@@ -1,48 +1,38 @@
11from urllib import urlencode
22from HTMLParser import HTMLParser
3−from xpath import *
3+from xpath import extract_text
4+from lxml import html
45
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}'
88
9+# the cookie set by vime contains all the following values, but only __utma seems to be requiered
910Cookie = {
10− 'vuid':'918282893.1027205400'
11− , 'ab_bs':'%7B%223%22%3A279%7D'
12− , '__utma':'18302654.101#6140782.1388942090.1388942090.1388942090.1'
13− , '__utmb':'18302654.1.10.1388942090'
14− , '__utmc':'18302654'
15− , '__utmz':'18#302654.1388942090.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)'
16− , '__utml':'search'
11+ #'vuid':'918282893.1027205400'
12+ # 'ab_bs':'%7B%223%22%3A279%7D'
13+ '__utma':'00000000.000#0000000.0000000000.0000000000.0000000000.0'
14+ # '__utmb':'18302654.1.10.1388942090'
15+ #, '__utmc':'18302654'
16+ #, '__utmz':'18#302654.1388942090.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)'
17+ #, '__utml':'search'
1718}
1819
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−
2120def request(query, params):
2221 params['url'] = search_url.format(query=urlencode({'q' :query}))
2322 print params['url']
2423 params['cookies'] = Cookie
2524 return params
2625
27−
2826def response(resp):
2927 results = []
30−
3128 dom = html.fromstring(resp.text)
29+
30+ p = HTMLParser()
3231
33− if results_xpath:
34− for result in dom.xpath(results_xpath):
35− url = extract_url(result.xpath(url_xpath))
36−
37− title = extract_text(result.xpath(title_xpath)[0 ])
38− content = 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})
32+ for result in dom.xpath(results_xpath):
33+ url = base_url + result.xpath(url_xpath)[0]
34+ title = p.unescape(extract_text(result.xpath(title_xpath)))
35+ content = '<a href="{0}"> <img src="{2}"/> </a>'.format(url, title, extract_text(result.xpath(content_xpath)[0]))
36+ results.append({'url': url, 'title': title, 'content': content})
4737
4838 return results