def tendering_info(self, response):
tr = Selector(response=response).xpath('//tr[@class="row"]')
print('招标信息', '---------', response.meta['company_name'])
for t in tr:
td = t.xpath('./td')
tendering_type = td[2].xpath('text()').extract_first()
tendering_method = td[3].xpath('text()').extract_first()
wining_bidder = td[4].xpath('text()').extract_first()
wining_number = td[5].xpath('text()').extract_first()
wining_data = td[6].xpath('text()').extract_first()
tendering = templates.Mark(companyName=response.meta['company_name'],
code=response.meta['code'],
tenderClass=tendering_type,
tenderType=tendering_method,
tenderNum=wining_number,
provinceTenderNum=wining_number,
tenderResultDate=wining_data,
tenderCorpName=wining_bidder,
tenderMoney=response.meta['tenderMoney'],
)
t_data = tendering.data()
yield scrapy.Request(url='https://api.maotouin.com/rest/companyInfo/addCompanyProjectTender.htm',
headers={'Content-Type': 'application/json'},
method='POST',
body=json.dumps(t_data),
callback=self.project_zz,
meta={'type': '招标'}
)
print('招标信息', t_data, '---------', response.meta['company_name'])
def bid_info(self, response):
attrs = [
{'that': '', 'attr': '//table[@width="100%"]/tr[3]/td[2]/text()', 'name': 'code'},
{'that': '', 'attr': '//table[@width="100%"]/tr[10]/td[2]/text()', 'name': 'tenderNum'},
{'that': '', 'attr': '//table[@width="100%"]/tr[10]/td[2]/text()', 'name': 'provinceTenderNum'},
{'that': '', 'attr': '//table[@width="100%"]/tr[11]/td[2]/text()', 'name': 'tenderClass'},
{'that': '', 'attr': '//table[@width="100%"]/tr[11]/td[4]/text()', 'name': 'tenderType'},
{'that': '', 'attr': '//table[@width="100%"]/tr[12]/td[2]/text()', 'name': 'tenderResultDate'},
{'that': '', 'attr': '//table[@width="100%"]/tr[12]/td[4]/text()', 'name': 'tenderMoney'},
{'that': '', 'attr': '//table[@width="100%"]/tr[13]/td[2]/text()', 'name': 'prjSize'},
{'that': '', 'attr': '//table[@width="100%"]/tr[13]/td[4]/text()', 'name': 'area'},
{'that': '', 'attr': '//table[@width="100%"]/tr[14]/td[2]/a/@title', 'name': 'agencyCorpName'},
{'that': '', 'attr': '//table[@width="100%"]/tr[14]/td[4]/text()', 'name': 'agencyCorpCode'},
{'that': '', 'attr': '//table[@width="100%"]/tr[15]/td[2]/a/text()', 'name': 'tenderCorpName'},
{'that': '', 'attr': '//table[@width="100%"]/tr[15]/td[4]/text()', 'name': 'tenderCorpCode'},
{'that': '', 'attr': '//table[@width="100%"]/tr[16]/td[2]/a/text()', 'name': 'constructorName'},
{'that': '', 'attr': '//table[@width="100%"]/tr[16]/td[4]/text()', 'name': 'constructorIDCard'},
{'that': '', 'attr': '//table[@width="100%"]/tr[17]/td[2]/a/text()', 'name': 'createDate'},
]
bid = templates.Projects('Mark')
bid_zz = bid.html_analysis(response=response, attrs=attrs)
bid_zz['companyName'] = response.meta['companyName']
bid_data = templates.Mark(**bid_zz)
bid_data = bid_data.data()
print(bid_data, '招标信息')
yield scrapy.Request(url='https://api.maotouin.com/rest/companyInfo/addCompanyProject.htm',
body=json.dumps(bid_data),
callback=self.project_zz,
headers={'Content-Type': 'application/json'}, method='POST',
meta={'type': '招标信息'}
)
def bid(self, response):
data_line = response.text
data_dict = re.split('jQuery\d+_\d+\(', data_line)[1]
data_dict = data_dict.replace(')', '')
json_data = json.loads(data_dict)
data = json_data['data']['TenderInfoList']
for d in data:
bid = templates.Mark(companyName=response.meta['companyName'], tenderNum=d['TenderNum'],
code=d['PrjNum'],
provinceTenderNum=d['TenderNum'], tenderResultDate=d['TenderResultDate'],
tenderType=d['TenderType'], tenderClass=d['TenderClass'],
tenderMoney=d['TenderMoney'],
)
bid_data = bid.data()
yield scrapy.Request(url='https://api.maotouin.com/rest/companyInfo/addCompanyProject.htm',
body=json.dumps(bid_data), callback=self.project_zz,
headers={'Content-Type': 'application/json'}, method='POST',
meta={'type': '招标'}
)
def win_bid(self, response):
tr = Selector(response=response).xpath('//table[@class="Tab"]/tr')
agencyCorpName = tr[5].xpath('./td[2]/span/text()').extract_first()
agencyCorpCode = tr[5].xpath('./td[4]/span/text()').extract_first()
tenderCorpName = tr[6].xpath('./td[2]/span/text()').extract_first()
tenderCorpCode = tr[6].xpath('./td[4]/span/text()').extract_first()
tenderType = tr[7].xpath('./td[2]/span/text()').extract_first()
tenderClass = tr[7].xpath('./td[4]/span/text()').extract_first()
tenderResultDate = tr[8].xpath('./td[2]/span/text()').extract_first()
tenderMoney = tr[8].xpath('./td[4]/span/text()').extract_first()
prjSize = tr[9].xpath('./td[2]/span/text()').extract_first()
area = tr[9].xpath('./td[4]/span/text()').extract_first()
constructorName = tr[10].xpath('./td[2]/text()').extract_first()
tenderNum = Selector(response=response).xpath(
'//span[@id="ctl00_ContentPlaceHolder1_FormView1_Label3"]/text()'
).extract_first()
bid = templates.Mark(companyName=response.meta['company_name'],
code=response.meta['code'],
tenderNum=tenderNum,
provinceTenderNum=tenderNum,
agencyCorpName=agencyCorpName,
agencyCorpCode=agencyCorpCode,
tenderCorpName=tenderCorpName,
tenderCorpCode=tenderCorpCode,
tenderType=tenderType,
tenderClass=tenderClass,
tenderResultDate=tenderResultDate,
tenderMoney=tenderMoney,
area=area,
prjSize=prjSize,
constructorName=constructorName)
b_data = bid.data()
yield scrapy.Request(
url=
'http://api.maotouin.com/rest/companyInfo/addCompanyProjectTender.htm',
headers={'Content-Type': 'application/json'},
callback=self.project_zz,
body=json.dumps(b_data),
method='POST',
meta={'type': '招标信息'})
print(bid.data(), '招标信息BBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBB')
def project(self, response):
basic = templates.Projects('Project')
attrs = [
{'that': '', 'attr': '//td[@id="lblPrjName"]/text()', 'name': 'name'},
{'that': '', 'attr': '//td[@id="lblPrjNum"]/text()', 'name': 'code'},
{'that': '', 'attr': '//td[@id="lblPrjNum"]/text()', 'name': 'provinceCode'},
{'that': '', 'attr': '//td[@id="lblPrjTypeNum"]/text()', 'name': 'catalog'},
{'that': '', 'attr': '//td[@id="lblBuildCorpName"]/text()', 'name': 'unit'},
{'that': '', 'attr': '//td[@id="lblBuildCorpCode"]/text()', 'name': 'unitLicenseNum'},
{'that': '', 'attr': '//td[@id="lblCountyNum"]/text()', 'name': 'area'},
{'that': '', 'attr': '//td[@id="lblPrjApprovalNum"]/text()', 'name': 'docuCode'},
{'that': '', 'attr': '//td[@id="lblPrjApprovalLevelNum"]/text()', 'name': 'level'},
{'that': '', 'attr': '//td[@id="lblAllInvest"]/text()', 'name': 'money'},
{'that': '', 'attr': '//td[@id="lblAllArea"]/text()', 'name': 'acreage'},
{'that': '', 'attr': '//td[@id="lblPrjPropertyNum"]/text()', 'name': 'trait'},
{'that': '', 'attr': '//td[@id="lblPrjFunctionNum"]/text()', 'name': 'purpose'},
]
basic_text = basic.html_analysis(response=response, attrs=attrs)
basic_text['companyName'] = response.meta['companyName']
if basic_text['level'] == '暂无':
basic_text['level'] = ''
basic_data = templates.Project(**basic_text)
basic_data = basic_data.data()
print('基本信息', '*******************************', basic_data)
yield scrapy.Request(url='https://api.maotouin.com/rest/companyInfo/addCompanyProject.htm',
body=json.dumps(basic_data), callback=self.project_zz,
headers={'Content-Type': 'application/json'}, method='POST',
meta={'type': '基本信息', 'company_name': basic_data['companyName']}
)
#
bid_list = Selector(response=response).xpath('//div[@id="project_step1"]/table/tbody/tr')
for b in bid_list:
tenderClass = b.xpath('./td[2]/text()').extract_first()
tenderType = b.xpath('./td[3]/text()').extract_first()
tenderCorpName = b.xpath('./td[4]/a/text()').extract_first()
tenderResultDate = b.xpath('./td[5]/text()').extract_first()
tenderMoney = b.xpath('./td[6]/text()').extract_first()
tenderNum = b.xpath('./td[7]/a/text()').extract_first()
bid_data = templates.Mark(tenderClass=tenderClass, tenderType=tenderType, tenderCorpName=tenderCorpName,
tenderResultDate=tenderResultDate, tenderMoney=tenderMoney, tenderNum=tenderNum,
provinceTenderNum=tenderNum, code=basic_data['code'],
companyName=response.meta['companyName']
)
bid_data = bid_data.data()
yield scrapy.Request(url='https://api.maotouin.com/rest/companyInfo/addCompanyProjectTender.htm',
body=json.dumps(bid_data), callback=self.project_zz,
headers={'Content-Type': 'application/json'}, method='POST',
meta={'type': '招标信息',}
)
# print('招标信息', '*******************************', bid_data)
drawing_list = Selector(response=response).xpath('//div[@id="project_step2"]/table/tbody/tr')
for d in drawing_list:
censorNum = d.xpath('./td[2]/text()').extract_first()
provinceCensorNum = d.xpath('./td[3]/text()').extract_first()
surveyCorpName = d.xpath('./td[4]/a/text()').extract_first()
designCorpName = d.xpath('./td[5]/a/text()').extract_first()
censorCorpName = d.xpath('./td[6]/a/text()').extract_first()
censorEDate = d.xpath('./td[7]/a/text()').extract_first()
drawing_data = templates.MakeDrawing(censorNum=censorNum, provinceCensorNum=provinceCensorNum,
surveyCorpName=surveyCorpName,
designCorpName=designCorpName, censorCorpName=censorCorpName,
censorEDate=censorEDate, code=basic_data['code'],
companyName=response.meta['companyName']
)
drawing_data = drawing_data.data()
yield scrapy.Request(url='https://api.maotouin.com/rest/companyInfo/addCompanyProjectCensor.htm',
body=json.dumps(drawing_data), callback=self.project_zz,
headers={'Content-Type': 'application/json'}, method='POST',
meta={'type': '施工图纸审查', }
)
print('施工图纸审查', '*******************************', drawing_data)
contract_list = Selector(response=response).xpath('//div[@id="project_step3"]/table/tbody/tr')
for d in contract_list:
contractType = d.xpath('./td[2]/text()').extract_first()
recordNum = d.xpath('./td[3]/text()').extract_first()
provinceRecordNum = d.xpath('./td[4]/text()').extract_first()
contractMoney = d.xpath('./td[5]/text()').extract_first()
contractDate = d.xpath('./td[6]/text()').extract_first()
contract_data = templates.Contract(contractType=contractType, recordNum=recordNum,
provinceRecordNum=provinceRecordNum,
contractMoney=contractMoney,
contractDate=contractDate, code=basic_data['code'],
companyName=response.meta['companyName']
)
contract_data = contract_data.data()
yield scrapy.Request(url='https://api.maotouin.com/rest/companyInfo/addCompanyProjectContract.htm',
body=json.dumps(contract_data), callback=self.project_zz,
headers={'Content-Type': 'application/json'}, method='POST',
meta={'type': '合同备案', }
)
print('合同备案', '*******************************', contract_data)
print(response.url, 'XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX')
construction_list = Selector(response=response).xpath('//div[@id="project_step4"]/table/tbody/tr')
for d in construction_list:
builderLicenceNum = d.xpath('./td[2]/text()').extract_first()
consCorpName = d.xpath('./td[3]/a/text()').extract_first()
contractMoney = d.xpath('./td[4]/text()').extract_first()
area = d.xpath('./td[5]/text()').extract_first()
createDate = d.xpath('./td[6]/text()').extract_first()
construction_data = templates.ConstructionPermit(builderLicenceNum=builderLicenceNum, provinceBuilderLicenceNum=builderLicenceNum,
consCorpName=consCorpName,
contractMoney=contractMoney,
area=area, code=basic_data['code'],
createDate=createDate,
companyName=response.meta['companyName']
)
construction_data = construction_data.data()
yield scrapy.Request(url='https://api.maotouin.com/rest/companyInfo/addCompanyProjectBuilderLicence.htm',
body=json.dumps(construction_data), callback=self.project_zz,
headers={'Content-Type': 'application/json'}, method='POST',
meta={'type': '施工许可', }
)
print('施工许可', '*******************************', construction_data)
completion_list = Selector(response=response).xpath('//div[@id="project_step4"]/table/tbody/tr')
for c in completion_list:
prjFinishNum = c.xpath('./td[2]/text()').extract_first()
provincePrjFinishNum = c.xpath('./td[3]/a/text()').extract_first()
factCost = c.xpath('./td[4]/text()').extract_first()
factArea = c.xpath('./td[5]/text()').extract_first()
factBeginDate = c.xpath('./td[6]/text()').extract_first()
factEndDate = c.xpath('./td[6]/text()').extract_first()
completion_data = templates.Completion(prjFinishNum=prjFinishNum,
provincePrjFinishNum=provincePrjFinishNum,
factCost=factCost,
factArea=factArea,
factBeginDate=factBeginDate,
code=basic_data['code'],
factEndDate=factEndDate,
companyName=response.meta['companyName']
)
completion_data = completion_data.data()
yield scrapy.Request(
url='https://api.maotouin.com/rest/companyInfo/addCompanyProjectFinish.htm',
body=json.dumps(completion_data), callback=self.project_zz,
headers={'Content-Type': 'application/json'}, method='POST',
meta={'type': '竣工验收', }
)
print('竣工验收', '*******************************', completion_data)
def company_project(self, response):
basic = Selector(response=response).xpath('//table[@class="detailTable"]')[0]
basic_tr = basic.xpath('./tr')
project_name = basic_tr[1].xpath('./td')[3].xpath('text()').extract_first()
project_number = basic_tr[1].xpath('./td')[1].xpath('text()').extract_first()
area = basic_tr[3].xpath('./td')[3].xpath('text()').extract_first()
if area is not None:
area_data = ''
for a in area.split():
area_data += a
else:
area_data = ''
unit = basic_tr[2].xpath('./td')[3].xpath('text()').extract_first()
unitLicenseNum = basic_tr[3].xpath('./td')[1].xpath('text()').extract_first()
catalog = basic_tr[2].xpath('./td')[1].xpath('text()').extract_first()
traits = basic_tr[7].xpath('./td')[3].xpath('text()').extract_first()
purpose = basic_tr[8].xpath('./td')[1].xpath('text()').extract_first()
money = basic_tr[6].xpath('./td')[1].xpath('text()').extract_first()
acreage = basic_tr[6].xpath('./td')[3].xpath('text()').extract_first()
level = basic_tr[4].xpath('./td')[3].xpath('text()').extract_first()
docuCode = basic_tr[4].xpath('./td')[1].xpath('text()').extract_first()
ccc = templates.Project(name=project_name, companyName=response.meta['company_name'],
area=area_data, provinceCode=project_number, unit=unit, unitLicenseNum=unitLicenseNum,
catalog=catalog, trait=traits, purpose=purpose, money=money, acreage=acreage,
level=level,
docuCode=docuCode, code=project_number
)
basic_data = ccc.data()
print('基本信息', basic_data)
yield scrapy.Request(url='https://api.maotouin.com/rest/companyInfo/addCompanyProject.htm',
headers={'Content-Type': 'application/json'},
method='POST',
body=json.dumps(basic_data),
callback=self.project_zz,
meta={'type': '基本信息', 'company_name': basic_data['companyName']}
)
# print(data)
mark = Selector(response=response).xpath('//table[@class="detailTable"]')[1]
mark_tr = mark.xpath('./tr')
del mark_tr[0]
mark_list = [k for index, k in enumerate(mark_tr) if (index % 2 != 0)]
print(len(mark_list), 'mmmmmmmmmmmmmmmmmmmm')
for m in mark_list:
td = m.xpath('./td')
if len(td) == 1:
pass
# print(len(td), '没有招标信息的', project_name)
else:
project_code = td[0].xpath('./a/text()').extract_first()
build_size = td[1].xpath('text()').extract_first()
mark_name = td[2].xpath('text()').extract_first()
have_project = td[3].xpath('text()').extract_first()
mark_data = templates.Mark(companyName=response.meta['company_name'],
tenderNum=project_code,
prjSize=build_size,
provinceTenderNum=project_code,
agencyCorpName=mark_name,
tenderCorpName=have_project,
code=project_number)
make_zz_data = mark_data.data()
print(project_code, build_size, mark_name, have_project, '招标信息')
yield scrapy.Request(url='https://api.maotouin.com/rest/companyInfo/addCompanyProjectTender.htm',
method='POST',
headers={'Content-Type': 'application/json'},
body=json.dumps(make_zz_data),
callback=self.project_zz,
meta={'type': '招标信息'}
)
contract = Selector(response=response).xpath('//table[@class="detailTable"]')[2]
contract = contract.xpath('./tr')
del contract[0]
contract_list = [k for index, k in enumerate(contract) if (index % 2 != 0)]
for m in contract_list:
td = m.xpath('./td')
if len(td) == 1:
print(len(td), '没有合同信息的', project_name)
else:
contract_mark_number = td[0].xpath('text()').extract_first()
contract_number = td[1].xpath('text()').extract_first()
send_company = td[2].xpath('text()').extract_first()
make_company = td[3].xpath('text()').extract_first()
union_company = td[4].xpath('text()').extract_first()
contract_object = templates.Contract(companyName=response.meta['company_name'],
code=project_number,
recordNum=contract_mark_number, contractNum=contract_number,
proprietorCorpName=send_company, contractorCorpName=make_company,
unionCorpName=union_company, provinceRecordNum=contract_mark_number
)
contract_data = contract_object.data()
print('合同信息', contract_data)
yield scrapy.Request(url='https://api.maotouin.com/rest/companyInfo/addCompanyProjectContract'
'.htm',
method='POST',
headers={'Content-Type': 'application/json'},
body=json.dumps(contract_data),
callback=self.project_zz,
meta={'type': '合同信息'}
)
make_drawing = Selector(response=response).xpath('//table[@class="detailTable"]')[3]
make_drawing = make_drawing.xpath('./tr')
make_see_number = make_drawing[1].xpath('./td')[1].xpath('text()').extract_first()
make_see_name = make_drawing[1].xpath('./td')[3].xpath('text()').extract_first()
drawing_num = make_drawing[2].xpath('./td')[1].xpath('text()').extract_first()
see_date = make_drawing[2].xpath('./td')[3].xpath('text()').extract_first()
see_name = make_drawing[3].xpath('./td')[1].xpath('text()').extract_first()
see_num = make_drawing[3].xpath('./td')[3].xpath('text()').extract_first()
desgin_name = make_drawing[4].xpath('./td')[1].xpath('text()').extract_first()
desgin_num = make_drawing[4].xpath('./td')[3].xpath('text()').extract_first()
make_size = make_drawing[5].xpath('./td')[1].xpath('text()').extract_first()
ok_pass = make_drawing[5].xpath('./td')[3].xpath('text()').extract_first()
see_error = make_drawing[6].xpath('./td')[1].xpath('text()').extract_first()
see_number = make_drawing[6].xpath('./td')[3].xpath('text()').extract_first()
drawing = templates.MakeDrawing(
censorNum=make_see_number,
censorCorpName=make_see_name,
censorCorpCode=drawing_num,
censorEDate=see_date,
surveyCorpName=see_name,
surveyCorpCode=see_num,
designCorpName=desgin_name,
designCorpCode=desgin_num,
companyName=response.meta['company_name'],
code=project_number,
prjSize=make_size,
engineers=[],
provinceCensorNum=make_see_number
)
drawing_data = drawing.data()
if drawing_data['censorNum']:
print(drawing_data, '施工图纸信息')
yield scrapy.Request(url='https://api.maotouin.com/rest/companyInfo/addCompanyProjectCensor.htm',
headers={'Content-Type': 'application/json'},
method='POST',
body=json.dumps(drawing_data),
callback=self.project_zz,
meta={'type': '施工图纸信息'}
)
construction = Selector(response=response).xpath('//table[@class="detailTable"]')[5]
construction_tr = construction.xpath('./tr')
# 施工许可证系统备案编号
construction_num = construction_tr[1].xpath('./td')[1].xpath('text()').extract_first()
# 暂时用不到
usr_plan_land_num = construction_tr[1].xpath('./td')[3].xpath('text()').extract_first()
# 暂时用不到
usr_make_land_num = construction_tr[2].xpath('./td')[1].xpath('text()').extract_first()
# 施工图审查合格书编号
qualified_num = construction_tr[2].xpath('./td')[3].xpath('text()').extract_first()
# 合同金额(万元)
money_capital = construction_tr[3].xpath('./td')[1].xpath('text()').extract_first()
# 面积（平方米）
construction_area = construction_tr[3].xpath('./td')[3].xpath('text()').extract_first()
# 建设规模暂时用不到
construction_size = construction_tr[4].xpath('./td')[1].xpath('text()').extract_first()
# 发证日期
construction_date = construction_tr[4].xpath('./td')[3].xpath('text()').extract_first()
# 勘察单位名称
c_survey_name = construction_tr[5].xpath('./td')[1].xpath('text()').extract_first()
# 勘察单位组织机构代码
c_survey_num = construction_tr[5].xpath('./td')[3].xpath('text()').extract_first()
# 设计单位名称
c_degsin_name = construction_tr[6].xpath('./td')[1].xpath('text()').extract_first()
# 设计单位组织机构代码
c_degsin_num = construction_tr[6].xpath('./td')[3].xpath('text()').extract_first()
# 施工单位名称
c_make_name = construction_tr[7].xpath('./td')[1].xpath('text()').extract_first()
# 施工单位组织机构代码
c_make_num = construction_tr[7].xpath('./td')[3].xpath('text()').extract_first()
# 施工单位安全生产许可证编号
c_make_safe_num = construction_tr[8].xpath('./td')[1].xpath('text()').extract_first()
# 监理单位名称
c_supervisor_name = construction_tr[8].xpath('./td')[3].xpath('text()').extract_first()
# 监理单位组织机构代码
c_supervisor_num = construction_tr[9].xpath('./td')[1].xpath('text()').extract_first()
# 项目经理姓名
c_project_person_name = construction_tr[9].xpath('./td')[3].xpath('text()').extract_first()
# 施工图审查人员证件类型
c_name_person_idctype = construction_tr[10].xpath('./td')[1].xpath('text()').extract_first()
# 项目经理身份证
c_name_person_idcard = construction_tr[10].xpath('./td')[3].xpath('text()').extract_first()
# 总监理工程师姓名
c_chief_name = construction_tr[11].xpath('./td')[1].xpath('text()').extract_first()
# 总监理工程师证件类型
c_chief_idtype = construction_tr[11].xpath('./td')[3].xpath('text()').extract_first()
# 总监理工程师证件号码
c_chief_idcard = construction_tr[12].xpath('./td')[1].xpath('text()').extract_first()
# 安全生产管理人员姓名
c_safe_manager = construction_tr[12].xpath('./td')[3].xpath('text()').extract_first()
# 安全生产管理证件类型
c_safe_idtype = construction_tr[13].xpath('./td')[1].xpath('text()').extract_first()
# 安全生产管理人员姓名
c_safe_idcard = construction_tr[13].xpath('./td')[3].xpath('text()').extract_first()
# 安全生产考核合格证书编号
c_safe_assessenment_num = construction_tr[14].xpath('./td')[1].xpath('text()').extract_first()
# 安全生产管理人员类型
c_safe_assessenment_type = construction_tr[14].xpath('./td')[3].xpath('text()').extract_first()
construction_model = templates.ConstructionPermit(builderLicenceNum=construction_num, censorNum=qualified_num,
contractMoney=money_capital, area=construction_area,
econCorpName=c_survey_name, econCorpCode=c_survey_num,
designCorpName=c_degsin_name, designCorpCode=c_degsin_num,
consCorpName=c_make_name, consCorpCode=c_make_num,
superCorpName=c_supervisor_name,
superCorpCode=c_supervisor_num,
constructorName=c_project_person_name,
constructorIDCard=c_name_person_idcard,
supervisionName=c_chief_name,
supervisionIDCard=c_chief_idcard,
companyName=response.meta['company_name'],
code=project_number,
provinceBuilderLicenceNum=construction_num
)
construction_make_data = construction_model.data()
print('施工许可信息', construction_make_data)
if construction_make_data['builderLicenceNum']:
yield scrapy.Request(url='https://api.maotouin.com/rest/companyInfo'
'/addCompanyProjectBuilderLicence.htm',
headers={'Content-Type': 'application/json'},
method='POST',
body=json.dumps(construction_make_data),
callback=self.project_zz,
meta={'type': '施工许可信息'}
)
completion_info = Selector(response=response).xpath('//table[@class="detailTable"]')[8]
completion_tr = completion_info.xpath('./tr')
# 竣工备案编号
completion_num = completion_tr[1].xpath('./td')[1].xpath('text()').extract_first()
# 施工许可证编号
completion_make_numer = completion_tr[1].xpath('./td')[3].xpath('text()').extract_first()
# 质量检测机构名称
test_name = completion_tr[2].xpath('./td')[1].xpath('text()').extract_first()
# 质量检测机构组织机构代码
test_number = completion_tr[2].xpath('./td')[3].xpath('text()').extract_first()
# 实际造价（万元）
actual_capital = completion_tr[3].xpath('./td')[1].xpath('text()').extract_first()
# 实际面积（平方米）
actual_area = completion_tr[3].xpath('./td')[3].xpath('text()').extract_first()
# 实际建设规模
actual_size = completion_tr[4].xpath('./td')[1].xpath('text()').extract_first()
# 结构体系
c_body = completion_tr[4].xpath('./td')[3].xpath('text()').extract_first()
# 备注
remarks = completion_tr[5].xpath('./td')[1].xpath('text()').extract_first()
Completion_data = templates.Completion(
companyName=response.meta['company_name'], code=project_number, prjFinishNum=completion_num,
factCost=actual_capital, factArea=actual_area, factSize=actual_size, prjStructureType=c_body,
mark=remarks, provincePrjFinishNum=completion_num
)
Completion_zz = Completion_data.data()
if Completion_zz['prjFinishNum']:
print('当前公司----%s---%s--竣工数据' % (project_name, Completion_zz))
yield scrapy.Request(url='https://api.maotouin.com/rest/companyInfo/addCompanyProjectFinish.htm',
headers={'Content-Type': 'application/json'},
method='POST',
body=json.dumps(Completion_zz),
callback=self.project_zz,
meta={'type': '竣工验收'}
)
def bid_info(self, response):
attrs = [
{
'that': '',
'attr': '//td[@class="name_level3 col_01_value"]/span/text()',
'name': 'code'
},
{
'that': '',
'attr': '//span[@id="lblTenderMoney"]/text()',
'name': 'tenderMoney'
},
{
'that': '',
'attr': '//span[@id="lblArea"]/text()',
'name': 'area'
},
{
'that': '',
'attr': '//span[@id="lblTenderNum"]/text()',
'name': 'tenderNum'
},
{
'that': '',
'attr': '//span[@id="lblTenderNum"]/text()',
'name': 'provinceTenderNum'
},
{
'that': '',
'attr': '//span[@id="lblTenderClassNum"]/text()',
'name': 'tenderClass'
},
{
'that': '',
'attr': '//span[@id="lblTenderTypeNum"]/text()',
'name': 'tenderType'
},
{
'that': '',
'attr': '//span[@id="lblTenderResultDate"]/text()',
'name': 'tenderResultDate'
},
{
'that': '',
'attr': '//span[@id="lblPrjSize"]/text()',
'name': 'prjSize'
},
{
'that': '',
'attr': '//span[@id="lblAgencyCorpName"]/text()',
'name': 'agencyCorpName'
},
{
'that': '',
'attr': '//span[@id="lblAgencyCorpCode"]/text()',
'name': 'agencyCorpCode'
},
{
'that': '',
'attr': '//span[@id="lblTenderCorpName"]/text()',
'name': 'tenderCorpName'
},
{
'that': '',
'attr': '//span[@id="lblTenderCorpCode"]/text()',
'name': 'tenderCorpCode'
},
{
'that': '',
'attr': '//span[@id="lblCreateDate"]/text()',
'name': 'createDate'
},
{
'that': '',
'attr': '//span[@id="lblConstructorName"]/text()',
'name': 'constructorName'
},
{
'that': '',
'attr': '//span[@id="lblConstructorIDCard"]/text()',
'name': 'constructorIDCard'
},
]
bid_object = templates.Projects('Mark')
bid_data = bid_object.html_analysis(response, attrs)
bid_data['companyName'] = response.meta['companyName']
bid_zz = templates.Mark(**bid_data)
bid_zz = bid_zz.data()
bid_zz['code'] = response.meta['code']
print(bid_zz, '招标信息')
yield scrapy.Request(
url=
'https://api.maotouin.com/rest/companyInfo/addCompanyProjectTender.htm',
body=json.dumps(bid_zz),
callback=self.project_zz,
headers={'Content-Type': 'application/json'},
method='POST',
meta={'type': '招标信息'})