Icycoide/searxng
1
0
Fork 1
mirror of https://github.com/searxng/searxng.git synced 2025-08-03 10:32:21 +02:00
Code Issues Projects Releases Packages Wiki Activity

Subtitleseeker's unit test

Browse source
This commit is contained in:
Cqoicebordel 2015-02-06 16:39:59 +01:00
parent 9f13af8d3c
commit 3a4d6045c1
3 changed files with 178 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

15
searx/engines/subtitleseeker.py
View file

@ -12,6 +12,7 @@ from cgi import escape
from urllib import quote_plus
from lxml import html
from searx.languages import language_codes
from searx.engines.xpath import extract_text
# engine dependent config
categories = ['videos']
@ -20,7 +21,7 @@ language = ""
# search-url
url = 'http://www.subtitleseeker.com/'
search_url = url+'search/TITLES/{query}&p={pageno}'
search_url = url + 'search/TITLES/{query}&p={pageno}'
# specific xpath variables
results_xpath = '//div[@class="boxRows"]'
@ -44,7 +45,7 @@ def response(resp):
if resp.search_params['language'] != 'all':
search_lang = [lc[1]
for lc in language_codes
if lc[0][:2] == resp.search_params['language']][0]
if lc[0][:2] == resp.search_params['language'].split('_')[0]][0]
# parse results
for result in dom.xpath(results_xpath):
@ -56,17 +57,17 @@ def response(resp):
elif search_lang:
href = href + search_lang + '/'
title = escape(link.xpath(".//text()")[0])
title = escape(extract_text(link))
content = result.xpath('.//div[contains(@class,"red")]//text()')[0]
content = extract_text(result.xpath('.//div[contains(@class,"red")]'))
content = content + " - "
text = result.xpath('.//div[contains(@class,"grey-web")]')[0]
content = content + html.tostring(text, method='text')
text = extract_text(result.xpath('.//div[contains(@class,"grey-web")]')[0])
content = content + text
if result.xpath(".//span") != []:
content = content +\
" - (" +\
result.xpath(".//span//text()")[0].strip() +\
extract_text(result.xpath(".//span")) +\
")"
# append result