RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

tests for CSS support in link extractors

This commit is contained in:
Artur Gaspar 2014-12-11 18:20:30 -02:00
parent d4cb03eded
commit 403fc686b8
1 changed files with 15 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
tests/test_contrib_linkextractors.py
View File

@ -284,6 +284,21 @@ class SgmlLinkExtractorTestCase(unittest.TestCase):
[Link(url='http://example.org/foo', text=u'>\u4eac<\u4e1c',
fragment='', nofollow=False)])
def test_restrict_css(self):
lx = self.extractor_cls(restrict_css=('#subwrapper a',))
self.assertEqual(lx.extract_links(self.response), [
Link(url='http://example.com/sample2.html', text=u'sample 2')
])
def test_restrict_css_and_restrict_xpaths_together(self):
lx = self.extractor_cls(restrict_xpaths=('//div[@id="subwrapper"]', ),
restrict_css=('#subwrapper + a', ))
self.assertEqual([link for link in lx.extract_links(self.response)], [
Link(url='http://example.com/sample1.html', text=u''),
Link(url='http://example.com/sample2.html', text=u'sample 2'),
Link(url='http://example.com/sample3.html', text=u'sample 3 text'),
])
def test_area_tag_with_unicode_present(self):
body = """<html><body>\xbe\xa9<map><area href="http://example.org/foo" /></map></body></html>"""
response = HtmlResponse("http://example.org", body=body, encoding='utf-8')