forked from zaclys/searxng
Merge pull request #1071 from return42/fix-lang-dailymotion
[fix] dailymotion engine: filter by language & country
This commit is contained in:
Alexandre Flament
GitHub
commit
c474616642
File diff suppressed because it is too large
Load Diff
|
|
@ -1,12 +1,17 @@
|
|||
# SPDX-License-Identifier: AGPL-3.0-or-later
|
||||
"""
|
||||
Dailymotion (Videos)
|
||||
"""Dailymotion (Videos)
|
||||
|
||||
"""
|
||||
|
||||
from json import loads
|
||||
from datetime import datetime
|
||||
from typing import Set
|
||||
from datetime import datetime, timedelta
|
||||
from urllib.parse import urlencode
|
||||
from searx.utils import match_language, html_to_text
|
||||
import time
|
||||
import babel
|
||||
|
||||
from searx.exceptions import SearxEngineAPIException
|
||||
from searx.network import raise_for_httperror
|
||||
from searx.utils import html_to_text
|
||||
|
||||
# about
|
||||
about = {
|
||||
|
|
@ -21,23 +26,89 @@ about = {
|
|||
# engine dependent config
|
||||
categories = ['videos']
|
||||
paging = True
|
||||
number_of_results = 10
|
||||
|
||||
time_range_support = True
|
||||
time_delta_dict = {
|
||||
"day": timedelta(days=1),
|
||||
"week": timedelta(days=7),
|
||||
"month": timedelta(days=31),
|
||||
"year": timedelta(days=365),
|
||||
}
|
||||
|
||||
safesearch = True
|
||||
safesearch_params = {2: '&is_created_for_kids=true', 1: '&is_created_for_kids=true', 0: ''}
|
||||
|
||||
# search-url
|
||||
# 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
|
||||
supported_languages_url = 'https://api.dailymotion.com/languages'
|
||||
# - https://developers.dailymotion.com/tools/
|
||||
# - https://www.dailymotion.com/doc/api/obj-video.html
|
||||
|
||||
result_fields = [
|
||||
'allow_embed',
|
||||
'description',
|
||||
'title',
|
||||
'created_time',
|
||||
'duration',
|
||||
'url',
|
||||
'thumbnail_360_url',
|
||||
'id',
|
||||
]
|
||||
search_url = (
|
||||
'https://api.dailymotion.com/videos?'
|
||||
'fields={fields}&password_protected={password_protected}&private={private}&sort={sort}&limit={limit}'
|
||||
).format(
|
||||
fields=','.join(result_fields),
|
||||
password_protected= 'false',
|
||||
private='false',
|
||||
sort='relevance',
|
||||
limit=number_of_results,
|
||||
)
|
||||
iframe_src = "https://www.dailymotion.com/embed/video/{video_id}"
|
||||
|
||||
# The request query filters by 'languages' & 'country', therefore instead of
|
||||
# fetching only languages we need to fetch locales.
|
||||
supported_languages_url = 'https://api.dailymotion.com/locales'
|
||||
supported_languages_iso639: Set[str] = set()
|
||||
|
||||
|
||||
def init(_engine_settings):
|
||||
global supported_languages_iso639
|
||||
supported_languages_iso639 = set([language.split('_')[0] for language in supported_languages])
|
||||
|
||||
|
||||
# do search-request
|
||||
def request(query, params):
|
||||
if params['language'] == 'all':
|
||||
locale = 'en-US'
|
||||
else:
|
||||
locale = match_language(params['language'], supported_languages)
|
||||
|
||||
params['url'] = search_url.format(
|
||||
query=urlencode({'search': query, 'localization': locale}), pageno=params['pageno']
|
||||
)
|
||||
if not query:
|
||||
return False
|
||||
|
||||
language = params['language']
|
||||
if language == 'all':
|
||||
language = 'en-US'
|
||||
locale = babel.Locale.parse(language, sep='-')
|
||||
|
||||
language_iso639 = locale.language
|
||||
if locale.language not in supported_languages_iso639:
|
||||
language_iso639 = 'en'
|
||||
|
||||
query_args = {
|
||||
'search': query,
|
||||
'languages': language_iso639,
|
||||
'page': params['pageno'],
|
||||
}
|
||||
|
||||
if locale.territory:
|
||||
localization = locale.language + '_' + locale.territory
|
||||
if localization in supported_languages:
|
||||
query_args['country'] = locale.territory
|
||||
|
||||
time_delta = time_delta_dict.get(params["time_range"])
|
||||
if time_delta:
|
||||
created_after = datetime.now() - time_delta
|
||||
query_args['created_after'] = datetime.timestamp(created_after)
|
||||
|
||||
query_str = urlencode(query_args)
|
||||
params['url'] = search_url + '&' + query_str + safesearch_params.get(params['safesearch'], '')
|
||||
params['raise_for_httperror'] = False
|
||||
|
||||
return params
|
||||
|
||||
|
|
@ -46,34 +117,51 @@ def request(query, params):
|
|||
def response(resp):
|
||||
results = []
|
||||
|
||||
search_res = loads(resp.text)
|
||||
search_res = resp.json()
|
||||
|
||||
# return empty array if there are no results
|
||||
if 'list' not in search_res:
|
||||
return []
|
||||
# check for an API error
|
||||
if 'error' in search_res:
|
||||
raise SearxEngineAPIException(search_res['error'].get('message'))
|
||||
|
||||
raise_for_httperror(resp)
|
||||
|
||||
# parse results
|
||||
for res in search_res['list']:
|
||||
for res in search_res.get('list', []):
|
||||
|
||||
title = res['title']
|
||||
url = res['url']
|
||||
|
||||
content = html_to_text(res['description'])
|
||||
thumbnail = res['thumbnail_360_url']
|
||||
if len(content) > 300:
|
||||
content = content[:300] + '...'
|
||||
|
||||
publishedDate = datetime.fromtimestamp(res['created_time'], None)
|
||||
|
||||
# http to https
|
||||
length = time.gmtime(res.get('duration'))
|
||||
if length.tm_hour:
|
||||
length = time.strftime("%H:%M:%S", length)
|
||||
else:
|
||||
length = time.strftime("%M:%S", length)
|
||||
|
||||
thumbnail = res['thumbnail_360_url']
|
||||
thumbnail = thumbnail.replace("http://", "https://")
|
||||
|
||||
results.append(
|
||||
{
|
||||
'template': 'videos.html',
|
||||
'url': url,
|
||||
'title': title,
|
||||
'content': content,
|
||||
'publishedDate': publishedDate,
|
||||
'iframe_src': "https://www.dailymotion.com/embed/video/" + res['id'],
|
||||
'thumbnail': thumbnail,
|
||||
}
|
||||
)
|
||||
item = {
|
||||
'template': 'videos.html',
|
||||
'url': url,
|
||||
'title': title,
|
||||
'content': content,
|
||||
'publishedDate': publishedDate,
|
||||
'length': length,
|
||||
'thumbnail': thumbnail,
|
||||
}
|
||||
|
||||
# HINT: no mater what the value is, without API token videos can't shown
|
||||
# embedded
|
||||
if res['allow_embed']:
|
||||
item['iframe_src'] = iframe_src.format(video_id=res['id'])
|
||||
|
||||
results.append(item)
|
||||
|
||||
# return results
|
||||
return results
|
||||
|
|
@ -81,18 +169,8 @@ def response(resp):
|
|||
|
||||
# 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
|
||||
response_json = resp.json()
|
||||
return [
|
||||
item['locale']
|
||||
for item in response_json['list']
|
||||
]
|
||||
|
|
|
|||
|
|
@ -2,9 +2,7 @@
|
|||
# list of language codes
|
||||
# this file is generated automatically by utils/fetch_languages.py
|
||||
language_codes = (
|
||||
('af-ZA', 'Afrikaans', 'Suid-Afrika', 'Afrikaans', '\U0001f1ff\U0001f1e6'),
|
||||
('ar-EG', 'العربية', 'مصر', 'Arabic', '\U0001f1ea\U0001f1ec'),
|
||||
('be-BY', 'Беларуская', 'Беларусь', 'Belarusian', '\U0001f1e7\U0001f1fe'),
|
||||
('bg-BG', 'Български', 'България', 'Bulgarian', '\U0001f1e7\U0001f1ec'),
|
||||
('ca-ES', 'Català', 'Espanya', 'Catalan', '\U0001f1ea\U0001f1f8'),
|
||||
('cs-CZ', 'Čeština', 'Česko', 'Czech', '\U0001f1e8\U0001f1ff'),
|
||||
|
|
@ -28,20 +26,15 @@ language_codes = (
|
|||
('es-ES', 'Español', 'España', 'Spanish', '\U0001f1ea\U0001f1f8'),
|
||||
('es-MX', 'Español', 'México', 'Spanish', '\U0001f1f2\U0001f1fd'),
|
||||
('et-EE', 'Eesti', 'Eesti', 'Estonian', '\U0001f1ea\U0001f1ea'),
|
||||
('fa-IR', 'فارسی', 'ایران', 'Persian', '\U0001f1ee\U0001f1f7'),
|
||||
('fi-FI', 'Suomi', 'Suomi', 'Finnish', '\U0001f1eb\U0001f1ee'),
|
||||
('fil-PH', 'Filipino', 'Pilipinas', 'Filipino', '\U0001f1f5\U0001f1ed'),
|
||||
('fr', 'Français', '', 'French', '\U0001f310'),
|
||||
('fr-BE', 'Français', 'Belgique', 'French', '\U0001f1e7\U0001f1ea'),
|
||||
('fr-CA', 'Français', 'Canada', 'French', '\U0001f1e8\U0001f1e6'),
|
||||
('fr-CH', 'Français', 'Suisse', 'French', '\U0001f1e8\U0001f1ed'),
|
||||
('fr-FR', 'Français', 'France', 'French', '\U0001f1eb\U0001f1f7'),
|
||||
('he-IL', 'עברית', 'ישראל', 'Hebrew', '\U0001f1ee\U0001f1f1'),
|
||||
('hi-IN', 'हिन्दी', 'भारत', 'Hindi', '\U0001f1ee\U0001f1f3'),
|
||||
('hr-HR', 'Hrvatski', 'Hrvatska', 'Croatian', '\U0001f1ed\U0001f1f7'),
|
||||
('hu-HU', 'Magyar', 'Magyarország', 'Hungarian', '\U0001f1ed\U0001f1fa'),
|
||||
('id-ID', 'Indonesia', 'Indonesia', 'Indonesian', '\U0001f1ee\U0001f1e9'),
|
||||
('is-IS', 'Íslenska', 'Ísland', 'Icelandic', '\U0001f1ee\U0001f1f8'),
|
||||
('it-IT', 'Italiano', 'Italia', 'Italian', '\U0001f1ee\U0001f1f9'),
|
||||
('ja-JP', '日本語', '日本', 'Japanese', '\U0001f1ef\U0001f1f5'),
|
||||
('ko-KR', '한국어', '대한민국', 'Korean', '\U0001f1f0\U0001f1f7'),
|
||||
|
|
@ -63,13 +56,10 @@ language_codes = (
|
|||
('ru-RU', 'Русский', 'Россия', 'Russian', '\U0001f1f7\U0001f1fa'),
|
||||
('sk-SK', 'Slovenčina', 'Slovensko', 'Slovak', '\U0001f1f8\U0001f1f0'),
|
||||
('sl-SI', 'Slovenščina', 'Slovenija', 'Slovenian', '\U0001f1f8\U0001f1ee'),
|
||||
('sr-RS', 'Српски', 'Србија', 'Serbian', '\U0001f1f7\U0001f1f8'),
|
||||
('sv-SE', 'Svenska', 'Sverige', 'Swedish', '\U0001f1f8\U0001f1ea'),
|
||||
('sw-TZ', 'Kiswahili', 'Tanzania', 'Swahili', '\U0001f1f9\U0001f1ff'),
|
||||
('th-TH', 'ไทย', 'ไทย', 'Thai', '\U0001f1f9\U0001f1ed'),
|
||||
('tr-TR', 'Türkçe', 'Türkiye', 'Turkish', '\U0001f1f9\U0001f1f7'),
|
||||
('uk-UA', 'Українська', 'Україна', 'Ukrainian', '\U0001f1fa\U0001f1e6'),
|
||||
('vi-VN', 'Tiếng Việt', 'Việt Nam', 'Vietnamese', '\U0001f1fb\U0001f1f3'),
|
||||
('zh', '中文', '', 'Chinese', '\U0001f310'),
|
||||
('zh-CN', '中文', '中国', 'Chinese', '\U0001f1e8\U0001f1f3'),
|
||||
('zh-HK', '中文', '中國香港特別行政區', 'Chinese', '\U0001f1ed\U0001f1f0'),
|
||||
|
|
|
|||
|
|
@ -88,6 +88,8 @@ class _HTMLTextExtractor(HTMLParser): # pylint: disable=W0223 # (see https://b
|
|||
|
||||
def handle_starttag(self, tag, attrs):
|
||||
self.tags.append(tag)
|
||||
if tag == 'br':
|
||||
self.result.append(' ')
|
||||
|
||||
def handle_endtag(self, tag):
|
||||
if not self.tags:
|
||||
|
|
@ -142,7 +144,7 @@ def html_to_text(html_str: str) -> str:
|
|||
>>> html_to_text('<style>.span { color: red; }</style><span>Example</span>')
|
||||
'Example'
|
||||
"""
|
||||
html_str = html_str.replace('\n', ' ')
|
||||
html_str = html_str.replace('\n', ' ').replace('\r', ' ')
|
||||
html_str = ' '.join(html_str.split())
|
||||
s = _HTMLTextExtractor()
|
||||
try:
|
||||
|
|
|
|||
|
|
@ -129,8 +129,8 @@ class TestLanguageParser(SearxTestCase):
|
|||
query = RawTextQuery(':hu-H', [])
|
||||
self.assertEqual(query.autocomplete_list, [":hu-hu"])
|
||||
|
||||
query = RawTextQuery(':v', [])
|
||||
self.assertEqual(query.autocomplete_list, [':vi', ':tiếng việt', ':việt_nam'])
|
||||
query = RawTextQuery(':zh-', [])
|
||||
self.assertEqual(query.autocomplete_list, [':zh-cn', ':zh-hk', ':zh-tw'])
|
||||
|
||||
|
||||
class TestTimeoutParser(SearxTestCase):
|
||||
|
|
|
|||
Loading…
Reference in New Issue