1
0
mirror of https://github.com/searxng/searxng.git synced 2024-11-14 16:50:11 +01:00
searxng/searx/engines/subtitleseeker.py

79 lines
2.0 KiB
Python
Raw Normal View History

## 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 cgi import escape
from urllib import quote_plus
from lxml import html
from searx.languages import language_codes
# 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 = ""
if resp.search_params['language'] != 'all':
search_lang = [lc[1]
for lc in language_codes
if lc[0][:2] == resp.search_params['language']][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 = escape(link.xpath(".//text()")[0])
content = result.xpath('.//div[contains(@class,"red")]//text()')[0]
content = content + " - "
text = result.xpath('.//div[contains(@class,"grey-web")]')[0]
content = content + html.tostring(text, method='text')
if result.xpath(".//span") != []:
content = content +\
2015-01-02 12:33:40 +01:00
" - (" +\
result.xpath(".//span//text()")[0].strip() +\
")"
# append result
results.append({'url': href,
'title': title,
'content': escape(content)})
# return results
return results