git.iko.soy/searx
on master help sign in
[enh] Improved vimeo search engines, and add the configuration in the sample
1950e69pw3t
engines.cfg_sample+7
compare with master
unifiedsplit
@@ -86,3 +86,10 @@ engine = dailymotion
86locale = en_US
86locale = en_US
87categories = videos
87categories = videos
88
88
89+[vimeo]
90+engine = vimeo
91+categories = videos
92+results_xpath = //div[@id="browse_content"]/ol/li
93+url_xpath=./a/@href
94+title_xpath=./a/div[@class="data"]/p[@class="title"]/text()
95+content_xpath=./a/img/@src
searx/engines/vimeo.py+19−29
@@ -1,48 +1,38 @@
1from urllib import urlencode
1from urllib import urlencode
2from HTMLParser import HTMLParser
2from HTMLParser import HTMLParser
3−from xpath import *
3+from xpath import extract_text
4+from lxml import html
4
5
5−categories = ['dev']
6−
7−search_url = 'http://vimeo.com/search?{query}'
6+base_url = 'http://vimeo.com'
7+search_url = base_url + '/search?{query}'
8
8
9+# the cookie set by vime contains all the following values, but only __utma seems to be requiered
9Cookie = {
10Cookie = {
10− 'vuid':'918282893.1027205400'
11+ #'vuid':'918282893.1027205400'
11− , 'ab_bs':'%7B%223%22%3A279%7D'
12+ # 'ab_bs':'%7B%223%22%3A279%7D'
12− , '__utma':'18302654.101#6140782.1388942090.1388942090.1388942090.1'
13+ '__utma':'00000000.000#0000000.0000000000.0000000000.0000000000.0'
13− , '__utmb':'18302654.1.10.1388942090'
14+ # '__utmb':'18302654.1.10.1388942090'
14− , '__utmc':'18302654'
15+ #, '__utmc':'18302654'
15− , '__utmz':'18#302654.1388942090.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)'
16+ #, '__utmz':'18#302654.1388942090.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)'
16− , '__utml':'search'
17+ #, '__utml':'search'
17}
18}
18
19
19−#'vuid=918282893.1027205400& ab_bs=%7B%223%22%3A279%7D& player="scaling=1&volume=1"& __utma=18302654.101#6140782.1388942090.1388942090.1388942090.1& __utmb=18302654.1.10.1388942090& __utmc=18302654& __utmz=18#302654.1388942090.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)& __utmli=search'
20−
21def request(query, params):
20def request(query, params):
22 params['url'] = search_url.format(query=urlencode({'q' :query}))
21 params['url'] = search_url.format(query=urlencode({'q' :query}))
23 print params['url']
22 print params['url']
24 params['cookies'] = Cookie
23 params['cookies'] = Cookie
25 return params
24 return params
26
25
27−
28def response(resp):
26def response(resp):
29 results = []
27 results = []
30−
31 dom = html.fromstring(resp.text)
28 dom = html.fromstring(resp.text)
29+
30+ p = HTMLParser()
32
31
33− if results_xpath:
34− for result in dom.xpath(results_xpath):
32+ for result in dom.xpath(results_xpath):
35− url = extract_url(result.xpath(url_xpath))
33+ url = base_url + result.xpath(url_xpath)[0]
36−
37− title = extract_text(result.xpath(title_xpath)[0 ])
34+ title = p.unescape(extract_text(result.xpath(title_xpath)))
38− content = extract_text(result.xpath(content_xpath)[0])
35+ content = '<a href="{0}"> <img src="{2}"/> </a>'.format(url, title, extract_text(result.xpath(content_xpath)[0]))
39− results.append({'url': url, 'title': title, 'content': content})
40− else:
41− for url, title, content in zip(
42− map(extract_url, dom.xpath(url_xpath)), \
43− map(extract_text, dom.xpath(title_xpath)), \
44− map(extract_text, dom.xpath(content_xpath)), \
45− ):
46− results.append({'url': url, 'title': title, 'content': content})
36+ results.append({'url': url, 'title': title, 'content': content})
47
37
48 return results
38 return results