From 0fc481f47ed8116b3acd4dd11c0527994582d526 Mon Sep 17 00:00:00 2001 From: Adam Tauber Date: Sat, 8 Mar 2014 19:09:03 +0100 Subject: [PATCH] [fix] yahoo url extraction --- searx/engines/yahoo.py | 9 +++++---- searx/engines/yahoo_news.py | 7 ++----- 2 files changed, 7 insertions(+), 9 deletions(-) diff --git a/searx/engines/yahoo.py b/searx/engines/yahoo.py index f070b8a7..a6c597e1 100644 --- a/searx/engines/yahoo.py +++ b/searx/engines/yahoo.py @@ -15,6 +15,10 @@ suggestion_xpath = '//div[@id="satat"]//a' paging = True +def parse_url(url_string): + start = url_string.find('http', url_string.find('/RU=')+1) + end = min(url_string.rfind('/RS'), url_string.rfind('/RK')) + return unquote(url_string[start:end]) def request(query, params): offset = (params['pageno'] - 1) * 10 + 1 @@ -34,10 +38,7 @@ def response(resp): dom = html.fromstring(resp.text) for result in dom.xpath(results_xpath): - url_string = extract_url(result.xpath(url_xpath), search_url) - start = url_string.find('http', url_string.find('/RU=')+1) - end = url_string.rfind('/RS') - url = unquote(url_string[start:end]) + url = parse_url(extract_url(result.xpath(url_xpath), search_url)) title = extract_text(result.xpath(title_xpath)[0]) content = extract_text(result.xpath(content_xpath)[0]) results.append({'url': url, 'title': title, 'content': content}) diff --git a/searx/engines/yahoo_news.py b/searx/engines/yahoo_news.py index 3c257866..35e32391 100644 --- a/searx/engines/yahoo_news.py +++ b/searx/engines/yahoo_news.py @@ -1,9 +1,9 @@ #!/usr/bin/env python from urllib import urlencode -from urlparse import unquote from lxml import html from searx.engines.xpath import extract_text, extract_url +from searx.engines.yahoo import parse_url categories = ['news'] search_url = 'http://news.search.yahoo.com/search?{query}&b={offset}' @@ -34,10 +34,7 @@ def response(resp): dom = html.fromstring(resp.text) for result in dom.xpath(results_xpath): - url_string = extract_url(result.xpath(url_xpath), search_url) - start = url_string.find('http', url_string.find('/RU=')+1) - end = url_string.rfind('/RS') - url = unquote(url_string[start:end]) + url = parse_url(extract_url(result.xpath(url_xpath), search_url)) title = extract_text(result.xpath(title_xpath)[0]) content = extract_text(result.xpath(content_xpath)[0]) results.append({'url': url, 'title': title, 'content': content})