diff options
Diffstat (limited to 'searx/engines')
| -rw-r--r-- | searx/engines/bing_images.py | 9 | ||||
| -rw-r--r-- | searx/engines/blekko_images.py | 68 | ||||
| -rw-r--r-- | searx/engines/gigablast.py | 63 | ||||
| -rw-r--r-- | searx/engines/google_images.py | 11 | ||||
| -rw-r--r-- | searx/engines/piratebay.py | 2 |
5 files changed, 149 insertions, 4 deletions
diff --git a/searx/engines/bing_images.py b/searx/engines/bing_images.py index 9d1c22f5a..b8c61c151 100644 --- a/searx/engines/bing_images.py +++ b/searx/engines/bing_images.py @@ -21,12 +21,18 @@ import re # engine dependent config categories = ['images'] paging = True +safesearch = True # search-url base_url = 'https://www.bing.com/' search_string = 'images/search?{query}&count=10&first={offset}' thumb_url = "http://ts1.mm.bing.net/th?id={ihk}" +# safesearch definitions +safesearch_types = {2: 'STRICT', + 1: 'DEMOTE', + 0: 'OFF'} + # do search-request def request(query, params): @@ -43,7 +49,8 @@ def request(query, params): offset=offset) params['cookies']['SRCHHPGUSR'] = \ - 'NEWWND=0&NRSLT=-1&SRCHLANG=' + language.split('-')[0] + 'NEWWND=0&NRSLT=-1&SRCHLANG=' + language.split('-')[0] +\ + '&ADLT=' + safesearch_types.get(params['safesearch'], 'DEMOTE') params['url'] = base_url + search_path diff --git a/searx/engines/blekko_images.py b/searx/engines/blekko_images.py new file mode 100644 index 000000000..2e7ec904f --- /dev/null +++ b/searx/engines/blekko_images.py @@ -0,0 +1,68 @@ +## Blekko (Images) +# +# @website https://blekko.com +# @provide-api yes (inofficial) +# +# @using-api yes +# @results JSON +# @stable yes +# @parse url, title, img_src + +from json import loads +from urllib import urlencode + +# engine dependent config +categories = ['images'] +paging = True +safesearch = True + +# search-url +base_url = 'https://blekko.com' +search_url = '/api/images?{query}&c={c}' + +# safesearch definitions +safesearch_types = {2: '1', + 1: '', + 0: '0'} + + +# do search-request +def request(query, params): + c = (params['pageno'] - 1) * 48 + + params['url'] = base_url +\ + search_url.format(query=urlencode({'q': query}), + c=c) + + if params['pageno'] != 1: + params['url'] += '&page={pageno}'.format(pageno=(params['pageno']-1)) + + # let Blekko know we wan't have profiling + params['cookies']['tag_lesslogging'] = '1' + + # parse safesearch argument + params['cookies']['safesearch'] = safesearch_types.get(params['safesearch'], '') + + return params + + +# get response from search-request +def response(resp): + results = [] + + search_results = loads(resp.text) + + # return empty array if there are no results + if not search_results: + return [] + + for result in search_results: + # append result + results.append({'url': result['page_url'], + 'title': result['title'], + 'content': '', + 'img_src': result['url'], + 'template': 'images.html'}) + + # return results + return results diff --git a/searx/engines/gigablast.py b/searx/engines/gigablast.py new file mode 100644 index 000000000..8749c3256 --- /dev/null +++ b/searx/engines/gigablast.py @@ -0,0 +1,63 @@ +## Gigablast (Web) +# +# @website http://gigablast.com +# @provide-api yes (http://gigablast.com/api.html) +# +# @using-api yes +# @results XML +# @stable yes +# @parse url, title, content + +from urllib import urlencode +from cgi import escape +from lxml import etree + +# engine dependent config +categories = ['general'] +paging = True +number_of_results = 5 + +# search-url +base_url = 'http://gigablast.com/' +search_string = 'search?{query}&n={number_of_results}&s={offset}&xml=1&qh=0' + +# specific xpath variables +results_xpath = '//response//result' +url_xpath = './/url' +title_xpath = './/title' +content_xpath = './/sum' + + +# do search-request +def request(query, params): + offset = (params['pageno'] - 1) * number_of_results + + search_path = search_string.format( + query=urlencode({'q': query}), + offset=offset, + number_of_results=number_of_results) + + params['url'] = base_url + search_path + + return params + + +# get response from search-request +def response(resp): + results = [] + + dom = etree.fromstring(resp.content) + + # parse results + for result in dom.xpath(results_xpath): + url = result.xpath(url_xpath)[0].text + title = result.xpath(title_xpath)[0].text + content = escape(result.xpath(content_xpath)[0].text) + + # append result + results.append({'url': url, + 'title': title, + 'content': content}) + + # return results + return results diff --git a/searx/engines/google_images.py b/searx/engines/google_images.py index 092ae6639..1c0e62f5c 100644 --- a/searx/engines/google_images.py +++ b/searx/engines/google_images.py @@ -15,18 +15,25 @@ from json import loads # engine dependent config categories = ['images'] paging = True +safesearch = True # search-url url = 'https://ajax.googleapis.com/' -search_url = url + 'ajax/services/search/images?v=1.0&start={offset}&rsz=large&safe=off&filter=off&{query}' +search_url = url + 'ajax/services/search/images?v=1.0&start={offset}&rsz=large&safe={safesearch}&filter=off&{query}' # do search-request def request(query, params): offset = (params['pageno'] - 1) * 8 + if params['safesearch'] == 0: + safesearch = 'off' + else: + safesearch = 'on' + params['url'] = search_url.format(query=urlencode({'q': query}), - offset=offset) + offset=offset, + safesearch=safesearch) return params diff --git a/searx/engines/piratebay.py b/searx/engines/piratebay.py index 207df276c..fa5c61128 100644 --- a/searx/engines/piratebay.py +++ b/searx/engines/piratebay.py @@ -20,7 +20,7 @@ categories = ['videos', 'music', 'files'] paging = True # search-url -url = 'https://thepiratebay.cr/' +url = 'https://thepiratebay.se/' search_url = url + 'search/{search_term}/{pageno}/99/{search_type}' # piratebay specific type-definitions |