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
|
# SPDX-License-Identifier: AGPL-3.0-or-later
"""
Rumble (Videos)
"""
from urllib.parse import urlencode
from lxml import html
from datetime import datetime
# about
from searx.utils import extract_text
about = {
"website": 'https://rumble.com/',
"wikidata_id": 'Q104765127',
"official_api_documentation": 'https://help.rumble.com/',
"use_official_api": False,
"require_api_key": False,
"results": 'HTML',
}
# engine dependent config
categories = ['videos']
paging = True
# search-url
base_url = 'https://rumble.com/'
url_xpath = './/a[@class="video-item--a"]/@href'
thumbnail_xpath = './/img[@class="video-item--img"]/@src'
title_xpath = './/h3[@class="video-item--title"]'
published_date = './/time[@class="video-item--meta video-item--time"]/@datetime'
earned_xpath = './/span[@class="video-item--meta video-item--earned"]/@data-value'
views_xpath = './/span[@class="video-item--meta video-item--views"]/@data-value'
rumbles_xpath = './/span[@class="video-item--meta video-item--rumbles"]/@data-value'
author_xpath = './/div[@class="ellipsis-1"]'
length_xpath = './/span[@class="video-item--duration"]/@data-value'
def request(query, params):
args = {"q": query}
if params["pageno"] > 1:
args['page'] = params["pageno"]
params['url'] = f'{base_url}search/video?{urlencode(args)}'
return params
def response(resp):
results = []
dom = html.fromstring(resp.text)
results_dom = dom.xpath('//li[contains(@class, "video-listing-entry")]')
if not results_dom:
return []
for result_dom in results_dom:
url = base_url + extract_text(result_dom.xpath(url_xpath))
thumbnail = extract_text(result_dom.xpath(thumbnail_xpath))
title = extract_text(result_dom.xpath(title_xpath))
p_date = extract_text(result_dom.xpath(published_date))
# fix offset date for line 644 webapp.py check
fixed_date = datetime.strptime(p_date, '%Y-%m-%dT%H:%M:%S%z')
earned = extract_text(result_dom.xpath(earned_xpath))
views = extract_text(result_dom.xpath(views_xpath))
rumbles = extract_text(result_dom.xpath(rumbles_xpath))
author = extract_text(result_dom.xpath(author_xpath))
length = extract_text(result_dom.xpath(length_xpath))
if earned:
content = f"{views} views - {rumbles} rumbles - ${earned}"
else:
content = f"{views} views - {rumbles} rumbles"
results.append(
{
'url': url,
'title': title,
'content': content,
'author': author,
'length': length,
'template': 'videos.html',
'publishedDate': fixed_date,
'thumbnail': thumbnail,
}
)
return results
|
