searxngRebrandZaclys/searx/engines/youtube_noapi.py

73 lines
2.2 KiB
Python
Raw Normal View History

# Youtube (Videos)
#
# @website https://www.youtube.com/
# @provide-api yes (https://developers.google.com/apis-explorer/#p/youtube/v3/youtube.search.list)
#
# @using-api no
# @results HTML
# @stable no
# @parse url, title, content, publishedDate, thumbnail, embedded
from urllib import quote_plus
from lxml import html
from searx.engines.xpath import extract_text
# engine dependent config
categories = ['videos', 'music']
paging = True
language_support = False
# search-url
base_url = 'https://www.youtube.com/results'
search_url = base_url + '?search_query={query}&page={page}'
embedded_url = '<iframe width="540" height="304" ' +\
'data-src="//www.youtube-nocookie.com/embed/{videoid}" ' +\
'frameborder="0" allowfullscreen></iframe>'
base_youtube_url = 'https://www.youtube.com/watch?v='
# specific xpath variables
results_xpath = "//ol/li/div[contains(@class, 'yt-lockup yt-lockup-tile yt-lockup-video vve-check')]"
url_xpath = './/h3/a/@href'
title_xpath = './/div[@class="yt-lockup-content"]/h3/a'
content_xpath = './/div[@class="yt-lockup-content"]/div[@class="yt-lockup-description yt-ui-ellipsis yt-ui-ellipsis-2"]'
# do search-request
def request(query, params):
params['url'] = search_url.format(query=quote_plus(query),
page=params['pageno'])
return params
# get response from search-request
def response(resp):
results = []
dom = html.fromstring(resp.text)
# parse results
for result in dom.xpath(results_xpath):
videoid = result.xpath('@data-context-item-id')[0]
url = base_youtube_url + videoid
thumbnail = 'https://i.ytimg.com/vi/' + videoid + '/hqdefault.jpg'
title = extract_text(result.xpath(title_xpath)[0])
content = extract_text(result.xpath(content_xpath)[0])
embedded = embedded_url.format(videoid=videoid)
# append result
results.append({'url': url,
'title': title,
'content': content,
'template': 'videos.html',
'embedded': embedded,
'thumbnail': thumbnail})
# return results
return results