diff options
| author | Adam Tauber <asciimoo@gmail.com> | 2014-03-18 18:20:10 +0100 |
|---|---|---|
| committer | Adam Tauber <asciimoo@gmail.com> | 2014-03-18 18:20:10 +0100 |
| commit | 018a14431bd3612db4e8840ce24f3e60026ece0f (patch) | |
| tree | 18c7f0ed489c0c0f206ac1f0a191b1ce0ab045b2 /searx/engines/vimeo.py | |
| parent | faed14b2c691746ba6cf98d164a5e6b1ca3ee4c9 (diff) | |
| parent | 993271bed30e24c7ae1e0f63b64e030829206f27 (diff) | |
Merge pull request #57 from pointhi/results
improving publishDate extraction and output of it
Diffstat (limited to 'searx/engines/vimeo.py')
| -rw-r--r-- | searx/engines/vimeo.py | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/searx/engines/vimeo.py b/searx/engines/vimeo.py index a95c75b49..d2d2a4dd0 100644 --- a/searx/engines/vimeo.py +++ b/searx/engines/vimeo.py @@ -2,6 +2,8 @@ from urllib import urlencode from HTMLParser import HTMLParser from lxml import html from xpath import extract_text +from datetime import datetime +from dateutil import parser base_url = 'http://vimeo.com' search_url = base_url + '/search?{query}' @@ -10,6 +12,7 @@ content_xpath = None title_xpath = None results_xpath = '' content_tpl = '<a href="{0}"> <img src="{2}"/> </a>' +publishedDate_xpath = './/p[@class="meta"]//attribute::datetime' # the cookie set by vimeo contains all the following values, # but only __utma seems to be requiered @@ -40,9 +43,12 @@ def response(resp): url = base_url + result.xpath(url_xpath)[0] title = p.unescape(extract_text(result.xpath(title_xpath))) thumbnail = extract_text(result.xpath(content_xpath)[0]) + publishedDate = parser.parse(extract_text(result.xpath(publishedDate_xpath)[0])) + results.append({'url': url, 'title': title, 'content': content_tpl.format(url, title, thumbnail), 'template': 'videos.html', + 'publishedDate': publishedDate, 'thumbnail': thumbnail}) return results |