1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
|
# 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 functools import reduce
from json import loads
from searx.engines.xpath import extract_text
from searx.utils import list_get
from searx.url_utils import quote_plus
# engine dependent config
categories = ['videos', 'music']
paging = True
language_support = False
time_range_support = True
# search-url
base_url = 'https://www.youtube.com/results'
search_url = base_url + '?search_query={query}&page={page}'
time_range_url = '&sp=EgII{time_range}%253D%253D'
time_range_dict = {'day': 'Ag',
'week': 'Aw',
'month': 'BA',
'year': 'BQ'}
embedded_url = '<iframe width="540" height="304" ' +\
'data-src="https://www.youtube-nocookie.com/embed/{videoid}" ' +\
'frameborder="0" allowfullscreen></iframe>'
base_youtube_url = 'https://www.youtube.com/watch?v='
# do search-request
def request(query, params):
params['url'] = search_url.format(query=quote_plus(query),
page=params['pageno'])
if params['time_range'] in time_range_dict:
params['url'] += time_range_url.format(time_range=time_range_dict[params['time_range']])
return params
# get response from search-request
def response(resp):
results = []
results_data = resp.text[resp.text.find('ytInitialData'):]
results_data = results_data[results_data.find('{'):results_data.find(';\n')]
results_json = loads(results_data) if results_data else {}
sections = results_json.get('contents', {})\
.get('twoColumnSearchResultsRenderer', {})\
.get('primaryContents', {})\
.get('sectionListRenderer', {})\
.get('contents', [])
for section in sections:
for video_container in section.get('itemSectionRenderer', {}).get('contents', []):
video = video_container.get('videoRenderer', {})
videoid = video.get('videoId')
if videoid is not None:
url = base_youtube_url + videoid
thumbnail = 'https://i.ytimg.com/vi/' + videoid + '/hqdefault.jpg'
title = get_text_from_json(video.get('title', {}))
content = get_text_from_json(video.get('descriptionSnippet', {}))
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
def get_text_from_json(element):
if 'runs' in element:
return reduce(lambda a, b: a + b.get('text', ''), element.get('runs'), '')
else:
return element.get('simpleText', '')
|
