def parse_info(self, response):
uid = self._extract_uid(response.url)
for link in self.investment_link_extractor.extract_links(response):
yield HoldDepthRequest(url=link.url, callback=self.parse_investment, meta={'uid': uid})
item = CorpInfo('corp_info')
item['uid'] = uid
item['corp_name'] = safe_extract(response.xpath('//*[@id="companyheader"]/h3/span/text()'))
corp_info = response.css('.company-info')[0]
for li in corp_info.xpath('li'):
label = safe_strip(li.xpath('label/text()').extract_first(), chars=self.label_strip_chars)
field = self.label_to_field[label]
if field is 'legal_rep':
item[field] = safe_extract(li.xpath('a/text()'), sep='')
else:
item[field] = safe_extract(li.xpath('text()'), sep='')
# parse shareholders and related pages
shareholders = []
for a in response.css('tr.white>td>div>a[href*=firm]'):
# yield request
url = response.urljoin(a.xpath('@href').extract_first())
yield Request(url=url, callback=self.parse_info)
shareholder = Shareholder()
shareholder['name'] = safe_extract(a.xpath('span/text()'))
shareholder['corp_uid'] = self._extract_uid(url)
tr = a.xpath('../../..')
shareholder['holder_type'] = safe_extract(tr.xpath('td[2]/text()'))
shareholder['reg_amount'] = safe_extract(tr.xpath('td[3]/p/text()'), sep='/')
shareholder['paid_amount'] = safe_extract(tr.xpath('td[4]/p/text()'), sep='/')
shareholder['method'] = safe_extract(tr.xpath('td[5]/text()'))
shareholders.append(shareholder)
for a in response.css('tr.white>td>div>a[href*=search]'):
shareholder = Shareholder()
shareholder['name'] = safe_extract(a.xpath('text()'))
tr = a.xpath('../../../..')
shareholder['holder_type'] = safe_extract(tr.xpath('td[2]/text()'))
shareholder['reg_amount'] = safe_extract(tr.xpath('td[3]/p/text()'), sep='/')
shareholder['paid_amount'] = safe_extract(tr.xpath('td[4]/p/text()'), sep='/')
shareholder['method'] = safe_extract(tr.xpath('td[5]/text()'))
shareholders.append(shareholder)
item['shareholders'] = shareholders
# parse subsidiaries
subsidiaries = []
for a in response.css('tr.white>td>a'):
# yield request
url = response.urljoin(a.xpath('@href').extract_first())
yield Request(url=url, callback=self.parse_info)
subsidiary = Subsidiary()
subsidiary['corp_uid'] = self._extract_uid(url)
subsidiary['corp_name'] = safe_strip(a.xpath('text()').extract_first())
subsidiaries.append(subsidiary)
item['subsidiaries'] = subsidiaries
yield item
def _parse_subsidiaries(self, response):
trs = response.xpath('//table[@id="branchTable"]/tr[@class="page-item"]')
items = []
for tr in trs:
item = Subsidiary()
item['reg_no'] = safe_strip(tr.xpath('td[2]/text()').extract_first())
item['name'] = safe_strip(tr.xpath('td[3]/text()').extract_first())
item['reg_office'] = safe_strip(tr.xpath('td[4]/text()').extract_first())
items.append(item)
return items
def _parse_shareholders(self, response):
trs = response.xpath('//table[@id="investorTable"]/tr[@class="page-item"]')
items = []
for tr in trs:
item = Shareholder()
item['holder_type'] = safe_strip(tr.xpath('td[1]/text()').extract_first())
item['name'] = safe_strip(tr.xpath('td[2]/text()').extract_first())
item['license_type'] = safe_strip(tr.xpath('td[3]/text()').extract_first())
items.append(item)
return items
def parse_staff(self, response):
item = CorpInfo('corp_info')
item['stock_id'] = response.meta['stock_id']
staff = []
for tr in response.xpath('//div[@class="zx_left"]//table/tr[position() > 1]'):
s = Staff()
s['name'] = safe_strip(tr.xpath('td[1]/text()').extract_first())
s['title'] = safe_strip(tr.xpath('td[2]/text()').extract_first())
s['gender'] = safe_strip(tr.xpath('td[4]/text()').extract_first())
staff.append(s)
item['staff'] = staff
yield item
def _parse_staff(self, response):
trs = response.xpath('//table[@id="memberTable"]/tr[@class="page-item"]')
items = []
for tr in trs:
item = Staff()
item['name'] = safe_strip(tr.xpath('td[2]/text()').extract_first())
item['title'] = safe_strip(tr.xpath('td[3]/text()').extract_first())
items.append(item)
name = safe_strip(tr.xpath('td[5]/text()').extract_first())
if name != '':
item = Staff()
item['name'] = name
item['title'] = safe_strip(tr.xpath('td[6]/text()').extract_first())
items.append(item)
return items
def parse_shareholders(self, response):
item = CorpInfo('corp_info')
item['stock_id'] = response.meta['stock_id']
shareholders = []
table = response.css('div.zx_left table')[0]
rowspan = int(table.xpath('tr[2]/td/@rowspan').extract_first())
chars = '1234567890.'
for i in xrange(2, 2 + rowspan):
s = Shareholder()
if i == 2:
s['name'] = safe_strip(table.xpath('tr[%d]/td[2]/text()' % i).extract_first(), chars)
s['ratio'] = float(safe_strip(table.xpath('tr[%d]/td[4]/text()' % i).extract_first()))
else:
s['name'] = safe_strip(table.xpath('tr[%d]/td[1]/text()' % i).extract_first(), chars)
s['ratio'] = float(safe_strip(table.xpath('tr[%d]/td[3]/text()' % i).extract_first()))
shareholders.append(s)
item['shareholders'] = shareholders
yield item
def parse_investment(self, response):
item = CorpInfo('corp_info')
item['uid'] = response.meta['uid']
investments = []
for a in response.css('.site-list-title>a[href*=firm]'):
url = response.urljoin(a.xpath('@href').extract_first())
yield Request(url=url, callback=self.parse_info)
investment = Investment()
investment['corp_uid'] = self._extract_uid(url)
investment['corp_name'] = safe_strip(a.xpath('text()').extract_first())
investments.append(investment)
item['investments'] = investments
yield item
def parse_brief(self, response):
item = CorpInfo('corp_info')
item['stock_id'] = response.meta['stock_id']
table = response.css('div.zx_left table')[0]
item['name'] = safe_strip(table.xpath('tr[1]/td[2]/text()').extract_first())
item['eng_name'] = safe_strip(table.xpath('tr[2]/td[2]/text()').extract_first())
item['address'] = safe_strip(table.xpath('tr[3]/td[2]/text()').extract_first())
item['brief_name'] = safe_strip(table.xpath('tr[4]/td[2]/text()').extract_first())
item['legal_rep'] = safe_strip(table.xpath('tr[5]/td[2]/text()').extract_first())
item['reg_capital'] = safe_strip(table.xpath('tr[7]/td[2]/text()').extract_first())
item['busi_type'] = safe_strip(table.xpath('tr[8]/td[2]/text()').extract_first())
item['postcode'] = safe_strip(table.xpath('tr[9]/td[2]/text()').extract_first())
item['tel'] = safe_strip(table.xpath('tr[10]/td[2]/text()').extract_first())
item['fax'] = safe_strip(table.xpath('tr[11]/td[2]/text()').extract_first())
item['homepage'] = safe_strip(table.xpath('tr[12]/td[2]/text()').extract_first())
yield item
def parse(self, response):
table = response.css('#jibenxinxi table')[0]
if 'szcredit' in response.url:
item = LimitedCorpCredit(self.col_name)
item['reg_no'] = safe_strip(table.xpath('tr[3]/td[1]/span/text()').extract_first())
item['corp_name'] = safe_strip(table.xpath('tr[3]/td[2]/span/text()').extract_first())
item['corp_type'] = safe_strip(table.xpath('tr[4]/td[1]/span/text()').extract_first())
item['legal_rep'] = safe_strip(table.xpath('tr[4]/td[2]/span/text()').extract_first())
item['reg_capital'] = safe_strip(table.xpath('tr[5]/td[1]/span/text()').extract_first())
item['fund_date'] = safe_strip(table.xpath('tr[5]/td[2]/span/text()').extract_first())
item['address'] = safe_strip(table.xpath('tr[6]/td/span/text()').extract_first())
item['op_period_from'] = safe_strip(table.xpath('tr[7]/td[1]/span/text()').extract_first())
item['op_period_to'] = safe_strip(table.xpath('tr[7]/td[2]/span/text()').extract_first())
item['reg_office'] = safe_strip(table.xpath('tr[3]/td[1]/span/text()').extract_first())
item['appr_date'] = safe_strip(table.xpath('tr[3]/td[2]/span/text()').extract_first())
item['reg_status'] = safe_strip(table.xpath('tr[9]/td[1]/span/text()').extract_first())
elif len(table.xpath('tr')) == 9:
item = IndividualCorpCredit(self.col_name)
item['reg_no'] = safe_strip(table.xpath('tr[3]/td[1]/text()').extract_first())
item['corp_name'] = safe_strip(table.xpath('tr[3]/td[2]/text()').extract_first())
item['corp_type'] = safe_strip(table.xpath('tr[4]/td[1]/text()').extract_first())
item['investor'] = safe_strip(table.xpath('tr[4]/td[2]/text()').extract_first())
item['address'] = safe_strip(table.xpath('tr[5]/td/text()').extract_first())
item['fund_date'] = safe_strip(table.xpath('tr[6]/td[2]/text()').extract_first())
item['busi_scope'] = safe_strip(table.xpath('tr[7]/td/text()').extract_first())
item['reg_office'] = safe_strip(table.xpath('tr[8]/td[1]/text()').extract_first())
item['appr_date'] = safe_strip(table.xpath('tr[8]/td[2]/text()').extract_first())
item['reg_status'] = safe_strip(table.xpath('tr[9]/td[1]/text()').extract_first())
elif len(table.xpath('tr')) == 10:
item = LimitedCorpCredit(self.col_name)
item['reg_no'] = safe_strip(table.xpath('tr[3]/td[1]/text()').extract_first())
item['corp_name'] = safe_strip(table.xpath('tr[3]/td[2]/text()').extract_first())
item['corp_type'] = safe_strip(table.xpath('tr[4]/td[1]/text()').extract_first())
item['legal_rep'] = safe_strip(table.xpath('tr[4]/td[2]/text()').extract_first())
item['reg_capital'] = safe_strip(table.xpath('tr[5]/td[1]/text()').extract_first())
item['fund_date'] = safe_strip(table.xpath('tr[5]/td[2]/text()').extract_first())
item['address'] = safe_strip(table.xpath('tr[6]/td/text()').extract_first())
item['op_period_from'] = safe_strip(table.xpath('tr[7]/td[1]/text()').extract_first())
item['op_period_to'] = safe_strip(table.xpath('tr[7]/td[2]/text()').extract_first())
item['busi_scope'] = safe_strip(table.xpath('tr[8]/td/text()').extract_first())
item['reg_office'] = safe_strip(table.xpath('tr[9]/td[1]/text()').extract_first())
item['appr_date'] = safe_strip(table.xpath('tr[9]/td[2]/text()').extract_first())
item['reg_status'] = safe_strip(table.xpath('tr[10]/td[1]/text()').extract_first())
yield item
def parse(self, response):
table = response.xpath('//div[@rel="layout-01_01"][1]/table')[0]
item = LimitedCorpCredit(self.col_name)
item['reg_no'] = safe_strip(table.xpath('tr[2]/td[1]/text()').extract_first())
item['corp_name'] = safe_strip(table.xpath('tr[2]/td[2]/text()').extract_first())
item['corp_type'] = safe_strip(table.xpath('tr[3]/td[1]/text()').extract_first())
item['legal_rep'] = safe_strip(table.xpath('tr[3]/td[2]/text()').extract_first())
item['reg_capital'] = safe_strip(table.xpath('tr[4]/td[1]/text()').extract_first())
item['fund_date'] = safe_strip(table.xpath('tr[4]/td[2]/text()').extract_first())
item['address'] = safe_strip(table.xpath('tr[5]/td/text()').extract_first())
item['op_period_from'] = safe_strip(table.xpath('tr[6]/td[1]/text()').extract_first())
item['op_period_to'] = safe_strip(table.xpath('tr[6]/td[2]/text()').extract_first())
item['busi_scope'] = safe_strip(table.xpath('tr[7]/td/text()').extract_first())
item['reg_office'] = safe_strip(table.xpath('tr[8]/td[1]/text()').extract_first())
item['appr_date'] = safe_strip(table.xpath('tr[8]/td[2]/text()').extract_first())
item['reg_status'] = safe_strip(table.xpath('tr[9]/td[1]/text()').extract_first())
# sub items
item['shareholders'] = self._parse_shareholders(response)
item['main_staff'] = self._parse_staff(response)
item['subsidiaries'] = self._parse_subsidiaries(response)
yield item
