blob: 03e1d7ffc2da1fc2d3c37683eed6333a0725a11c (
plain)
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
|
from urllib import urlencode
from json import loads
from lxml import html
categories = ['videos']
locale = 'en_US'
# see http://www.dailymotion.com/doc/api/obj-video.html
search_url = 'https://api.dailymotion.com/videos?fields=title,description,duration,url,thumbnail_360_url&sort=relevance&limit=25&page={pageno}&{query}' # noqa
# TODO use video result template
content_tpl = '<a href="{0}" title="{0}" ><img src="{1}" /></a><br />'
paging = True
def request(query, params):
params['url'] = search_url.format(
query=urlencode({'search': query, 'localization': locale}),
pageno=params['pageno'])
return params
def response(resp):
results = []
search_res = loads(resp.text)
if not 'list' in search_res:
return results
for res in search_res['list']:
title = res['title']
url = res['url']
if res['thumbnail_360_url']:
content = content_tpl.format(url, res['thumbnail_360_url'])
else:
content = ''
if res['description']:
description = text_content_from_html(res['description'])
content += description[:500]
results.append({'url': url, 'title': title, 'content': content})
return results
def text_content_from_html(html_string):
desc_html = html.fragment_fromstring(html_string, create_parent=True)
return desc_html.text_content()
|
