Renamed LinkExtractors extract_urls method to extract_links

--HG--
extra : convert_revision : svn%3Ab85faa78-f9eb-468e-a121-7cced6da292c%40594

scrapy/trunk/scrapy/contrib/spiders/crawl.py

@@ -85,7 +85,7 @@ class CrawlSpider(BaseSpider):
         requests = []
         seen = set()
         for rule in self._rules:
-            links = [l for l in rule.link_extractor.extract_urls(response) if l not in seen]
+            links = [l for l in rule.link_extractor.extract_links(response) if l not in seen]
             if links and rule.process_links:
                 links = rule.process_links(links)
             seen = seen.union(links)

scrapy/trunk/scrapy/link/__init__.py

@@ -7,7 +7,7 @@ from scrapy.utils.url import urljoin_rfc as urljoin
 
 class LinkExtractor(FixedSGMLParser):
     """LinkExtractor are used to extract links from web pages. They are
-    instantiated and later "applied" to a Response using the extract_urls
+    instantiated and later "applied" to a Response using the extract_links
     method which must receive a Response object and return a dict whoose keys
     are the (absolute) urls to follow, and its values any arbitrary data. In
     this case the values are the text of the hyperlink.
@@ -16,7 +16,7 @@ class LinkExtractor(FixedSGMLParser):
     functionality for extracting links to follow, but you could override this
     class or create a new one if you need some additional functionality. The
     only requisite is that the new (or overrided) class must provide a
-    extract_urls method that receives a Response and returns a dict with the
+    extract_links method that receives a Response and returns a dict with the
     links to follow as its keys.
 
     The constructor arguments are:
@@ -35,7 +35,7 @@ class LinkExtractor(FixedSGMLParser):
         self.scan_attr = attr if callable(attr) else lambda a: a == attr
         self.current_link = None
 
-    def extract_urls(self, response, unique=False):
+    def extract_links(self, response, unique=False):
         self.reset()
         self.unique = unique
         self.feed(response.body.to_string())

scrapy/trunk/scrapy/link/extractors.py

@@ -54,11 +54,11 @@ class RegexLinkExtractor(LinkExtractor):
         attr_func = lambda x: x in attrs
         LinkExtractor.__init__(self, tag=tag_func, attr=attr_func)
 
-    def extract_urls(self, response, unique=True):
+    def extract_links(self, response, unique=True):
         if self.restrict_xpaths:
             response = new_response_from_xpaths(response, self.restrict_xpaths)
 
-        links = LinkExtractor.extract_urls(self, response, unique)
+        links = LinkExtractor.extract_links(self, response, unique)
         links = [link for link in links if _is_valid_url(link.url)]
 
         if self.allow_res:

scrapy/trunk/scrapy/tests/test_link.py

@@ -17,7 +17,7 @@ class LinkExtractorTestCase(unittest.TestCase):
         response = Response("example.org", "http://example.org/somepage/index.html", body=html)
 
         lx = LinkExtractor()  # default: tag=a, attr=href
-        self.assertEqual(lx.extract_urls(response), 
+        self.assertEqual(lx.extract_links(response),
                          [Link(url='http://example.org/somepage/item/12.html', text='Item 12'), 
                           Link(url='http://example.org/about.html', text='About us'),
                           Link(url='http://example.org/othercat.html', text='Other category'), 
@@ -30,7 +30,7 @@ class LinkExtractorTestCase(unittest.TestCase):
         response = Response("example.org", "http://example.org/somepage/index.html", body=html)
 
         lx = LinkExtractor()  # default: tag=a, attr=href
-        self.assertEqual(lx.extract_urls(response), 
+        self.assertEqual(lx.extract_links(response),
                          [Link(url='http://otherdomain.com/base/item/12.html', text='Item 12')])
 
     def test_matches(self):

scrapy/trunk/scrapy/tests/test_spiders/testplugin.py

@@ -22,7 +22,7 @@ class TestSpider(BaseSpider):
     def parse(self, response):
         xlink = LinkExtractor()
         itemre = re.compile(self.itemurl_re)
-        for link in xlink.extract_urls(response):
+        for link in xlink.extract_links(response):
             if itemre.search(link.url):
                 yield Request(url=link.url, callback=self.parse_item)