diff options
| -rw-r--r-- | .gitignore | 3 | ||||
| -rw-r--r-- | searx/engines/__init__.py | 2 | ||||
| -rw-r--r-- | searx/engines/filecrop.py | 71 | ||||
| -rw-r--r-- | searx/engines/yacy.py | 38 | ||||
| -rw-r--r-- | searx/templates/about.html | 2 | ||||
| -rw-r--r-- | searx/webapp.py | 3 |
6 files changed, 116 insertions, 3 deletions
diff --git a/.gitignore b/.gitignore index 4cc20423c..76ae1ca2c 100644 --- a/.gitignore +++ b/.gitignore @@ -1,2 +1,5 @@ env engines.cfg + +*.pyc +*/*.pyc
\ No newline at end of file diff --git a/searx/engines/__init__.py b/searx/engines/__init__.py index 43ad1b52e..1ca11ff90 100644 --- a/searx/engines/__init__.py +++ b/searx/engines/__init__.py @@ -261,7 +261,7 @@ def get_engines_stats(): for engine in errors: if max_errors: - engine['percentage'] = int(engine['avg']/max_errors*100) + engine['percentage'] = int(float(engine['avg'])/max_errors*100) else: engine['percentage'] = 0 diff --git a/searx/engines/filecrop.py b/searx/engines/filecrop.py new file mode 100644 index 000000000..52426b84a --- /dev/null +++ b/searx/engines/filecrop.py @@ -0,0 +1,71 @@ +from urllib import urlencode +from HTMLParser import HTMLParser + +url = 'http://www.filecrop.com/' +search_url = url + '/search.php?{query}&size_i=0&size_f=100000000&engine_r=1&engine_d=1&engine_e=1&engine_4=1&engine_m=1' + +class FilecropResultParser(HTMLParser): + def __init__(self): + HTMLParser.__init__(self) + self.__start_processing = False + + self.results = [] + self.result = {} + + self.tr_counter = 0 + self.data_counter = 0 + + def handle_starttag(self, tag, attrs): + + if tag == 'tr': + if ('bgcolor', '#edeff5') in attrs or ('bgcolor', '#ffffff') in attrs: + self.__start_processing = True + + if not self.__start_processing: + return + + if tag == 'label': + self.result['title'] = [attr[1] for attr in attrs if attr[0] == 'title'][0] + elif tag == 'a' and ('rel', 'nofollow') in attrs and ('class', 'sourcelink') in attrs: + if 'content' in self.result: + self.result['content'] += [attr[1] for attr in attrs if attr[0] == 'title'][0] + else: + self.result['content'] = [attr[1] for attr in attrs if attr[0] == 'title'][0] + self.result['content'] += ' ' + elif tag == 'a': + self.result['url'] = url + [attr[1] for attr in attrs if attr[0] == 'href'][0] + + def handle_endtag(self, tag): + if self.__start_processing is False: + return + + if tag == 'tr': + self.tr_counter += 1 + + if self.tr_counter == 2: + self.__start_processing = False + self.tr_counter = 0 + self.data_counter = 0 + self.results.append(self.result) + self.result = {} + + def handle_data(self, data): + if not self.__start_processing: + return + + if 'content' in self.result: + self.result['content'] += data + ' ' + else: + self.result['content'] = data + ' ' + + self.data_counter += 1 + +def request(query, params): + params['url'] = search_url.format(query=urlencode({'w' :query})) + return params + +def response(resp): + parser = FilecropResultParser() + parser.feed(resp.text) + + return parser.results diff --git a/searx/engines/yacy.py b/searx/engines/yacy.py new file mode 100644 index 000000000..c93ac522f --- /dev/null +++ b/searx/engines/yacy.py @@ -0,0 +1,38 @@ +from json import loads +from urllib import urlencode + +url = 'http://localhost:8090' +search_url = '/yacysearch.json?{query}&maximumRecords=10' + +def request(query, params): + params['url'] = url + search_url.format(query=urlencode({'query':query})) + return params + +def response(resp): + raw_search_results = loads(resp.text) + + if not len(raw_search_results): + return [] + + search_results = raw_search_results.get('channels', {})[0].get('items', []) + + results = [] + + for result in search_results: + tmp_result = {} + tmp_result['title'] = result['title'] + tmp_result['url'] = result['link'] + tmp_result['content'] = '' + + if len(result['description']): + tmp_result['content'] += result['description'] +"<br/>" + + if len(result['pubDate']): + tmp_result['content'] += result['pubDate'] + "<br/>" + + if result['size'] != '-1': + tmp_result['content'] += result['sizename'] + + results.append(tmp_result) + + return results diff --git a/searx/templates/about.html b/searx/templates/about.html index b90757914..14a0080f9 100644 --- a/searx/templates/about.html +++ b/searx/templates/about.html @@ -37,7 +37,7 @@ <p>It's ok if you don't trust us regarding the logs, <a href="https://github.com/asciimoo/searx">take the code</a> and run it yourself! decentralize!</p> <h3>How to add to firefox?</h3> <p><a href="#" onclick="window.external.AddSearchProvider(window.location.protocol + '//' + window.location.host + '/opensearch.xml')">Install</a> searx as a search engine on any version of Firefox! (javascript required)</p> -<h2 id="faq">Developer FAQ</h2> +<h2 id="dev_faq">Developer FAQ</h2> <h3>New engines?</h3> <p><ul> <li>Edit your engines.cfg, see <a href="https://raw.github.com/asciimoo/searx/master/engines.cfg_sample">sample config</a></li> diff --git a/searx/webapp.py b/searx/webapp.py index b7e2a4674..2d48f2323 100644 --- a/searx/webapp.py +++ b/searx/webapp.py @@ -152,7 +152,8 @@ def preferences(): selected_categories.append(category) if selected_categories: resp = make_response(redirect('/')) - resp.set_cookie('categories', ','.join(selected_categories)) + # cookie max age: 4 weeks + resp.set_cookie('categories', ','.join(selected_categories), max_age=60*60*24*7*4) return resp return render('preferences.html') |