searxng/searx/engines/dailymotion.py

99 lines
2.8 KiB
Python
Raw Normal View History

"""
Dailymotion (Videos)
@website https://www.dailymotion.com
@provide-api yes (http://www.dailymotion.com/developer)
@using-api yes
@results JSON
@stable yes
@parse url, title, thumbnail, publishedDate, embedded
@todo set content-parameter with correct data
"""
2013-12-30 21:42:37 +00:00
from json import loads
from datetime import datetime
2016-11-30 17:43:03 +00:00
from searx.url_utils import urlencode
from searx.utils import match_language, html_to_text
2013-12-30 21:42:37 +00:00
# engine dependent config
2013-12-30 21:42:37 +00:00
categories = ['videos']
paging = True
language_support = True
2013-12-30 21:42:37 +00:00
# search-url
2013-12-30 21:42:37 +00:00
# see http://www.dailymotion.com/doc/api/obj-video.html
search_url = 'https://api.dailymotion.com/videos?fields=created_time,title,description,duration,url,thumbnail_360_url,id&sort=relevance&limit=5&page={pageno}&{query}' # noqa
embedded_url = '<iframe frameborder="0" width="540" height="304" ' +\
'data-src="https://www.dailymotion.com/embed/video/{videoid}" allowfullscreen></iframe>'
2014-01-29 23:01:42 +00:00
supported_languages_url = 'https://api.dailymotion.com/languages'
# do search-request
2013-12-30 21:42:37 +00:00
def request(query, params):
if params['language'] == 'all':
locale = 'en-US'
else:
locale = match_language(params['language'], supported_languages)
params['url'] = search_url.format(
2014-01-29 23:01:42 +00:00
query=urlencode({'search': query, 'localization': locale}),
pageno=params['pageno'])
2013-12-30 21:42:37 +00:00
return params
# get response from search-request
2013-12-30 21:42:37 +00:00
def response(resp):
results = []
2013-12-30 21:42:37 +00:00
search_res = loads(resp.text)
# return empty array if there are no results
if 'list' not in search_res:
return []
# parse results
2013-12-30 21:42:37 +00:00
for res in search_res['list']:
title = res['title']
url = res['url']
content = html_to_text(res['description'])
thumbnail = res['thumbnail_360_url']
publishedDate = datetime.fromtimestamp(res['created_time'], None)
embedded = embedded_url.format(videoid=res['id'])
# http to https
thumbnail = thumbnail.replace("http://", "https://")
results.append({'template': 'videos.html',
'url': url,
'title': title,
'content': content,
'publishedDate': publishedDate,
'embedded': embedded,
'thumbnail': thumbnail})
# return results
return results
# get supported languages from their site
def _fetch_supported_languages(resp):
supported_languages = {}
response_json = loads(resp.text)
for language in response_json['list']:
supported_languages[language['code']] = {}
name = language['native_name']
if name:
supported_languages[language['code']]['name'] = name
english_name = language['name']
if english_name:
supported_languages[language['code']]['english_name'] = english_name
return supported_languages