From 1d5741954eb6786bbbc31e9bc4d540f73bccdb46 Mon Sep 17 00:00:00 2001 From: Thomas Pointhuber Date: Tue, 4 Mar 2014 13:10:04 +0100 Subject: [PATCH 1/4] Create bing_news.py --- searx/engines/bing_news.py | 51 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) create mode 100644 searx/engines/bing_news.py diff --git a/searx/engines/bing_news.py b/searx/engines/bing_news.py new file mode 100644 index 000000000..5b48a5450 --- /dev/null +++ b/searx/engines/bing_news.py @@ -0,0 +1,51 @@ +from urllib import urlencode +from cgi import escape +from lxml import html + +categories = ['news'] + +base_url = 'http://www.bing.com/' +search_string = 'news/search?{query}&first={offset}' +paging = True +language_support = True + + +def request(query, params): + offset = (params['pageno'] - 1) * 10 + 1 + if params['language'] == 'all': + language = 'en-US' + else: + language = params['language'].replace('_', '-') + search_path = search_string.format( + query=urlencode({'q': query, 'setmkt': language}), + offset=offset) + + params['cookies']['SRCHHPGUSR'] = \ + 'NEWWND=0&NRSLT=-1&SRCHLANG=' + language.split('-')[0] + #if params['category'] == 'images': + # params['url'] = base_url + 'images/' + search_path + params['url'] = base_url + search_path + return params + + +def response(resp): + global base_url + results = [] + dom = html.fromstring(resp.content) + for result in dom.xpath('//div[@class="sa_cc"]'): + link = result.xpath('.//h3/a')[0] + url = link.attrib.get('href') + title = ' '.join(link.xpath('.//text()')) + content = escape(' '.join(result.xpath('.//p//text()'))) + results.append({'url': url, 'title': title, 'content': content}) + + if results: + return results + + for result in dom.xpath('//li[@class="b_algo"]'): + link = result.xpath('.//h2/a')[0] + url = link.attrib.get('href') + title = ' '.join(link.xpath('.//text()')) + content = escape(' '.join(result.xpath('.//p//text()'))) + results.append({'url': url, 'title': title, 'content': content}) + return results From 0549f8c7c8d25d9764c83bc006fa32cdddc13c46 Mon Sep 17 00:00:00 2001 From: Thomas Pointhuber Date: Tue, 4 Mar 2014 13:11:04 +0100 Subject: [PATCH 2/4] Create google_news.py --- searx/engines/google_news.py | 37 ++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 searx/engines/google_news.py diff --git a/searx/engines/google_news.py b/searx/engines/google_news.py new file mode 100644 index 000000000..ca27a5b2f --- /dev/null +++ b/searx/engines/google_news.py @@ -0,0 +1,37 @@ +#!/usr/bin/env python + +from urllib import urlencode +from json import loads + +categories = ['news'] + +url = 'https://ajax.googleapis.com/' +search_url = url + 'ajax/services/search/news?v=2.0&start={offset}&rsz=large&safe=off&filter=off&{query}&hl={language}' # noqa + +paging = True +language_support = True + + +def request(query, params): + offset = (params['pageno'] - 1) * 8 + language = 'en-US' + if params['language'] != 'all': + language = params['language'].replace('_', '-') + params['url'] = search_url.format(offset=offset, + query=urlencode({'q': query}), + language=language) + return params + + +def response(resp): + results = [] + search_res = loads(resp.text) + + if not search_res.get('responseData', {}).get('results'): + return [] + + for result in search_res['responseData']['results']: + results.append({'url': result['unescapedUrl'], + 'title': result['titleNoFormatting'], + 'content': result['content']}) + return results From f1404ce72d5c789a12211a5ea9f3ea08ebf83986 Mon Sep 17 00:00:00 2001 From: Thomas Pointhuber Date: Tue, 4 Mar 2014 13:11:53 +0100 Subject: [PATCH 3/4] Create yahoo_news.py --- searx/engines/yahoo_news.py | 51 +++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) create mode 100644 searx/engines/yahoo_news.py diff --git a/searx/engines/yahoo_news.py b/searx/engines/yahoo_news.py new file mode 100644 index 000000000..6ece496cd --- /dev/null +++ b/searx/engines/yahoo_news.py @@ -0,0 +1,51 @@ +#!/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 + +categories = ['news'] +search_url = 'http://news.search.yahoo.com/search?{query}&b={offset}' +results_xpath = '//div[@class="res"]' +url_xpath = './/h3/a/@href' +title_xpath = './/h3/a' +content_xpath = './/div[@class="abstr"]' +suggestion_xpath = '//div[@id="satat"]//a' + +paging = True + + +def request(query, params): + offset = (params['pageno'] - 1) * 10 + 1 + if params['language'] == 'all': + language = 'en' + else: + language = params['language'].split('_')[0] + params['url'] = search_url.format(offset=offset, + query=urlencode({'p': query})) + params['cookies']['sB'] = 'fl=1&vl=lang_{lang}&sh=1&rw=new&v=1'\ + .format(lang=language) + return params + + +def response(resp): + results = [] + 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('/RU=')+4 + end = url_string.rfind('/RS') + url = unquote(url_string[start:end]) + title = extract_text(result.xpath(title_xpath)[0]) + content = extract_text(result.xpath(content_xpath)[0]) + results.append({'url': url, 'title': title, 'content': content}) + + if not suggestion_xpath: + return results + + for suggestion in dom.xpath(suggestion_xpath): + results.append({'suggestion': extract_text(suggestion)}) + + return results From dcd1b99a52ed905f59c1c572db97ad4b466420c2 Mon Sep 17 00:00:00 2001 From: Thomas Pointhuber Date: Tue, 4 Mar 2014 13:13:16 +0100 Subject: [PATCH 4/4] Adding news site's to settings.yml --- searx/settings.yml | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/searx/settings.yml b/searx/settings.yml index 86514c1e4..7a32c629c 100644 --- a/searx/settings.yml +++ b/searx/settings.yml @@ -17,6 +17,11 @@ engines: locale : en-US shortcut : bi + - name : bing news + engine : bing_news + locale : en-US + shortcut : bin + - name : currency engine : currency_convert categories : general @@ -61,6 +66,10 @@ engines: engine : google_images shortcut : goi + - name : google news + engine : google_news + shortcut : gon + - name : piratebay engine : piratebay categories : videos, music, files @@ -112,6 +121,10 @@ engines: engine : yahoo shortcut : yh + - name : yahoo news + engine : yahoo_news + shortcut : yhn + - name : youtube engine : youtube categories : videos