1
0
Fork 0
mirror of https://github.com/YunoHost-Apps/searx_ynh.git synced 2024-09-03 20:16:30 +02:00
searx_ynh/sources/searx/engines/vimeo.py

73 lines
2.1 KiB
Python
Raw Normal View History

2014-12-01 12:26:38 +01:00
## Vimeo (Videos)
#
# @website https://vimeo.com/
# @provide-api yes (http://developer.vimeo.com/api), they have a maximum count of queries/hour
#
# @using-api no (TODO, rewrite to api)
# @results HTML (using search portal)
# @stable no (HTML can change)
# @parse url, title, publishedDate, thumbnail
#
# @todo rewrite to api
# @todo set content-parameter with correct data
2014-05-10 11:56:19 +02:00
from urllib import urlencode
from HTMLParser import HTMLParser
from lxml import html
from searx.engines.xpath import extract_text
from dateutil import parser
2014-12-01 12:26:38 +01:00
# engine dependent config
categories = ['videos']
paging = True
2014-05-10 11:56:19 +02:00
2014-12-01 12:26:38 +01:00
# search-url
base_url = 'https://vimeo.com'
search_url = base_url + '/search/page:{pageno}?{query}'
# specific xpath variables
url_xpath = './a/@href'
content_xpath = './a/img/@src'
title_xpath = './a/div[@class="data"]/p[@class="title"]/text()'
results_xpath = '//div[@id="browse_content"]/ol/li'
publishedDate_xpath = './/p[@class="meta"]//attribute::datetime'
2014-05-10 11:56:19 +02:00
2014-12-01 12:26:38 +01:00
# do search-request
2014-05-10 11:56:19 +02:00
def request(query, params):
2014-12-01 12:26:38 +01:00
params['url'] = search_url.format(pageno=params['pageno'] ,
query=urlencode({'q': query}))
# TODO required?
params['cookies']['__utma'] = '00000000.000#0000000.0000000000.0000000000.0000000000.0'
2014-05-10 11:56:19 +02:00
return params
2014-12-01 12:26:38 +01:00
# get response from search-request
2014-05-10 11:56:19 +02:00
def response(resp):
results = []
2014-12-01 12:26:38 +01:00
2014-05-10 11:56:19 +02:00
dom = html.fromstring(resp.text)
p = HTMLParser()
2014-12-01 12:26:38 +01:00
# parse results
2014-05-10 11:56:19 +02:00
for result in dom.xpath(results_xpath):
url = base_url + result.xpath(url_xpath)[0]
title = p.unescape(extract_text(result.xpath(title_xpath)))
thumbnail = extract_text(result.xpath(content_xpath)[0])
publishedDate = parser.parse(extract_text(
result.xpath(publishedDate_xpath)[0]))
2014-12-01 12:26:38 +01:00
# append result
2014-05-10 11:56:19 +02:00
results.append({'url': url,
'title': title,
2014-12-01 12:26:38 +01:00
'content': '',
2014-05-10 11:56:19 +02:00
'template': 'videos.html',
'publishedDate': publishedDate,
'thumbnail': thumbnail})
2014-12-01 12:26:38 +01:00
# return results
2014-05-10 11:56:19 +02:00
return results