def testExtractTag(self):
pattern = "<a name='$name'></a>"
_scraper = Scraper(pattern)
exp = BeautifulSoup(pattern)
# one attribute
actual = BeautifulSoup("<a name='abc'></a>")
self.assertEqual('abc', _scraper.extractTag(exp.contents[0], actual.contents[0])['name'])
# one attribute
actual = BeautifulSoup("<a name='abc' age='27'></a>")
self.assertEqual('abc', _scraper.extractTag(exp.contents[0], actual.contents[0])['name'])
# two attributes
pattern = "<a name='$name' age='$age'></a>"
exp = BeautifulSoup(pattern)
actual = BeautifulSoup("<a name='abc' age='27'></a>")
ret = _scraper.extractTag(exp.contents[0], actual.contents[0])
self.assertEqual(2, len(ret))
self.assertEqual('abc', ret['name'])
self.assertEqual('27', ret['age'])
# get attribute from sub tag
pattern = "<a><b name='$name'></b></a>"
exp = BeautifulSoup(pattern)
# one attribute
actual = BeautifulSoup("<a><b name='abc'></b></a>")
self.assertEqual('abc', _scraper.extractTag(exp.contents[0], actual.contents[0])['name'])
def testExtractAsteriskValue(self):
pattern = "<a>*$content</a>"
_scraper = Scraper(pattern)
exp = BeautifulSoup(pattern)
# extract text
actual = BeautifulSoup("<a>hello world</a>")
self.assertTrue(_scraper.matchTag(exp.contents[0], actual.contents[0]))
self.assertEqual('hello world', _scraper.extractTag(exp.contents[0], actual.contents[0])['content'][0])
pattern = "<a>*(b)$content</a>"
_scraper = Scraper(pattern)
exp = BeautifulSoup(pattern)
# asterisk only restrict on tag but not text
actual = BeautifulSoup("<a>hello world</a>")
self.assertTrue(_scraper.matchTag(exp.contents[0], actual.contents[0]))
self.assertEqual('hello world', _scraper.extractTag(exp.contents[0], actual.contents[0])['content'][0])
# asterisk restrict tag
actual = BeautifulSoup("<a><c></c></a>")
self.assertFalse(_scraper.matchTag(exp.contents[0], actual.contents[0]))
# asterisk restrict tag
actual = BeautifulSoup("<a><b>hello world</b></a>")
self.assertTrue(_scraper.matchTag(exp.contents[0], actual.contents[0]))
self.assertEqual(BeautifulSoup('<b>hello world</b>').contents[0], _scraper.extractTag(exp.contents[0], actual.contents[0])['content'][0])
# asterisk restrict tag
actual = BeautifulSoup("<a><b>hello</b><b>world</b></a>")
self.assertTrue(_scraper.matchTag(exp.contents[0], actual.contents[0]))
ret = _scraper.extractTag(exp.contents[0], actual.contents[0])
self.assertEqual(BeautifulSoup('<b>hello</b>').contents[0], ret['content'][0])
self.assertEqual(BeautifulSoup('<b>world</b>').contents[0], ret['content'][1])
# prefix asterisk
pattern = "<a>*(b)<c></c>$content</a>"
_scraper = Scraper(pattern)
exp = BeautifulSoup(pattern)
actual = BeautifulSoup("<a><b></b><b></b><c></c>hello world</a>")
self.assertTrue(_scraper.matchTag(exp.contents[0], actual.contents[0]))
ret = _scraper.extractTag(exp.contents[0], actual.contents[0])
self.assertEqual('hello world', ret['content'])
# prefix asterisk
pattern = "<a>*(b)<c></c>*$content</a>"
_scraper = Scraper(pattern)
exp = BeautifulSoup(pattern)
actual = BeautifulSoup("<a><b></b><c></c><d>hello world</d></a>")
self.assertTrue(_scraper.matchTag(exp.contents[0], actual.contents[0]))
ret = _scraper.extractTag(exp.contents[0], actual.contents[0])
self.assertEqual(BeautifulSoup('<d>hello world</d>').contents[0], ret['content'][0])
actual = BeautifulSoup("<a><b></b><c></c><d>hello</d><d>world</d></a>")
self.assertTrue(_scraper.matchTag(exp.contents[0], actual.contents[0]))
ret = _scraper.extractTag(exp.contents[0], actual.contents[0])
self.assertEqual(BeautifulSoup('<d>hello</d>').contents[0], ret['content'][0])
self.assertEqual(BeautifulSoup('<d>world</d>').contents[0], ret['content'][1])
# prefix asterisk
pattern = "<a>*<c></c>*$content</a>"
_scraper = Scraper(pattern)
exp = BeautifulSoup(pattern)
actual = BeautifulSoup("<a><b></b>some text<c></c><d>hello world</d></a>")
self.assertTrue(_scraper.matchTag(exp.contents[0], actual.contents[0]))
ret = _scraper.extractTag(exp.contents[0], actual.contents[0])
self.assertEqual(BeautifulSoup('<d>hello world</d>').contents[0], ret['content'][0])
