return params
 

searx/engines/google_videos.py

@@ -7,7 +7,7 @@
  @using-api   no
  @results     HTML
  @stable      no
- @parse       url, title, content
+ @parse       url, title, content, thumbnail
 """
 
 from datetime import date, timedelta
@@ -15,7 +15,7 @@ from json import loads
 from lxml import html
 from searx.engines.xpath import extract_text
 from searx.url_utils import urlencode
-
+import re
 
 # engine dependent config
 categories = ['videos']
@@ -25,7 +25,7 @@ time_range_support = True
 number_of_results = 10
 
 search_url = 'https://www.google.com/search'\
-    '?{query}'\
+    '?q={query}'\
     '&tbm=vid'\
     '&{search_options}'
 time_range_attr = "qdr:{range}"
@@ -69,15 +69,27 @@ def response(resp):
     # parse results
     for result in dom.xpath('//div[@class="g"]'):
 
-        title = extract_text(result.xpath('.//h3/a'))
-        url = result.xpath('.//h3/a/@href')[0]
+        title = extract_text(result.xpath('.//h3'))
+        url = result.xpath('.//div[@class="r"]/a/@href')[0]
         content = extract_text(result.xpath('.//span[@class="st"]'))
 
+        # get thumbnails
+        script = str(dom.xpath('//script[contains(., "_setImagesSrc")]')[0].text)
+        id = result.xpath('.//div[@class="s"]//img/@id')[0]
+        thumbnails_data = re.findall('s=\'(.*?)(?:\\\\[a-z,1-9,\\\\]+\'|\')\;var ii=\[(?:|[\'vidthumb\d+\',]+)\'' + id,
+                                     script)
+        tmp = []
+        if len(thumbnails_data) != 0:
+            tmp = re.findall('(data:image/jpeg;base64,[a-z,A-Z,0-9,/,\+]+)', thumbnails_data[0])
+        thumbnail = ''
+        if len(tmp) != 0:
+            thumbnail = tmp[-1]
+
         # append result
         results.append({'url': url,
                         'title': title,
                         'content': content,
-                        'thumbnail': '',
+                        'thumbnail': thumbnail,
                         'template': 'videos.html'})
 
     return results

searx/engines/mediawiki.py

@@ -45,7 +45,10 @@ def request(query, params):
 
     format_strings = list(Formatter().parse(base_url))
 
-    language = params['language'].split('-')[0]
+    if params['language'] == 'all':
+        language = 'en'
+    else:
+        language = params['language'].split('-')[0]
 
     # format_string [('https://', 'language', '', None), ('.wikipedia.org/', None, None, None)]
     if any(x[1] == 'language' for x in format_strings):