def parse(self, data):
# Locate url
treebuilder = treebuilders.getTreeBuilder("etree", etree)
p = html5parser.HTMLParser(tree=treebuilder)#, tokenizer=sanitizer.HTMLSanitizer)
res = chardet.detect(data)
if res and res.has_key('encoding'):
encoding = res['encoding']
if encoding is None:
document = p.parse(StringIO(data))
else:
document = p.parse(StringIO(data), encoding=encoding)
d = document.xpath('//a[text()="XLS"]')
if len(d) > 0:
url = d[0].attrib['href']
url = urljoin(self.url, url)
(status, headers, body) = httpc.get_(url, ok=[500, 501,300, 301, 503, 200, 404, 405])
f = open(self.filename, 'wb')
f.write(body)
f.close()
return self.readFile(self.filename)
def test_get_(self):
status, msg, body = httpc.get_(self.base_url() + 'hello')
self.assertEquals(status, 200)
self.assertEquals(msg.dict['x-get'], 'hello')
self.assertEquals(body, 'hello world')
def get(self, url):
(status, headers, body) = httpc.get_(url, ok=[500, 501, 300, 301, 503, 200, 404, 405])
return body
def test_get_(self):
status, msg, body = httpc.get_(self.base_url() + 'hello')
self.assertEquals(status, 200)
self.assertEquals(msg.dict['x-get'], 'hello')
self.assertEquals(body, 'hello world')
