mirror of
https://github.com/searxng/searxng.git
synced 2024-12-27 11:40:29 +00:00
Merge branch 'master' of https://github.com/asciimoo/searx into boilerplate
This commit is contained in:
commit
1b90e1403b
24 changed files with 293 additions and 126 deletions
30
Dockerfile
30
Dockerfile
|
@ -1,10 +1,17 @@
|
|||
FROM alpine:3.10
|
||||
ENTRYPOINT ["/sbin/tini","--","/usr/local/searx/dockerfiles/docker-entrypoint.sh"]
|
||||
EXPOSE 8080
|
||||
VOLUME /etc/searx
|
||||
VOLUME /var/log/uwsgi
|
||||
|
||||
ARG VERSION_GITCOMMIT=unknow
|
||||
ARG SEARX_GIT_VERSION=unknow
|
||||
ARG VERSION_GITCOMMIT=unknown
|
||||
ARG SEARX_GIT_VERSION=unknown
|
||||
|
||||
ARG SEARX_GID=1000
|
||||
ARG SEARX_UID=1000
|
||||
ARG SEARX_GID=977
|
||||
ARG SEARX_UID=977
|
||||
|
||||
RUN addgroup -g ${SEARX_GID} searx && \
|
||||
adduser -u ${SEARX_UID} -D -h /usr/local/searx -s /bin/sh -G searx searx
|
||||
|
||||
ARG TIMESTAMP_SETTINGS=0
|
||||
ARG TIMESTAMP_UWSGI=0
|
||||
|
@ -16,19 +23,14 @@ ENV INSTANCE_NAME=searx \
|
|||
BASE_URL= \
|
||||
MORTY_KEY= \
|
||||
MORTY_URL=
|
||||
EXPOSE 8080
|
||||
VOLUME /etc/searx
|
||||
VOLUME /var/log/uwsgi
|
||||
|
||||
WORKDIR /usr/local/searx
|
||||
|
||||
RUN addgroup -g ${SEARX_GID} searx && \
|
||||
adduser -u ${SEARX_UID} -D -h /usr/local/searx -s /bin/sh -G searx searx
|
||||
|
||||
COPY requirements.txt ./requirements.txt
|
||||
|
||||
RUN apk -U upgrade \
|
||||
&& apk add -t build-dependencies \
|
||||
RUN apk upgrade --no-cache \
|
||||
&& apk add --no-cache -t build-dependencies \
|
||||
build-base \
|
||||
py3-setuptools \
|
||||
python3-dev \
|
||||
|
@ -38,7 +40,7 @@ RUN apk -U upgrade \
|
|||
openssl-dev \
|
||||
tar \
|
||||
git \
|
||||
&& apk add \
|
||||
&& apk add --no-cache \
|
||||
ca-certificates \
|
||||
su-exec \
|
||||
python3 \
|
||||
|
@ -50,8 +52,7 @@ RUN apk -U upgrade \
|
|||
uwsgi-python3 \
|
||||
&& pip3 install --upgrade pip \
|
||||
&& pip3 install --no-cache -r requirements.txt \
|
||||
&& apk del build-dependencies \
|
||||
&& rm -f /var/cache/apk/*
|
||||
&& apk del build-dependencies
|
||||
|
||||
COPY --chown=searx:searx . .
|
||||
|
||||
|
@ -62,7 +63,6 @@ RUN su searx -c "/usr/bin/python3 -m compileall -q searx"; \
|
|||
echo "VERSION_STRING = VERSION_STRING + \"-$VERSION_GITCOMMIT\"" >> /usr/local/searx/searx/version.py; \
|
||||
fi
|
||||
|
||||
ENTRYPOINT ["/sbin/tini","--","/usr/local/searx/dockerfiles/docker-entrypoint.sh"]
|
||||
|
||||
# Keep this argument at the end since it change each time
|
||||
ARG LABEL_DATE=
|
||||
|
|
|
@ -18,7 +18,7 @@ from lxml import html
|
|||
from searx import logger, utils
|
||||
from searx.engines.xpath import extract_text
|
||||
from searx.url_utils import urlencode
|
||||
from searx.utils import match_language, gen_useragent
|
||||
from searx.utils import match_language, gen_useragent, eval_xpath
|
||||
|
||||
logger = logger.getChild('bing engine')
|
||||
|
||||
|
@ -65,11 +65,11 @@ def response(resp):
|
|||
|
||||
dom = html.fromstring(resp.text)
|
||||
# parse results
|
||||
for result in dom.xpath('//div[@class="sa_cc"]'):
|
||||
link = result.xpath('.//h3/a')[0]
|
||||
for result in eval_xpath(dom, '//div[@class="sa_cc"]'):
|
||||
link = eval_xpath(result, './/h3/a')[0]
|
||||
url = link.attrib.get('href')
|
||||
title = extract_text(link)
|
||||
content = extract_text(result.xpath('.//p'))
|
||||
content = extract_text(eval_xpath(result, './/p'))
|
||||
|
||||
# append result
|
||||
results.append({'url': url,
|
||||
|
@ -77,11 +77,11 @@ def response(resp):
|
|||
'content': content})
|
||||
|
||||
# parse results again if nothing is found yet
|
||||
for result in dom.xpath('//li[@class="b_algo"]'):
|
||||
link = result.xpath('.//h2/a')[0]
|
||||
for result in eval_xpath(dom, '//li[@class="b_algo"]'):
|
||||
link = eval_xpath(result, './/h2/a')[0]
|
||||
url = link.attrib.get('href')
|
||||
title = extract_text(link)
|
||||
content = extract_text(result.xpath('.//p'))
|
||||
content = extract_text(eval_xpath(result, './/p'))
|
||||
|
||||
# append result
|
||||
results.append({'url': url,
|
||||
|
@ -89,7 +89,7 @@ def response(resp):
|
|||
'content': content})
|
||||
|
||||
try:
|
||||
result_len_container = "".join(dom.xpath('//span[@class="sb_count"]/text()'))
|
||||
result_len_container = "".join(eval_xpath(dom, '//span[@class="sb_count"]/text()'))
|
||||
result_len_container = utils.to_string(result_len_container)
|
||||
if "-" in result_len_container:
|
||||
# Remove the part "from-to" for paginated request ...
|
||||
|
@ -113,9 +113,9 @@ def response(resp):
|
|||
def _fetch_supported_languages(resp):
|
||||
supported_languages = []
|
||||
dom = html.fromstring(resp.text)
|
||||
options = dom.xpath('//div[@id="limit-languages"]//input')
|
||||
options = eval_xpath(dom, '//div[@id="limit-languages"]//input')
|
||||
for option in options:
|
||||
code = option.xpath('./@id')[0].replace('_', '-')
|
||||
code = eval_xpath(option, './@id')[0].replace('_', '-')
|
||||
if code == 'nb':
|
||||
code = 'no'
|
||||
supported_languages.append(code)
|
||||
|
|
|
@ -11,7 +11,7 @@
|
|||
|
||||
import re
|
||||
from lxml import html
|
||||
from searx.utils import is_valid_lang
|
||||
from searx.utils import is_valid_lang, eval_xpath
|
||||
from searx.url_utils import urljoin
|
||||
|
||||
categories = ['general']
|
||||
|
@ -47,14 +47,14 @@ def response(resp):
|
|||
|
||||
dom = html.fromstring(resp.text)
|
||||
|
||||
for k, result in enumerate(dom.xpath(results_xpath)[1:]):
|
||||
for k, result in enumerate(eval_xpath(dom, results_xpath)[1:]):
|
||||
try:
|
||||
from_result, to_results_raw = result.xpath('./td')
|
||||
from_result, to_results_raw = eval_xpath(result, './td')
|
||||
except:
|
||||
continue
|
||||
|
||||
to_results = []
|
||||
for to_result in to_results_raw.xpath('./p/a'):
|
||||
for to_result in eval_xpath(to_results_raw, './p/a'):
|
||||
t = to_result.text_content()
|
||||
if t.strip():
|
||||
to_results.append(to_result.text_content())
|
||||
|
|
|
@ -11,6 +11,7 @@
|
|||
|
||||
from lxml.html import fromstring
|
||||
from searx.engines.xpath import extract_text
|
||||
from searx.utils import eval_xpath
|
||||
from searx.url_utils import urlencode
|
||||
|
||||
# engine dependent config
|
||||
|
@ -45,16 +46,16 @@ def response(resp):
|
|||
|
||||
# parse results
|
||||
# Quickhits
|
||||
for r in doc.xpath('//div[@class="search_quickresult"]/ul/li'):
|
||||
for r in eval_xpath(doc, '//div[@class="search_quickresult"]/ul/li'):
|
||||
try:
|
||||
res_url = r.xpath('.//a[@class="wikilink1"]/@href')[-1]
|
||||
res_url = eval_xpath(r, './/a[@class="wikilink1"]/@href')[-1]
|
||||
except:
|
||||
continue
|
||||
|
||||
if not res_url:
|
||||
continue
|
||||
|
||||
title = extract_text(r.xpath('.//a[@class="wikilink1"]/@title'))
|
||||
title = extract_text(eval_xpath(r, './/a[@class="wikilink1"]/@title'))
|
||||
|
||||
# append result
|
||||
results.append({'title': title,
|
||||
|
@ -62,13 +63,13 @@ def response(resp):
|
|||
'url': base_url + res_url})
|
||||
|
||||
# Search results
|
||||
for r in doc.xpath('//dl[@class="search_results"]/*'):
|
||||
for r in eval_xpath(doc, '//dl[@class="search_results"]/*'):
|
||||
try:
|
||||
if r.tag == "dt":
|
||||
res_url = r.xpath('.//a[@class="wikilink1"]/@href')[-1]
|
||||
title = extract_text(r.xpath('.//a[@class="wikilink1"]/@title'))
|
||||
res_url = eval_xpath(r, './/a[@class="wikilink1"]/@href')[-1]
|
||||
title = extract_text(eval_xpath(r, './/a[@class="wikilink1"]/@title'))
|
||||
elif r.tag == "dd":
|
||||
content = extract_text(r.xpath('.'))
|
||||
content = extract_text(eval_xpath(r, '.'))
|
||||
|
||||
# append result
|
||||
results.append({'title': title,
|
||||
|
|
|
@ -18,7 +18,7 @@ from json import loads
|
|||
from searx.engines.xpath import extract_text
|
||||
from searx.poolrequests import get
|
||||
from searx.url_utils import urlencode
|
||||
from searx.utils import match_language
|
||||
from searx.utils import match_language, eval_xpath
|
||||
|
||||
# engine dependent config
|
||||
categories = ['general']
|
||||
|
@ -106,19 +106,19 @@ def response(resp):
|
|||
doc = fromstring(resp.text)
|
||||
|
||||
# parse results
|
||||
for i, r in enumerate(doc.xpath(result_xpath)):
|
||||
for i, r in enumerate(eval_xpath(doc, result_xpath)):
|
||||
if i >= 30:
|
||||
break
|
||||
try:
|
||||
res_url = r.xpath(url_xpath)[-1]
|
||||
res_url = eval_xpath(r, url_xpath)[-1]
|
||||
except:
|
||||
continue
|
||||
|
||||
if not res_url:
|
||||
continue
|
||||
|
||||
title = extract_text(r.xpath(title_xpath))
|
||||
content = extract_text(r.xpath(content_xpath))
|
||||
title = extract_text(eval_xpath(r, title_xpath))
|
||||
content = extract_text(eval_xpath(r, content_xpath))
|
||||
|
||||
# append result
|
||||
results.append({'title': title,
|
||||
|
|
|
@ -1,3 +1,14 @@
|
|||
"""
|
||||
DuckDuckGo (definitions)
|
||||
|
||||
- `Instant Answer API`_
|
||||
- `DuckDuckGo query`_
|
||||
|
||||
.. _Instant Answer API: https://duckduckgo.com/api
|
||||
.. _DuckDuckGo query: https://api.duckduckgo.com/?q=DuckDuckGo&format=json&pretty=1
|
||||
|
||||
"""
|
||||
|
||||
import json
|
||||
from lxml import html
|
||||
from re import compile
|
||||
|
@ -25,7 +36,8 @@ def result_to_text(url, text, htmlResult):
|
|||
def request(query, params):
|
||||
params['url'] = url.format(query=urlencode({'q': query}))
|
||||
language = match_language(params['language'], supported_languages, language_aliases)
|
||||
params['headers']['Accept-Language'] = language.split('-')[0]
|
||||
language = language.split('-')[0]
|
||||
params['headers']['Accept-Language'] = language
|
||||
return params
|
||||
|
||||
|
||||
|
@ -43,8 +55,9 @@ def response(resp):
|
|||
|
||||
# add answer if there is one
|
||||
answer = search_res.get('Answer', '')
|
||||
if answer != '':
|
||||
results.append({'answer': html_to_text(answer)})
|
||||
if answer:
|
||||
if search_res.get('AnswerType', '') not in ['calc']:
|
||||
results.append({'answer': html_to_text(answer)})
|
||||
|
||||
# add infobox
|
||||
if 'Definition' in search_res:
|
||||
|
|
|
@ -11,6 +11,7 @@
|
|||
from lxml import html, etree
|
||||
import re
|
||||
from searx.engines.xpath import extract_text
|
||||
from searx.utils import eval_xpath
|
||||
from searx.url_utils import quote, urljoin
|
||||
from searx import logger
|
||||
|
||||
|
@ -52,9 +53,9 @@ def response(resp):
|
|||
dom = html.fromstring(resp.text)
|
||||
|
||||
try:
|
||||
number_of_results_string = re.sub('[^0-9]', '', dom.xpath(
|
||||
'//a[@class="active" and contains(@href,"/suchen/dudenonline")]/span/text()')[0]
|
||||
)
|
||||
number_of_results_string =\
|
||||
re.sub('[^0-9]', '',
|
||||
eval_xpath(dom, '//a[@class="active" and contains(@href,"/suchen/dudenonline")]/span/text()')[0])
|
||||
|
||||
results.append({'number_of_results': int(number_of_results_string)})
|
||||
|
||||
|
@ -62,12 +63,12 @@ def response(resp):
|
|||
logger.debug("Couldn't read number of results.")
|
||||
pass
|
||||
|
||||
for result in dom.xpath('//section[not(contains(@class, "essay"))]'):
|
||||
for result in eval_xpath(dom, '//section[not(contains(@class, "essay"))]'):
|
||||
try:
|
||||
url = result.xpath('.//h2/a')[0].get('href')
|
||||
url = eval_xpath(result, './/h2/a')[0].get('href')
|
||||
url = urljoin(base_url, url)
|
||||
title = result.xpath('string(.//h2/a)').strip()
|
||||
content = extract_text(result.xpath('.//p'))
|
||||
title = eval_xpath(result, 'string(.//h2/a)').strip()
|
||||
content = extract_text(eval_xpath(result, './/p'))
|
||||
# append result
|
||||
results.append({'url': url,
|
||||
'title': title,
|
||||
|
|
|
@ -15,6 +15,7 @@ from json import loads
|
|||
from time import time
|
||||
from lxml.html import fromstring
|
||||
from searx.url_utils import urlencode
|
||||
from searx.utils import eval_xpath
|
||||
|
||||
# engine dependent config
|
||||
categories = ['general']
|
||||
|
@ -99,9 +100,9 @@ def response(resp):
|
|||
def _fetch_supported_languages(resp):
|
||||
supported_languages = []
|
||||
dom = fromstring(resp.text)
|
||||
links = dom.xpath('//span[@id="menu2"]/a')
|
||||
links = eval_xpath(dom, '//span[@id="menu2"]/a')
|
||||
for link in links:
|
||||
href = link.xpath('./@href')[0].split('lang%3A')
|
||||
href = eval_xpath(link, './@href')[0].split('lang%3A')
|
||||
if len(href) == 2:
|
||||
code = href[1].split('_')
|
||||
if len(code) == 2:
|
||||
|
|
|
@ -14,7 +14,7 @@ from lxml import html, etree
|
|||
from searx.engines.xpath import extract_text, extract_url
|
||||
from searx import logger
|
||||
from searx.url_utils import urlencode, urlparse, parse_qsl
|
||||
from searx.utils import match_language
|
||||
from searx.utils import match_language, eval_xpath
|
||||
|
||||
logger = logger.getChild('google engine')
|
||||
|
||||
|
@ -156,7 +156,7 @@ def parse_url(url_string, google_hostname):
|
|||
|
||||
# returns extract_text on the first result selected by the xpath or None
|
||||
def extract_text_from_dom(result, xpath):
|
||||
r = result.xpath(xpath)
|
||||
r = eval_xpath(result, xpath)
|
||||
if len(r) > 0:
|
||||
return extract_text(r[0])
|
||||
return None
|
||||
|
@ -227,21 +227,21 @@ def response(resp):
|
|||
# convert the text to dom
|
||||
dom = html.fromstring(resp.text)
|
||||
|
||||
instant_answer = dom.xpath('//div[@id="_vBb"]//text()')
|
||||
instant_answer = eval_xpath(dom, '//div[@id="_vBb"]//text()')
|
||||
if instant_answer:
|
||||
results.append({'answer': u' '.join(instant_answer)})
|
||||
try:
|
||||
results_num = int(dom.xpath('//div[@id="resultStats"]//text()')[0]
|
||||
results_num = int(eval_xpath(dom, '//div[@id="resultStats"]//text()')[0]
|
||||
.split()[1].replace(',', ''))
|
||||
results.append({'number_of_results': results_num})
|
||||
except:
|
||||
pass
|
||||
|
||||
# parse results
|
||||
for result in dom.xpath(results_xpath):
|
||||
for result in eval_xpath(dom, results_xpath):
|
||||
try:
|
||||
title = extract_text(result.xpath(title_xpath)[0])
|
||||
url = parse_url(extract_url(result.xpath(url_xpath), google_url), google_hostname)
|
||||
title = extract_text(eval_xpath(result, title_xpath)[0])
|
||||
url = parse_url(extract_url(eval_xpath(result, url_xpath), google_url), google_hostname)
|
||||
parsed_url = urlparse(url, google_hostname)
|
||||
|
||||
# map result
|
||||
|
@ -250,7 +250,7 @@ def response(resp):
|
|||
continue
|
||||
# if parsed_url.path.startswith(maps_path) or parsed_url.netloc.startswith(map_hostname_start):
|
||||
# print "yooooo"*30
|
||||
# x = result.xpath(map_near)
|
||||
# x = eval_xpath(result, map_near)
|
||||
# if len(x) > 0:
|
||||
# # map : near the location
|
||||
# results = results + parse_map_near(parsed_url, x, google_hostname)
|
||||
|
@ -287,11 +287,11 @@ def response(resp):
|
|||
continue
|
||||
|
||||
# parse suggestion
|
||||
for suggestion in dom.xpath(suggestion_xpath):
|
||||
for suggestion in eval_xpath(dom, suggestion_xpath):
|
||||
# append suggestion
|
||||
results.append({'suggestion': extract_text(suggestion)})
|
||||
|
||||
for correction in dom.xpath(spelling_suggestion_xpath):
|
||||
for correction in eval_xpath(dom, spelling_suggestion_xpath):
|
||||
results.append({'correction': extract_text(correction)})
|
||||
|
||||
# return results
|
||||
|
@ -300,9 +300,9 @@ def response(resp):
|
|||
|
||||
def parse_images(result, google_hostname):
|
||||
results = []
|
||||
for image in result.xpath(images_xpath):
|
||||
url = parse_url(extract_text(image.xpath(image_url_xpath)[0]), google_hostname)
|
||||
img_src = extract_text(image.xpath(image_img_src_xpath)[0])
|
||||
for image in eval_xpath(result, images_xpath):
|
||||
url = parse_url(extract_text(eval_xpath(image, image_url_xpath)[0]), google_hostname)
|
||||
img_src = extract_text(eval_xpath(image, image_img_src_xpath)[0])
|
||||
|
||||
# append result
|
||||
results.append({'url': url,
|
||||
|
@ -389,10 +389,10 @@ def attributes_to_html(attributes):
|
|||
def _fetch_supported_languages(resp):
|
||||
supported_languages = {}
|
||||
dom = html.fromstring(resp.text)
|
||||
options = dom.xpath('//*[@id="langSec"]//input[@name="lr"]')
|
||||
options = eval_xpath(dom, '//*[@id="langSec"]//input[@name="lr"]')
|
||||
for option in options:
|
||||
code = option.xpath('./@value')[0].split('_')[-1]
|
||||
name = option.xpath('./@data-name')[0].title()
|
||||
code = eval_xpath(option, './@value')[0].split('_')[-1]
|
||||
name = eval_xpath(option, './@data-name')[0].title()
|
||||
supported_languages[code] = {"name": name}
|
||||
|
||||
return supported_languages
|
||||
|
|
78
searx/engines/seedpeer.py
Normal file
78
searx/engines/seedpeer.py
Normal file
|
@ -0,0 +1,78 @@
|
|||
# Seedpeer (Videos, Music, Files)
|
||||
#
|
||||
# @website https://seedpeer.me
|
||||
# @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 json import loads
|
||||
from operator import itemgetter
|
||||
from searx.url_utils import quote, urljoin
|
||||
from searx.engines.xpath import extract_text
|
||||
|
||||
|
||||
url = 'https://seedpeer.me/'
|
||||
search_url = url + 'search/{search_term}?page={page_no}'
|
||||
torrent_file_url = url + 'torrent/{torrent_hash}'
|
||||
|
||||
# specific xpath variables
|
||||
script_xpath = '//script[@type="text/javascript"][not(@src)]'
|
||||
torrent_xpath = '(//table)[2]/tbody/tr'
|
||||
link_xpath = '(./td)[1]/a/@href'
|
||||
age_xpath = '(./td)[2]'
|
||||
size_xpath = '(./td)[3]'
|
||||
|
||||
|
||||
# do search-request
|
||||
def request(query, params):
|
||||
params['url'] = search_url.format(search_term=quote(query),
|
||||
page_no=params['pageno'])
|
||||
return params
|
||||
|
||||
|
||||
# get response from search-request
|
||||
def response(resp):
|
||||
results = []
|
||||
dom = html.fromstring(resp.text)
|
||||
result_rows = dom.xpath(torrent_xpath)
|
||||
|
||||
try:
|
||||
script_element = dom.xpath(script_xpath)[0]
|
||||
json_string = script_element.text[script_element.text.find('{'):]
|
||||
torrents_json = loads(json_string)
|
||||
except:
|
||||
return []
|
||||
|
||||
# parse results
|
||||
for torrent_row, torrent_json in zip(result_rows, torrents_json['data']['list']):
|
||||
title = torrent_json['name']
|
||||
seed = int(torrent_json['seeds'])
|
||||
leech = int(torrent_json['peers'])
|
||||
size = int(torrent_json['size'])
|
||||
torrent_hash = torrent_json['hash']
|
||||
|
||||
torrentfile = torrent_file_url.format(torrent_hash=torrent_hash)
|
||||
magnetlink = 'magnet:?xt=urn:btih:{}'.format(torrent_hash)
|
||||
|
||||
age = extract_text(torrent_row.xpath(age_xpath))
|
||||
link = torrent_row.xpath(link_xpath)[0]
|
||||
|
||||
href = urljoin(url, link)
|
||||
|
||||
# append result
|
||||
results.append({'url': href,
|
||||
'title': title,
|
||||
'content': age,
|
||||
'seed': seed,
|
||||
'leech': leech,
|
||||
'filesize': size,
|
||||
'torrentfile': torrentfile,
|
||||
'magnetlink': magnetlink,
|
||||
'template': 'torrent.html'})
|
||||
|
||||
# return results sorted by seeder
|
||||
return sorted(results, key=itemgetter('seed'), reverse=True)
|
|
@ -51,7 +51,9 @@ def get_client_id():
|
|||
|
||||
if response.ok:
|
||||
tree = html.fromstring(response.content)
|
||||
script_tags = tree.xpath("//script[contains(@src, '/assets/app')]")
|
||||
# script_tags has been moved from /assets/app/ to /assets/ path. I
|
||||
# found client_id in https://a-v2.sndcdn.com/assets/49-a0c01933-3.js
|
||||
script_tags = tree.xpath("//script[contains(@src, '/assets/')]")
|
||||
app_js_urls = [script_tag.get('src') for script_tag in script_tags if script_tag is not None]
|
||||
|
||||
# extracts valid app_js urls from soundcloud.com content
|
||||
|
|
|
@ -16,6 +16,7 @@ from datetime import datetime, timedelta
|
|||
import re
|
||||
from searx.engines.xpath import extract_text
|
||||
from searx.languages import language_codes
|
||||
from searx.utils import eval_xpath
|
||||
|
||||
# engine dependent config
|
||||
categories = ['general']
|
||||
|
@ -70,8 +71,8 @@ def response(resp):
|
|||
dom = html.fromstring(resp.text)
|
||||
|
||||
# parse results
|
||||
for result in dom.xpath(results_xpath):
|
||||
links = result.xpath(link_xpath)
|
||||
for result in eval_xpath(dom, results_xpath):
|
||||
links = eval_xpath(result, link_xpath)
|
||||
if not links:
|
||||
continue
|
||||
link = links[0]
|
||||
|
@ -87,8 +88,8 @@ def response(resp):
|
|||
|
||||
title = extract_text(link)
|
||||
|
||||
if result.xpath(content_xpath):
|
||||
content = extract_text(result.xpath(content_xpath))
|
||||
if eval_xpath(result, content_xpath):
|
||||
content = extract_text(eval_xpath(result, content_xpath))
|
||||
else:
|
||||
content = ''
|
||||
|
||||
|
|
|
@ -16,7 +16,7 @@ from searx.poolrequests import get
|
|||
from searx.engines.xpath import extract_text
|
||||
from searx.engines.wikipedia import _fetch_supported_languages, supported_languages_url
|
||||
from searx.url_utils import urlencode
|
||||
from searx.utils import match_language
|
||||
from searx.utils import match_language, eval_xpath
|
||||
|
||||
from json import loads
|
||||
from lxml.html import fromstring
|
||||
|
@ -57,22 +57,6 @@ language_fallback_xpath = '//sup[contains(@class,"wb-language-fallback-indicator
|
|||
calendar_name_xpath = './/sup[contains(@class,"wb-calendar-name")]'
|
||||
media_xpath = value_xpath + '//div[contains(@class,"commons-media-caption")]//a'
|
||||
|
||||
# xpath_cache
|
||||
xpath_cache = {}
|
||||
|
||||
|
||||
def get_xpath(xpath_str):
|
||||
result = xpath_cache.get(xpath_str, None)
|
||||
if not result:
|
||||
result = etree.XPath(xpath_str)
|
||||
xpath_cache[xpath_str] = result
|
||||
return result
|
||||
|
||||
|
||||
def eval_xpath(element, xpath_str):
|
||||
xpath = get_xpath(xpath_str)
|
||||
return xpath(element)
|
||||
|
||||
|
||||
def get_id_cache(result):
|
||||
id_cache = {}
|
||||
|
|
|
@ -1,6 +1,6 @@
|
|||
from lxml import html
|
||||
from lxml.etree import _ElementStringResult, _ElementUnicodeResult
|
||||
from searx.utils import html_to_text
|
||||
from searx.utils import html_to_text, eval_xpath
|
||||
from searx.url_utils import unquote, urlencode, urljoin, urlparse
|
||||
|
||||
search_url = None
|
||||
|
@ -104,15 +104,15 @@ def response(resp):
|
|||
results = []
|
||||
dom = html.fromstring(resp.text)
|
||||
if results_xpath:
|
||||
for result in dom.xpath(results_xpath):
|
||||
url = extract_url(result.xpath(url_xpath), search_url)
|
||||
title = extract_text(result.xpath(title_xpath))
|
||||
content = extract_text(result.xpath(content_xpath))
|
||||
for result in eval_xpath(dom, results_xpath):
|
||||
url = extract_url(eval_xpath(result, url_xpath), search_url)
|
||||
title = extract_text(eval_xpath(result, title_xpath))
|
||||
content = extract_text(eval_xpath(result, content_xpath))
|
||||
tmp_result = {'url': url, 'title': title, 'content': content}
|
||||
|
||||
# add thumbnail if available
|
||||
if thumbnail_xpath:
|
||||
thumbnail_xpath_result = result.xpath(thumbnail_xpath)
|
||||
thumbnail_xpath_result = eval_xpath(result, thumbnail_xpath)
|
||||
if len(thumbnail_xpath_result) > 0:
|
||||
tmp_result['img_src'] = extract_url(thumbnail_xpath_result, search_url)
|
||||
|
||||
|
@ -120,14 +120,14 @@ def response(resp):
|
|||
else:
|
||||
for url, title, content in zip(
|
||||
(extract_url(x, search_url) for
|
||||
x in dom.xpath(url_xpath)),
|
||||
map(extract_text, dom.xpath(title_xpath)),
|
||||
map(extract_text, dom.xpath(content_xpath))
|
||||
x in eval_xpath(dom, url_xpath)),
|
||||
map(extract_text, eval_xpath(dom, title_xpath)),
|
||||
map(extract_text, eval_xpath(dom, content_xpath))
|
||||
):
|
||||
results.append({'url': url, 'title': title, 'content': content})
|
||||
|
||||
if not suggestion_xpath:
|
||||
return results
|
||||
for suggestion in dom.xpath(suggestion_xpath):
|
||||
for suggestion in eval_xpath(dom, suggestion_xpath):
|
||||
results.append({'suggestion': extract_text(suggestion)})
|
||||
return results
|
||||
|
|
|
@ -14,7 +14,7 @@
|
|||
from lxml import html
|
||||
from searx.engines.xpath import extract_text, extract_url
|
||||
from searx.url_utils import unquote, urlencode
|
||||
from searx.utils import match_language
|
||||
from searx.utils import match_language, eval_xpath
|
||||
|
||||
# engine dependent config
|
||||
categories = ['general']
|
||||
|
@ -109,21 +109,21 @@ def response(resp):
|
|||
dom = html.fromstring(resp.text)
|
||||
|
||||
try:
|
||||
results_num = int(dom.xpath('//div[@class="compPagination"]/span[last()]/text()')[0]
|
||||
results_num = int(eval_xpath(dom, '//div[@class="compPagination"]/span[last()]/text()')[0]
|
||||
.split()[0].replace(',', ''))
|
||||
results.append({'number_of_results': results_num})
|
||||
except:
|
||||
pass
|
||||
|
||||
# parse results
|
||||
for result in dom.xpath(results_xpath):
|
||||
for result in eval_xpath(dom, results_xpath):
|
||||
try:
|
||||
url = parse_url(extract_url(result.xpath(url_xpath), search_url))
|
||||
title = extract_text(result.xpath(title_xpath)[0])
|
||||
url = parse_url(extract_url(eval_xpath(result, url_xpath), search_url))
|
||||
title = extract_text(eval_xpath(result, title_xpath)[0])
|
||||
except:
|
||||
continue
|
||||
|
||||
content = extract_text(result.xpath(content_xpath)[0])
|
||||
content = extract_text(eval_xpath(result, content_xpath)[0])
|
||||
|
||||
# append result
|
||||
results.append({'url': url,
|
||||
|
@ -131,7 +131,7 @@ def response(resp):
|
|||
'content': content})
|
||||
|
||||
# if no suggestion found, return results
|
||||
suggestions = dom.xpath(suggestion_xpath)
|
||||
suggestions = eval_xpath(dom, suggestion_xpath)
|
||||
if not suggestions:
|
||||
return results
|
||||
|
||||
|
@ -148,9 +148,9 @@ def response(resp):
|
|||
def _fetch_supported_languages(resp):
|
||||
supported_languages = []
|
||||
dom = html.fromstring(resp.text)
|
||||
options = dom.xpath('//div[@id="yschlang"]/span/label/input')
|
||||
options = eval_xpath(dom, '//div[@id="yschlang"]/span/label/input')
|
||||
for option in options:
|
||||
code_parts = option.xpath('./@value')[0][5:].split('_')
|
||||
code_parts = eval_xpath(option, './@value')[0][5:].split('_')
|
||||
if len(code_parts) == 2:
|
||||
code = code_parts[0] + '-' + code_parts[1].upper()
|
||||
else:
|
||||
|
|
|
@ -67,8 +67,9 @@ def merge_two_infoboxes(infobox1, infobox2):
|
|||
|
||||
for url2 in infobox2.get('urls', []):
|
||||
unique_url = True
|
||||
for url1 in infobox1.get('urls', []):
|
||||
if compare_urls(urlparse(url1.get('url', '')), urlparse(url2.get('url', ''))):
|
||||
parsed_url2 = urlparse(url2.get('url', ''))
|
||||
for url1 in urls1:
|
||||
if compare_urls(urlparse(url1.get('url', '')), parsed_url2):
|
||||
unique_url = False
|
||||
break
|
||||
if unique_url:
|
||||
|
@ -188,8 +189,9 @@ class ResultContainer(object):
|
|||
add_infobox = True
|
||||
infobox_id = infobox.get('id', None)
|
||||
if infobox_id is not None:
|
||||
parsed_url_infobox_id = urlparse(infobox_id)
|
||||
for existingIndex in self.infoboxes:
|
||||
if compare_urls(urlparse(existingIndex.get('id', '')), urlparse(infobox_id)):
|
||||
if compare_urls(urlparse(existingIndex.get('id', '')), parsed_url_infobox_id):
|
||||
merge_two_infoboxes(existingIndex, infobox)
|
||||
add_infobox = False
|
||||
|
||||
|
|
|
@ -748,6 +748,11 @@ engines:
|
|||
page_size : 10
|
||||
disabled : True
|
||||
|
||||
- name : seedpeer
|
||||
shortcut : speu
|
||||
engine : seedpeer
|
||||
categories: files, music, videos
|
||||
|
||||
# - name : yacy
|
||||
# engine : yacy
|
||||
# shortcut : ya
|
||||
|
|
|
@ -4,7 +4,7 @@
|
|||
{% endif %}
|
||||
<h3 class="result_title"><a href="{{ result.url }}" {% if results_on_new_tab %}target="_blank" rel="noopener noreferrer"{% else %}rel="noreferrer"{% endif %}>{{ result.title|safe }}</a></h3>
|
||||
{% if result.content %}<span class="content">{{ result.content|safe }}</span><br />{% endif %}
|
||||
{% if result.seed %}<span class="stats">{{ _('Seeder') }} : {{ result.seed }}, {{ _('Leecher') }} : {{ result.leech }}</span><br />{% endif %}
|
||||
{% if result.seed is defined %}<span class="stats">{{ _('Seeder') }} : {{ result.seed }}, {{ _('Leecher') }} : {{ result.leech }}</span><br />{% endif %}
|
||||
<span>
|
||||
{% if result.magnetlink %}<a href="{{ result.magnetlink }}" class="magnetlink">{{ _('magnet link') }}</a>{% endif %}
|
||||
{% if result.torrentfile %}<a href="{{ result.torrentfile }}" class="torrentfile" {% if results_on_new_tab %}target="_blank" rel="noopener noreferrer"{% else %}rel="noreferrer"{% endif %}>{{ _('torrent file') }}</a>{% endif %}
|
||||
|
|
|
@ -8,6 +8,6 @@
|
|||
<p>
|
||||
{% if result.magnetlink %}<a href="{{ result.magnetlink }}" class="magnetlink">{{ _('magnet link') }}</a>{% endif %}
|
||||
{% if result.torrentfile %}<a href="{{ result.torrentfile }}" {% if results_on_new_tab %}target="_blank" rel="noopener noreferrer"{% else %}rel="noreferrer"{% endif %} class="torrentfile">{{ _('torrent file') }}</a>{% endif %} -
|
||||
{% if result.seed %}<span class="stats">{{ _('Seeder') }} : {{ result.seed }}, {{ _('Leecher') }} : {{ result.leech }}</span>{% endif %}
|
||||
{% if result.seed is defined %}<span class="stats">{{ _('Seeder') }} : {{ result.seed }}, {{ _('Leecher') }} : {{ result.leech }}</span>{% endif %}
|
||||
</p>
|
||||
</div>
|
||||
|
|
|
@ -3,7 +3,7 @@
|
|||
{{ result_header(result, favicons) }}
|
||||
{{ result_sub_header(result) }}
|
||||
|
||||
{% if result.seed %}<p class="result-content">{{ icon('transfer') }} {{ _('Seeder') }} <span class="badge">{{ result.seed }}</span> • {{ _('Leecher') }} <span class="badge">{{ result.leech }}</span>{% endif %}
|
||||
{% if result.seed is defined %}<p class="result-content">{{ icon('transfer') }} {{ _('Seeder') }} <span class="badge">{{ result.seed }}</span> • {{ _('Leecher') }} <span class="badge">{{ result.leech }}</span>{% endif %}
|
||||
{% if result.filesize %}<br />{{ icon('floppy-disk') }} {{ _('Filesize') }}
|
||||
<span class="badge">
|
||||
{% if result.filesize < 1024 %}{{ result.filesize }} {{ _('Bytes') }}
|
||||
|
|
|
@ -6,7 +6,7 @@
|
|||
{% if result.magnetlink %}<p class="altlink"> • {{ result_link(result.magnetlink, icon('magnet') + _('magnet link'), "magnetlink") }}</p>{% endif %}
|
||||
{% if result.torrentfile %}<p class="altlink"> • {{ result_link(result.torrentfile, icon('download-alt') + _('torrent file'), "torrentfile") }}</p>{% endif %}
|
||||
|
||||
{% if result.seed %}<p class="stat"> • {{ icon('arrow-swap') }} {{ _('Seeder') }} <span class="badge">{{ result.seed }}</span> • {{ _('Leecher') }} <span class="badge">{{ result.leech }}</span></p>{% endif %}
|
||||
{% if result.seed is defined %}<p class="stat"> • {{ icon('arrow-swap') }} {{ _('Seeder') }} <span class="badge">{{ result.seed }}</span> • {{ _('Leecher') }} <span class="badge">{{ result.leech }}</span></p>{% endif %}
|
||||
|
||||
{%- if result.filesize %}<p class="stat">{{ icon('floppy-disk') }} {{ _('Filesize') }}<span class="badge">
|
||||
{%- if result.filesize < 1024 %}{{ result.filesize }} {{ _('Bytes') }}
|
||||
|
|
|
@ -13,6 +13,7 @@ from numbers import Number
|
|||
from os.path import splitext, join
|
||||
from io import open
|
||||
from random import choice
|
||||
from lxml.etree import XPath
|
||||
import sys
|
||||
import json
|
||||
|
||||
|
@ -51,6 +52,7 @@ ecma_unescape2_re = re.compile(r'%([0-9a-fA-F]{2})', re.UNICODE)
|
|||
useragents = json.loads(open(os.path.dirname(os.path.realpath(__file__))
|
||||
+ "/data/useragents.json", 'r', encoding='utf-8').read())
|
||||
|
||||
xpath_cache = dict()
|
||||
lang_to_lc_cache = dict()
|
||||
|
||||
|
||||
|
@ -450,3 +452,16 @@ def get_engine_from_settings(name):
|
|||
return engine
|
||||
|
||||
return {}
|
||||
|
||||
|
||||
def get_xpath(xpath_str):
|
||||
result = xpath_cache.get(xpath_str, None)
|
||||
if result is None:
|
||||
result = XPath(xpath_str)
|
||||
xpath_cache[xpath_str] = result
|
||||
return result
|
||||
|
||||
|
||||
def eval_xpath(element, xpath_str):
|
||||
xpath = get_xpath(xpath_str)
|
||||
return xpath(element)
|
||||
|
|
|
@ -157,20 +157,18 @@ outgoing_proxies = settings['outgoing'].get('proxies') or None
|
|||
|
||||
@babel.localeselector
|
||||
def get_locale():
|
||||
locale = request.accept_languages.best_match(settings['locales'].keys())
|
||||
|
||||
if request.preferences.get_value('locale') != '':
|
||||
locale = request.preferences.get_value('locale')
|
||||
if 'locale' in request.form\
|
||||
and request.form['locale'] in settings['locales']:
|
||||
return request.form['locale']
|
||||
|
||||
if 'locale' in request.args\
|
||||
and request.args['locale'] in settings['locales']:
|
||||
locale = request.args['locale']
|
||||
return request.args['locale']
|
||||
|
||||
if 'locale' in request.form\
|
||||
and request.form['locale'] in settings['locales']:
|
||||
locale = request.form['locale']
|
||||
if request.preferences.get_value('locale') != '':
|
||||
return request.preferences.get_value('locale')
|
||||
|
||||
return locale
|
||||
return request.accept_languages.best_match(settings['locales'].keys())
|
||||
|
||||
|
||||
# code-highlighter
|
||||
|
|
66
tests/unit/engines/test_seedpeer.py
Normal file
66
tests/unit/engines/test_seedpeer.py
Normal file
|
@ -0,0 +1,66 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
from collections import defaultdict
|
||||
import mock
|
||||
from searx.engines import seedpeer
|
||||
from searx.testing import SearxTestCase
|
||||
|
||||
|
||||
class TestBtdiggEngine(SearxTestCase):
|
||||
|
||||
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', params['url'])
|
||||
|
||||
def test_response(self):
|
||||
self.assertRaises(AttributeError, seedpeer.response, None)
|
||||
self.assertRaises(AttributeError, seedpeer.response, [])
|
||||
self.assertRaises(AttributeError, seedpeer.response, '')
|
||||
self.assertRaises(AttributeError, seedpeer.response, '[]')
|
||||
|
||||
response = mock.Mock(text='<html></html>')
|
||||
self.assertEqual(seedpeer.response(response), [])
|
||||
|
||||
html = u"""
|
||||
<html>
|
||||
<head>
|
||||
<script></script>
|
||||
<script type="text/javascript" src="not_here.js"></script>
|
||||
<script type="text/javascript">
|
||||
window.initialData=
|
||||
{"data": {"list": [{"name": "Title", "seeds": "10", "peers": "20", "size": "1024", "hash": "abc123"}]}}
|
||||
</script>
|
||||
</head>
|
||||
<body>
|
||||
<table></table>
|
||||
<table>
|
||||
<thead><tr></tr></thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td><a href="link">Title</a></td>
|
||||
<td>1 year</td>
|
||||
<td>1 KB</td>
|
||||
<td>10</td>
|
||||
<td>20</td>
|
||||
<td></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</body>
|
||||
</html>
|
||||
"""
|
||||
response = mock.Mock(text=html)
|
||||
results = seedpeer.response(response)
|
||||
self.assertEqual(type(results), list)
|
||||
self.assertEqual(len(results), 1)
|
||||
self.assertEqual(results[0]['title'], 'Title')
|
||||
self.assertEqual(results[0]['url'], 'https://seedpeer.me/link')
|
||||
self.assertEqual(results[0]['seed'], 10)
|
||||
self.assertEqual(results[0]['leech'], 20)
|
||||
self.assertEqual(results[0]['filesize'], 1024)
|
||||
self.assertEqual(results[0]['torrentfile'], 'https://seedpeer.me/torrent/abc123')
|
||||
self.assertEqual(results[0]['magnetlink'], 'magnet:?xt=urn:btih:abc123')
|
Loading…
Reference in a new issue