[fix] pep8 compatibility

This commit is contained in:
Adam Tauber 2014-10-19 12:18:21 +02:00
parent 28fed5d9ad
commit b0fd71b7b3
2 changed files with 22 additions and 18 deletions

View file

@ -1,8 +1,9 @@
## Yahoo (News) # Yahoo (News)
# #
# @website https://news.yahoo.com # @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) # @using-api no (because pricing)
# @results HTML (using search portal) # @results HTML (using search portal)
# @stable no (HTML can change) # @stable no (HTML can change)
@ -22,7 +23,7 @@ paging = True
language_support = True language_support = True
# search-url # 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 # specific xpath variables
results_xpath = '//div[@class="res"]' results_xpath = '//div[@class="res"]'
@ -41,7 +42,7 @@ def request(query, params):
language = 'en' language = 'en'
else: else:
language = params['language'].split('_')[0] language = params['language'].split('_')[0]
params['url'] = search_url.format(offset=offset, params['url'] = search_url.format(offset=offset,
query=urlencode({'p': query}), query=urlencode({'p': query}),
lang=language) lang=language)

View file

@ -45,11 +45,9 @@ def load_single_https_ruleset(filepath):
# get root node # get root node
root = tree.getroot() root = tree.getroot()
#print(etree.tostring(tree))
# check if root is a node with the name ruleset # check if root is a node with the name ruleset
# TODO improve parsing # TODO improve parsing
if root.tag != 'ruleset': if root.tag != 'ruleset':
return () return ()
# check if rule is deactivated by default # check if rule is deactivated by default
@ -68,36 +66,39 @@ def load_single_https_ruleset(filepath):
for ruleset in root: for ruleset in root:
# this child define a target # this child define a target
if ruleset.tag == 'target': if ruleset.tag == 'target':
# check if required tags available # check if required tags available
if not ruleset.attrib.get('host'): if not ruleset.attrib.get('host'):
continue continue
# convert host-rule to valid regex # convert host-rule to valid regex
host = ruleset.attrib.get('host').replace('.', '\.').replace('*', '.*') host = ruleset.attrib.get('host')\
.replace('.', '\.').replace('*', '.*')
# append to host list # append to host list
hosts.append(host) hosts.append(host)
# this child define a rule # this child define a rule
elif ruleset.tag == 'rule': elif ruleset.tag == 'rule':
# check if required tags available # check if required tags available
if not ruleset.attrib.get('from')\ if not ruleset.attrib.get('from')\
or not ruleset.attrib.get('to'): or not ruleset.attrib.get('to'):
continue 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('$', '\\') rule_from = ruleset.attrib.get('from').replace('$', '\\')
rule_to = ruleset.attrib.get('to').replace('$', '\\') rule_to = ruleset.attrib.get('to').replace('$', '\\')
# TODO, not working yet because of the hack above, currently doing that in webapp.py # TODO, not working yet because of the hack above,
#rule_from_rgx = re.compile(rule_from, re.I) # currently doing that in webapp.py
# rule_from_rgx = re.compile(rule_from, re.I)
# append rule # append rule
rules.append((rule_from, rule_to)) rules.append((rule_from, rule_to))
# this child define an exclusion # this child define an exclusion
elif ruleset.tag == 'exclusion': elif ruleset.tag == 'exclusion':
# check if required tags available # check if required tags available
if not ruleset.attrib.get('pattern'): if not ruleset.attrib.get('pattern'):
continue continue
@ -124,7 +125,9 @@ def load_https_rules(rules_path):
rules_path += '/' rules_path += '/'
# search all xml files which are stored in the https rule directory # 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 # load xml-files
for ruleset_file in xml_files: for ruleset_file in xml_files:
@ -137,5 +140,5 @@ def load_https_rules(rules_path):
# append ruleset # append ruleset
https_rules.append(ruleset) https_rules.append(ruleset)
print(' * {n} https-rules loaded'.format(n=len(https_rules))) print(' * {n} https-rules loaded'.format(n=len(https_rules)))