def post(self):
company = Company()
company.name = self.GetParam("name")
company.industry = self.GetParam("industry")
company.url = self.GetParam("url")
company.put()
self.redirect("/companies/view/" + company.urlname)
def process_company_file(data_file):
workbook = xlrd.open_workbook(settings.MEDIA_ROOT+'/'+data_file.uploaded_file.name)
worksheets = workbook.sheet_names()
data_file.number_of_sheets = len(worksheets)
data_file.save()
for worksheet_name in worksheets:
worksheet = workbook.sheet_by_name(worksheet_name)
num_rows = worksheet.nrows - 1
curr_row = 0
while curr_row < num_rows:
curr_row += 1
company_name = worksheet.cell_value(curr_row, 0)
industry = worksheet.cell_value(curr_row, 1)
isin = worksheet.cell_value(curr_row, 2)
bse_code = worksheet.cell_value(curr_row, 3)
industry, created = Industry.objects.get_or_create(industry_name=industry)
industry.created_by = data_file.uploaded_by
industry.save()
try:
company = Company.objects.get(isin_code=isin)
except:
try:
company = Company.objects.get(company_name=company_name)
except:
company = Company()
company.isin_code = isin
if bse_code:
company.BSE_code = int(bse_code)
company.industry = industry
company.company_name = company_name
company.created_by = data_file.uploaded_by
company.save()
data_file.processing_completed = True
data_file.save()
def get_snp_500_companies(url):
companies = []
table = pd.read_html(url)[0]
for index, row in table.iterrows():
company = Company(row['Symbol'])
company.name = row['Security']
company.sector = row['GICS Sector']
company.industry = row['GICS Sub Industry']
company.date_added = row['Date first added']
companies.append(company)
return companies
def save_company(self, tree):
company = Company()
#company introduction
l = tree.xpath('//div[contains(@class, \'jobs_txt\')]/p')
#print "company introduction:"
for i in l:
if not i.text is None:
#print i.text
company.introduction = i.text
#company name
l = tree.xpath('//td[@class=\'sr_bt\']')
for i in l:
tr = l[0].getparent()
print "company name:"
iters = tr.itersiblings();
for it in iters:
a_list = it.xpath('//td/table/tr/td/a')
for i in a_list:
if not i.text is None:
#print i.text
company.name = i.text
break
break
#company info
l = tree.xpath('//td/strong')
txt1_tag = ['公司行业：', '公司性质：', '公司规模：' ]
remove_from_list(l, txt1_tag)
for i in l:
td = i.getparent()
iters = td.itertext()
index = 0
for it in iters:
it = it.lstrip()
if it in txt1_tag:
continue
if index == 0:
company.industry = it
elif index == 1:
company.nature = it
elif index == 2:
company.scale = it
index += 1
#print "[%s]" % it.lstrip()
break
company.save()
def getCompanyInfo(dom):
'''获取一个公司的信息'''
info_items = dom('.companyInfoItems')
info_trs = info_items('.companyInfoTab tr')
company_info = {}
for tr in info_trs:
tr = pq(tr)
k = tr('td:eq(0)').text().split(u'：')[0]
v = tr('td:eq(1)').text()
company_info[k] = v
scale = company_info.get(u'公司规模')
if scale:
sh = re.search(r'(\d+)-(\d+)', scale)
scale = sh.groups() if sh else (None, None)
else:
scale = (None, None)
####
jcs = dom('.jobContact>div>div').find('div') # Job Contact
for jc in jcs:
jc = pq(jc)
jctext = jc.text().split(u'：')
if len(jctext) == 2:
k, v = jctext
company_info[k] = v
com = Company()
com.name = info_items('.companyTitle').text()
com.industry = company_info.get(u'公司行业')
com.type = company_info.get(u'公司类型')
com.address = company_info.get(u'公司地址')
com.website = company_info.get(u'公司主页')
com.scale_low, com.scale_high = scale
com.email = None
com.phone_num = None
com.description = dom('.black12 tr:eq(2)').find('td').html()
com.etag = ''
return com
def getCompanyInfo(dom):
'''获取一个公司的信息'''
info_items = dom('.companyInfoItems')
info_trs = info_items('.companyInfoTab tr')
company_info = {}
for tr in info_trs:
tr = pq(tr)
k = tr('td:eq(0)').text().split(u'：')[0]
v = tr('td:eq(1)').text()
company_info[k] = v
scale = company_info.get(u'公司规模')
if scale:
sh = re.search(r'(\d+)-(\d+)', scale)
scale = sh.groups() if sh else (None, None)
else:
scale = (None, None)
####
jcs = dom('.jobContact>div>div').find('div') # Job Contact
for jc in jcs:
jc = pq(jc)
jctext = jc.text().split(u'：')
if len(jctext) == 2:
k, v = jctext
company_info[k] = v
com = Company()
com.name = info_items('.companyTitle').text()
com.industry = company_info.get(u'公司行业')
com.type = company_info.get(u'公司类型')
com.address = company_info.get(u'公司地址')
com.website = company_info.get(u'公司主页')
com.scale_low, com.scale_high = scale
com.email = None
com.phone_num = None
com.description = dom('.black12 tr:eq(2)').find('td').html()
com.etag = ''
return com
