def industry(names=False, rigs=True, categories=[0], detail=-1):
for cat in categories:
if not cat in (0, 6, 7, 8, 18, 22):
raise LookupError
i = Industry(names=names, rigs=rigs, categories=categories, detail=detail)
items = i.fetch()
return jsonify(items=items)
def parseIndustry():
url = 'http://www.sse.com.cn/sseportal/webapp/datapresent/SSEQueryFirstSSENewAct'
from lxml import etree
from lxml.html import parse
page = parse(url).getroot()
result = etree.tostring(page)
#print result
#r = page.xpath('//td[@class="table3"]');
r = page.xpath('//tr[@valign="top"]')
#print len(r)
from industry import Industry
for data in r:
dataTree = etree.ElementTree(data)
#print etree.tostring(dataTree)
#values = dataTree.xpath('//text()')
row = dataTree.xpath('//td')
length = len(row)
#print length
if (length == 5):
continue
rows = []
for column in row:
col = etree.ElementTree(column)
#print etree.tostring(col)
values = col.xpath('//text()')
temp = values[0].strip()
#print temp
rows.append(temp)
industry = Industry()
name = str(rows[0])
href = dataTree.xpath('//a/@href')
print href
try:
pe = float(rows[4])
avgPrice = str(rows[5])
industry.name = name
industry.PE = pe
industry.avgPrice = avgPrice
except:
continue
print industry
newUrl = 'http://www.sse.com.cn' + str(href[0])
print newUrl
newPage = parse(newUrl).getroot()
newResult = etree.tostring(newPage)
print newResult
