logo

searx

My custom branche(s) on searx, a meta-search engine git clone https://hacktivis.me/git/searx.git
commit: 993271bed30e24c7ae1e0f63b64e030829206f27
parent 337bd6d907503176eb94290c3f386ce88167dea8
Author: Thomas Pointhuber <thomas.pointhuber@gmx.at>
Date:   Tue, 18 Mar 2014 15:56:22 +0100

extract publishDate from vimeo

Diffstat:

Msearx/engines/vimeo.py6++++++
Msearx/engines/yahoo_news.py2+-
2 files changed, 7 insertions(+), 1 deletion(-)

diff --git 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 diff --git a/searx/engines/yahoo_news.py b/searx/engines/yahoo_news.py @@ -53,7 +53,7 @@ def response(resp): - timedelta(hours=int(timeNumbers[0]))\ - timedelta(minutes=int(timeNumbers[1])) else: - publishedDate =parser.parse(publishedDate) + publishedDate = parser.parse(publishedDate) if publishedDate.year == 1900: publishedDate = publishedDate.replace(year=datetime.now().year)