logo

searx

My custom branche(s) on searx, a meta-search engine
commit: d13c5aa37b02e4df8d5aa7481d0fece3a341f8c2
parent: 27cae541972cabd460142aa3d009ea00c37c29d5
Author: asciimoo <asciimoo@gmail.com>
Date:   Sun,  5 Jan 2014 00:46:42 +0100

[mod] unused imports and whitespaces purged

Diffstat:

Msearx/engines/filecrop.py10++++------
Msearx/engines/yacy.py10+++++-----
2 files changed, 9 insertions(+), 11 deletions(-)

diff --git a/searx/engines/filecrop.py b/searx/engines/filecrop.py @@ -1,6 +1,4 @@ -from json import loads from urllib import urlencode -from searx.utils import html_to_text from HTMLParser import HTMLParser url = 'http://www.filecrop.com/' @@ -10,7 +8,7 @@ class FilecropResultParser(HTMLParser): def __init__(self): HTMLParser.__init__(self) self.__start_processing = False - + self.results = [] self.result = {} @@ -22,7 +20,7 @@ class FilecropResultParser(HTMLParser): if tag == 'tr': if ('bgcolor', '#edeff5') in attrs or ('bgcolor', '#ffffff') in attrs: self.__start_processing = True - + if not self.__start_processing: return @@ -50,7 +48,7 @@ class FilecropResultParser(HTMLParser): self.data_counter = 0 self.results.append(self.result) self.result = {} - + def handle_data(self, data): if not self.__start_processing: return @@ -59,7 +57,7 @@ class FilecropResultParser(HTMLParser): self.result['content'] += data + ' ' else: self.result['content'] = data + ' ' - + self.data_counter += 1 def request(query, params): diff --git a/searx/engines/yacy.py b/searx/engines/yacy.py @@ -1,5 +1,5 @@ from json import loads -from urllib import urlencode, quote +from urllib import urlencode url = 'http://localhost:8090' search_url = '/yacysearch.json?{query}&maximumRecords=10' @@ -10,7 +10,7 @@ def request(query, params): def response(resp): raw_search_results = loads(resp.text) - + if not len(raw_search_results): return [] @@ -22,10 +22,10 @@ def response(resp): tmp_result = {} tmp_result['title'] = result['title'] tmp_result['url'] = result['link'] - tmp_result['content'] = '' - + tmp_result['content'] = '' + if len(result['description']): - tmp_result['content'] += result['description'] +"<br/>" + tmp_result['content'] += result['description'] +"<br/>" if len(result['pubDate']): tmp_result['content'] += result['pubDate'] + "<br/>"