Merge branch 'master' into devel_google_videos

This commit is contained in:
Noémi Ványi 2019-01-04 22:27:05 +01:00 committed by GitHub
commit 1ea56576dc
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
9 changed files with 27261 additions and 167 deletions

View file

@ -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 \

File diff suppressed because one or more lines are too long

View file

@ -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',

View file

@ -1,115 +0,0 @@
"""
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 ''

View file

@ -32,8 +32,9 @@ search_url = base_url + 'do/search'
# specific xpath variables
# ads xpath //div[@id="results"]/div[@id="sponsored"]//div[@class="result"]
# not ads: div[@class="result"] are the direct childs of div[@id="results"]
results_xpath = '//div[@class="result"]'
results_xpath = '//li[contains(@class, "search-result") and contains(@class, "search-item")]'
link_xpath = './/h3/a'
content_xpath = './p[@class="search-item__body"]'
# do search-request
@ -73,14 +74,10 @@ def response(resp):
if re.match(r"^http(s|)://(www\.)?startpage\.com/do/search\?.*$", url):
continue
# block ixquick search url's
if re.match(r"^http(s|)://(www\.)?ixquick\.com/do/search\?.*$", url):
continue
title = extract_text(link)
if result.xpath('./p[@class="desc clk"]'):
content = extract_text(result.xpath('./p[@class="desc clk"]'))
if result.xpath(content_xpath):
content = extract_text(result.xpath(content_xpath))
else:
content = ''

View file

@ -218,24 +218,6 @@ engines:
shortcut : fd
disabled : True
- name : findx
engine : findx
shortcut : fx
categories : general
disabled : True
- name : findx images
engine : findx
shortcut : fxi
categories : images
disabled : True
- name : findx videos
engine : findx
shortcut : fxv
categories : videos
disabled : True
- name : flickr
categories : images
shortcut : fl
@ -597,14 +579,6 @@ engines:
timeout : 6.0
disabled : True
- name : ixquick
engine : startpage
base_url : 'https://www.ixquick.eu/'
search_url : 'https://www.ixquick.eu/do/search'
shortcut : iq
timeout : 6.0
disabled : True
- name : swisscows
engine : swisscows
shortcut : sw
@ -723,6 +697,19 @@ engines:
shortcut : du
disabled : True
- name : seznam
shortcut: szn
engine: xpath
paging : True
search_url : https://search.seznam.cz/?q={query}&count=10&from={pageno}
results_xpath: //div[@class="Page-content"]//div[@class="Result "]
url_xpath : ./h3/a/@href
title_xpath : ./h3
content_xpath : .//p[@class="Result-description"]
first_page_num : 0
page_size : 10
disabled : True
# - name : yacy
# engine : yacy
# shortcut : ya

View file

@ -52,7 +52,7 @@ class TestBingImagesEngine(SearxTestCase):
<li>
<div>
<div class="imgpt">
<a m='{"purl":"page_url","murl":"img_url"}' mad='{"turl":"thumb_url"}'>
<a m='{"purl":"page_url","murl":"img_url","turl":"thumb_url"}'>
<img src="" alt="alt text" />
</a>
</div>
@ -60,7 +60,7 @@ class TestBingImagesEngine(SearxTestCase):
</div>
<div>
<div class="imgpt">
<a m='{"purl":"page_url2","murl":"img_url2"}' mad='{"turl":"thumb_url2"}'>
<a m='{"purl":"page_url2","murl":"img_url2","turl":"thumb_url2"}'>
<img src="" alt="alt text 2" />
</a>
</div>
@ -71,7 +71,7 @@ class TestBingImagesEngine(SearxTestCase):
<li>
<div>
<div class="imgpt">
<a m='{"purl":"page_url3","murl":"img_url3"}' mad='{"turl":"thumb_url3"}'>
<a m='{"purl":"page_url3","murl":"img_url3","turl":"thumb_url3"}'>
<img src="" alt="alt text 3" />
</a>
</div>

View file

@ -31,14 +31,14 @@ class TestStartpageEngine(SearxTestCase):
self.assertEqual(startpage.response(response), [])
html = """
<div class='result' style=' *width : auto; *margin-right : 10%;'>
<li class="search-result search-item">
<h3>
<a href='http://this.should.be.the.link/' id='title_2' name='title_2' >
This should be the title
</a>
<span id='title_stars_2' name='title_stars_2'> </span>
</h3>
<p class='desc clk'>
<p class="search-item__body">
This should be the content.
</p>
<p>
@ -56,7 +56,7 @@ class TestStartpageEngine(SearxTestCase):
Mis en surbrillance
</A>
</p>
</div>
</li>
"""
response = mock.Mock(text=html.encode('utf-8'))
results = startpage.response(response)
@ -67,14 +67,14 @@ class TestStartpageEngine(SearxTestCase):
self.assertEqual(results[0]['content'], 'This should be the content.')
html = """
<div class='result' style=' *width : auto; *margin-right : 10%;'>
<li class="search-result search-item">
<h3>
<a href='http://www.google.com/aclk?sa=l&ai=C' id='title_2' name='title_2' >
This should be the title
</a>
<span id='title_stars_2' name='title_stars_2'> </span>
</h3>
<p class='desc clk'>
<p class="search-item__body">
This should be the content.
</p>
<p>
@ -92,20 +92,20 @@ class TestStartpageEngine(SearxTestCase):
Mis en surbrillance
</A>
</p>
</div>
<div class='result' style=' *width : auto; *margin-right : 10%;'>
</li>
<li class="search-result search-item">
<h3>
<span id='title_stars_2' name='title_stars_2'> </span>
</h3>
<p class='desc clk'>
<p class="search-item__body">
This should be the content.
</p>
<p>
<span class='url'>www.speed<b>test</b>.net/fr/
</span>
</p>
</div>
<div class='result' style=' *width : auto; *margin-right : 10%;'>
</li>
<li class="search-result search-item">
<h3>
<a href='http://this.should.be.the.link/' id='title_2' name='title_2' >
This should be the title
@ -127,7 +127,7 @@ class TestStartpageEngine(SearxTestCase):
Mis en surbrillance
</A>
</p>
</div>
</li>
"""
response = mock.Mock(text=html.encode('utf-8'))
results = startpage.response(response)

View file

@ -27,12 +27,14 @@ def fetch_supported_languages():
if hasattr(engines[engine_name], 'fetch_supported_languages'):
try:
engines_languages[engine_name] = engines[engine_name].fetch_supported_languages()
if type(engines_languages[engine_name]) == list:
engines_languages[engine_name] = sorted(engines_languages[engine_name])
except Exception as e:
print(e)
# write json file
with io.open(engines_languages_file, "w", encoding="utf-8") as f:
dump(engines_languages, f, ensure_ascii=False)
dump(engines_languages, f, ensure_ascii=False, indent=4, separators=(',', ': '))
return engines_languages