def spiderHKEX(self, url=None):
if not url:
html = GetHtmlTxt(self.browser, self._siteBaseDict[self.target])
else:
html = GetHtmlTxt(self.browser, url)
de = decoder.PageDecoder(self.target)
de.decode(html)
self.data = de.data()
return self.data
def spiderNASDAQ(self):
self.data = []
replace_list = ['pricings', 'upcoming', 'filings', 'withdrawn']
for i in replace_list:
html = GetHtmlTxt(self._siteBaseDict[self.target].replace(
'###', i))
de = decoder.PageDecoder(self.target)
de.decode(html)
self.data += de.data()
# sleep()
return self.data
def spiderHKEX(self):
html = GetHtmlTxt(self._siteBaseDict[self.target])
de = decoder.PageDecoder(self.target)
de.decode(html)
self.data = de.data()
return self.data