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

76 lines
2.3 KiB
Python
Raw Normal View History

2015-01-13 17:13:08 +01:00
# Vimeo (Videos)
2014-12-13 13:56:02 +01:00
#
2014-12-01 12:26:38 +01:00
# @website https://vimeo.com/
2014-12-13 13:56:02 +01:00
# @provide-api yes (http://developer.vimeo.com/api),
# they have a maximum count of queries/hour
#
2014-12-01 12:26:38 +01:00
# @using-api no (TODO, rewrite to api)
# @results HTML (using search portal)
# @stable no (HTML can change)
2015-01-13 17:13:08 +01:00
# @parse url, title, publishedDate, thumbnail, embedded
2014-12-01 12:26:38 +01:00
#
# @todo rewrite to api
# @todo set content-parameter with correct data
2014-05-10 11:56:19 +02:00
from urllib import urlencode
from lxml import html
2015-01-13 17:13:08 +01:00
from HTMLParser import HTMLParser
2014-05-10 11:56:19 +02:00
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
2015-09-08 23:05:37 +02:00
base_url = 'https://vimeo.com'
2014-12-01 12:26:38 +01:00
search_url = base_url + '/search/page:{pageno}?{query}'
# specific xpath variables
2015-09-08 23:05:37 +02:00
results_xpath = '//div[contains(@class,"results_grid")]/ul/li'
url_xpath = './/a/@href'
title_xpath = './/span[@class="title"]'
thumbnail_xpath = './/img[@class="js-clip_thumbnail_image"]/@src'
publishedDate_xpath = './/time/attribute::datetime'
2014-05-10 11:56:19 +02:00
2015-01-13 17:13:08 +01:00
embedded_url = '<iframe data-src="//player.vimeo.com/video{videoid}" ' +\
'width="540" height="304" frameborder="0" ' +\
'webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>'
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):
2014-12-13 13:56:02 +01:00
params['url'] = search_url.format(pageno=params['pageno'],
2014-12-01 12:26:38 +01:00
query=urlencode({'q': query}))
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):
2015-01-13 17:13:08 +01:00
videoid = result.xpath(url_xpath)[0]
url = base_url + videoid
2014-05-10 11:56:19 +02:00
title = p.unescape(extract_text(result.xpath(title_xpath)))
2015-09-08 23:05:37 +02:00
thumbnail = extract_text(result.xpath(thumbnail_xpath)[0])
2015-02-09 13:30:16 +01:00
publishedDate = parser.parse(extract_text(result.xpath(publishedDate_xpath)[0]))
2015-01-13 17:13:08 +01:00
embedded = embedded_url.format(videoid=videoid)
2014-05-10 11:56:19 +02:00
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,
2015-01-13 17:13:08 +01:00
'embedded': embedded,
2014-05-10 11:56:19 +02:00
'thumbnail': thumbnail})
2014-12-01 12:26:38 +01:00
# return results
2014-05-10 11:56:19 +02:00
return results