improve publishDate extraction from yahoo

Browse Source
This commit is contained in:
Thomas Pointhuber 2014-03-15 19:20:29 +01:00
parent 794165d19c
commit 5538c6771a
1 changed files with 17 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
searx/engines/yahoo_news.py
View File

@ -4,7 +4,8 @@ from urllib import urlencode
from lxml import html from lxml import html
from searx.engines.xpath import extract_text, extract_url from searx.engines.xpath import extract_text, extract_url
from searx.engines.yahoo import parse_url from searx.engines.yahoo import parse_url
from datetime import datetime from datetime import datetime, timedelta
import re
categories = ['news'] categories = ['news']
search_url = 'http://news.search.yahoo.com/search?{query}&b={offset}' search_url = 'http://news.search.yahoo.com/search?{query}&b={offset}'
@ -39,9 +40,21 @@ def response(resp):
url = parse_url(extract_url(result.xpath(url_xpath), search_url)) url = parse_url(extract_url(result.xpath(url_xpath), search_url))
title = extract_text(result.xpath(title_xpath)[0]) title = extract_text(result.xpath(title_xpath)[0])
content = extract_text(result.xpath(content_xpath)[0]) content = extract_text(result.xpath(content_xpath)[0])
# Feb 20 04:02am publishedDate = extract_text(result.xpath(publishedDate_xpath)[0])
publishedDate = datetime.strptime(extract_text(result.xpath(publishedDate_xpath)[0]),"%b %d %H:%M%p")
#publishedDate.replace(year=2014) if re.match("^[0-9]+ minute(s|) ago$", publishedDate):
publishedDate = datetime.now() - timedelta(minutes=int(re.match(r'\d+', publishedDate).group()))
else:
if re.match("^[0-9]+ hour(s|), [0-9]+ minute(s|) ago$", publishedDate):
timeNumbers = re.findall(r'\d+', publishedDate)
publishedDate = datetime.now() - timedelta(hours=int(timeNumbers[0])) - timedelta(minutes=int(timeNumbers[1]))
else:
# TODO year in string possible?
publishedDate = datetime.strptime(publishedDate,"%b %d %H:%M%p")
if publishedDate.year == 1900:
publishedDate = publishedDate.replace(year=datetime.now().year)
results.append({'url': url, 'title': title, 'content': content,'publishedDate':publishedDate}) results.append({'url': url, 'title': title, 'content': content,'publishedDate':publishedDate})
if not suggestion_xpath: if not suggestion_xpath: