logo

searx

My custom branche(s) on searx, a meta-search engine
commit: b0fd71b7b3463864e6c60156610d383af2ac9709
parent: 28fed5d9ad4227ca772f258d5e9bd3d48452b845
Author: Adam Tauber <asciimoo@gmail.com>
Date:   Sun, 19 Oct 2014 12:18:21 +0200

[fix] pep8 compatibility

Diffstat:

Msearx/engines/yahoo_news.py13+++++++------
Msearx/https_rewrite.py27+++++++++++++++------------
2 files changed, 22 insertions(+), 18 deletions(-)

diff --git a/searx/engines/yahoo_news.py b/searx/engines/yahoo_news.py @@ -1,8 +1,9 @@ -## Yahoo (News) -# +# Yahoo (News) +# # @website https://news.yahoo.com -# @provide-api yes (https://developer.yahoo.com/boss/search/), $0.80/1000 queries -# +# @provide-api yes (https://developer.yahoo.com/boss/search/) +# $0.80/1000 queries +# # @using-api no (because pricing) # @results HTML (using search portal) # @stable no (HTML can change) @@ -22,7 +23,7 @@ paging = True language_support = True # search-url -search_url = 'https://news.search.yahoo.com/search?{query}&b={offset}&fl=1&vl=lang_{lang}' +search_url = 'https://news.search.yahoo.com/search?{query}&b={offset}&fl=1&vl=lang_{lang}' # noqa # specific xpath variables results_xpath = '//div[@class="res"]' @@ -41,7 +42,7 @@ def request(query, params): language = 'en' else: language = params['language'].split('_')[0] - + params['url'] = search_url.format(offset=offset, query=urlencode({'p': query}), lang=language) diff --git a/searx/https_rewrite.py b/searx/https_rewrite.py @@ -45,11 +45,9 @@ def load_single_https_ruleset(filepath): # get root node root = tree.getroot() - #print(etree.tostring(tree)) - # check if root is a node with the name ruleset # TODO improve parsing - if root.tag != 'ruleset': + if root.tag != 'ruleset': return () # check if rule is deactivated by default @@ -68,36 +66,39 @@ def load_single_https_ruleset(filepath): for ruleset in root: # this child define a target if ruleset.tag == 'target': - # check if required tags available + # check if required tags available if not ruleset.attrib.get('host'): continue # convert host-rule to valid regex - host = ruleset.attrib.get('host').replace('.', '\.').replace('*', '.*') + host = ruleset.attrib.get('host')\ + .replace('.', '\.').replace('*', '.*') # append to host list hosts.append(host) # this child define a rule elif ruleset.tag == 'rule': - # check if required tags available + # check if required tags available if not ruleset.attrib.get('from')\ or not ruleset.attrib.get('to'): continue - # TODO hack, which convert a javascript regex group into a valid python regex group + # TODO hack, which convert a javascript regex group + # into a valid python regex group rule_from = ruleset.attrib.get('from').replace('$', '\\') rule_to = ruleset.attrib.get('to').replace('$', '\\') - # TODO, not working yet because of the hack above, currently doing that in webapp.py - #rule_from_rgx = re.compile(rule_from, re.I) + # TODO, not working yet because of the hack above, + # currently doing that in webapp.py + # rule_from_rgx = re.compile(rule_from, re.I) # append rule rules.append((rule_from, rule_to)) # this child define an exclusion elif ruleset.tag == 'exclusion': - # check if required tags available + # check if required tags available if not ruleset.attrib.get('pattern'): continue @@ -124,7 +125,9 @@ def load_https_rules(rules_path): rules_path += '/' # search all xml files which are stored in the https rule directory - xml_files = [ join(rules_path,f) for f in listdir(rules_path) if isfile(join(rules_path,f)) and f[-4:] == '.xml' ] + xml_files = [join(rules_path, f) + for f in listdir(rules_path) + if isfile(join(rules_path, f)) and f[-4:] == '.xml'] # load xml-files for ruleset_file in xml_files: @@ -137,5 +140,5 @@ def load_https_rules(rules_path): # append ruleset https_rules.append(ruleset) - + print(' * {n} https-rules loaded'.format(n=len(https_rules)))