diff --git a/scrapy/contrib/linkextractors/lxmlhtml.py b/scrapy/contrib/linkextractors/lxmlhtml.py index f747fa99b..1ff8e4d36 100644 --- a/scrapy/contrib/linkextractors/lxmlhtml.py +++ b/scrapy/contrib/linkextractors/lxmlhtml.py @@ -81,17 +81,18 @@ class LxmlParserLinkExtractor(object): class LxmlLinkExtractor(FilteringLinkExtractor): def __init__(self, allow=(), deny=(), allow_domains=(), deny_domains=(), restrict_xpaths=(), - restrict_css=(), tags=('a', 'area'), attrs=('href',), canonicalize=True, - unique=True, process_value=None, deny_extensions=None): + tags=('a', 'area'), attrs=('href',), canonicalize=True, + unique=True, process_value=None, deny_extensions=None, restrict_css=()): tags, attrs = set(arg_to_iter(tags)), set(arg_to_iter(attrs)) tag_func = lambda x: x in tags attr_func = lambda x: x in attrs lx = LxmlParserLinkExtractor(tag=tag_func, attr=attr_func, unique=unique, process=process_value) - super(LxmlLinkExtractor, self).__init__(lx, allow, deny, - allow_domains, deny_domains, restrict_xpaths, restrict_css, - canonicalize, deny_extensions) + super(LxmlLinkExtractor, self).__init__(lx, allow=allow, deny=deny, + allow_domains=allow_domains, deny_domains=deny_domains, + restrict_xpaths=restrict_xpaths, restrict_css=restrict_css, + canonicalize=canonicalize, deny_extensions=deny_extensions) def extract_links(self, response): html = Selector(response) diff --git a/scrapy/contrib/linkextractors/sgml.py b/scrapy/contrib/linkextractors/sgml.py index 3a8fdbb69..335773db1 100644 --- a/scrapy/contrib/linkextractors/sgml.py +++ b/scrapy/contrib/linkextractors/sgml.py @@ -98,8 +98,8 @@ class BaseSgmlLinkExtractor(SGMLParser): class SgmlLinkExtractor(FilteringLinkExtractor): def __init__(self, allow=(), deny=(), allow_domains=(), deny_domains=(), restrict_xpaths=(), - restrict_css=(), tags=('a', 'area'), attrs=('href',), canonicalize=True, unique=True, - process_value=None, deny_extensions=None): + tags=('a', 'area'), attrs=('href',), canonicalize=True, unique=True, + process_value=None, deny_extensions=None, restrict_css=()): warnings.warn( "SgmlLinkExtractor is deprecated and will be removed in future releases. " @@ -115,9 +115,10 @@ class SgmlLinkExtractor(FilteringLinkExtractor): lx = BaseSgmlLinkExtractor(tag=tag_func, attr=attr_func, unique=unique, process_value=process_value) - super(SgmlLinkExtractor, self).__init__(lx, allow, deny, - allow_domains, deny_domains, restrict_xpaths, restrict_css, - canonicalize, deny_extensions) + super(SgmlLinkExtractor, self).__init__(lx, allow=allow, deny=deny, + allow_domains=allow_domains, deny_domains=deny_domains, + restrict_xpaths=restrict_xpaths, restrict_css=restrict_css, + canonicalize=canonicalize, deny_extensions=deny_extensions) # FIXME: was added to fix a RegexLinkExtractor testcase self.base_url = None diff --git a/scrapy/linkextractor.py b/scrapy/linkextractor.py index 52271959f..227d79b46 100644 --- a/scrapy/linkextractor.py +++ b/scrapy/linkextractor.py @@ -42,7 +42,7 @@ class FilteringLinkExtractor(object): _csstranslator = ScrapyHTMLTranslator() def __init__(self, link_extractor, allow, deny, allow_domains, deny_domains, - restrict_xpaths, restrict_css, canonicalize, deny_extensions): + restrict_xpaths, canonicalize, deny_extensions, restrict_css): self.link_extractor = link_extractor