def finish_info(self, response):
attrs = [
{'that': '', 'attr': '//div[@class="detail"][1]/div[@class="detail_list"]/table/tr[3]/td[2]/text()',
'name': 'code'},
{'that': '', 'attr': '//div[@class="detail"][1]/div[@class="detail_list"]/table/tr[10]/td[2]/text()',
'name': 'prjFinishNum'},
{'that': '', 'attr': '//div[@class="detail"][1]/div[@class="detail_list"]/table/tr[10]/td[2]/text()',
'name': 'provincePrjFinishNum'},
{'that': '', 'attr': '//div[@class="detail"][1]/div[@class="detail_list"]/table/tr[11]/td[2]/text()',
'name': 'factCost'},
{'that': '', 'attr': '//div[@class="detail"][1]/div[@class="detail_list"]/table/tr[11]/td[4]/text()',
'name': 'factArea'},
{'that': '', 'attr': '//div[@class="detail"][1]/div[@class="detail_list"]/table/tr[12]/td[2]/text()',
'name': 'factSize'},
{'that': '', 'attr': '//div[@class="detail"][1]/div[@class="detail_list"]/table/tr[13]/td[2]/text()',
'name': 'factBeginDate'},
{'that': '', 'attr': '//div[@class="detail"][1]/div[@class="detail_list"]/table/tr[13]/td[4]/text()',
'name': 'factEndDate'},
{'that': '', 'attr': '//div[@class="detail"][1]/div[@class="detail_list"]/table/tr[14]/td[2]/text()',
'name': 'createDate'},
{'that': '', 'attr': '//div[@class="detail"][1]/div[@class="detail_list"]/table/tr[14]/td[4]/text()',
'name': 'mark'},
]
finish = templates.Projects('Completion')
finish = finish.html_analysis(response=response, attrs=attrs)
finish['companyName'] = response.meta['companyName']
finish_data = templates.Completion(**finish)
print(finish_data.data(), '竣工')
contract_data = finish_data.data()
yield scrapy.Request(url='https://api.maotouin.com/rest/companyInfo/addCompanyProjectFinish.htm',
body=json.dumps(contract_data),
callback=self.project_zz, method='POST',
headers={'Content-Type': 'application/json'},
meta={'type': '竣工'}
)
def contract_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': 'recordNum'},
{'that': '', 'attr': '//table[@width="100%"]/tr[10]/td[2]/text()', 'name': 'provinceRecordNum'},
{'that': '', 'attr': '//table[@width="100%"]/tr[12]/td[2]/text()', 'name': 'contractType'},
{'that': '', 'attr': '//table[@width="100%"]/tr[12]/td[4]/text()', 'name': 'contractMoney'},
{'that': '', 'attr': '//table[@width="100%"]/tr[13]/td[2]/text()', 'name': 'prjSize'},
{'that': '', 'attr': '//table[@width="100%"]/tr[13]/td[4]/text()', 'name': 'contractDate'},
{'that': '', 'attr': '//table[@width="100%"]/tr[14]/td[2]/a/@title', 'name': 'proprietorCorpName'},
{'that': '', 'attr': '//table[@width="100%"]/tr[14]/td[4]/text()', 'name': 'proprietorCorpCode'},
{'that': '', 'attr': '//table[@width="100%"]/tr[15]/td[2]/a/text()', 'name': 'contractorCorpName'},
{'that': '', 'attr': '//table[@width="100%"]/tr[15]/td[4]/text()', 'name': 'contractorCorpCode'},
{'that': '', 'attr': '//table[@width="100%"]/tr[16]/td[2]/a/text()', 'name': 'unionCorpName'},
{'that': '', 'attr': '//table[@width="100%"]/tr[16]/td[4]/text()', 'name': 'unionCorpCode'},
{'that': '', 'attr': '//table[@width="100%"]/tr[17]/td[2]/a/text()', 'name': 'createDate'},
]
contract = templates.Projects('Contract')
contract = contract.html_analysis(response=response, attrs=attrs)
contract['companyName'] = response.meta['companyName']
contract_data = templates.Contract(**contract)
contract_data = contract_data.data()
print(contract_data, '合同信息')
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': '合同信息'}
)
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 construction_info(self, response):
attrs = [
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[3]/td[2]/text()', 'name': 'code'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[10]/td[2]/text()', 'name': 'builderLicenceNum'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[10]/td[2]/text()',
'name': 'provinceBuilderLicenceNum'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[11]/td[2]/text()', 'name': 'censorNum'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[11]/td[4]/text()', 'name': 'contractMoney'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[12]/td[2]/a/@title', 'name': 'constructorName'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[12]/td[4]/text()', 'name': 'constructorIDCard'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[13]/td[2]/a/text()', 'name': 'supervisionName'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[13]/td[4]/text()', 'name': 'supervisionIDCard'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[14]/td[2]/text()', 'name': 'area'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[14]/td[4]/text()', 'name': 'createDate'},
{'that': '', 'attr': '//div[@class="classContent t1"]/table/tr[2]/td[3]/a/text()',
'name': 'designCorpName'},
{'that': '', 'attr': '//div[@class="classContent t1"]/table/tr[2]/td[4]/text()', 'name': 'designCorpCode'},
{'that': '', 'attr': '//div[@class="classContent t1"]/table/tr[2]/td[5]/text()', 'name': 'designCorpArea'},
{'that': '', 'attr': '//div[@class="classContent t1"]/table/tr[3]/td[3]/a/text()', 'name': 'econCorpName'},
{'that': '', 'attr': '//div[@class="classContent t1"]/table/tr[3]/td[4]/text()', 'name': 'econCorpCode'},
{'that': '', 'attr': '//div[@class="classContent t1"]/table/tr[3]/td[5]/text()', 'name': 'econCorpArea'},
{'that': '', 'attr': '//div[@class="classContent t1"]/table/tr[4]/td[3]/a/text()', 'name': 'consCorpName'},
{'that': '', 'attr': '//div[@class="classContent t1"]/table/tr[4]/td[4]/text()', 'name': 'consCorpCode'},
{'that': '', 'attr': '//div[@class="classContent t1"]/table/tr[4]/td[5]/text()', 'name': 'consCorpArea'},
{'that': '', 'attr': '//div[@class="classContent t1"]/table/tr[5]/td[3]/a/text()', 'name': 'superCorpName'},
{'that': '', 'attr': '//div[@class="classContent t1"]/table/tr[5]/td[4]/text()', 'name': 'superCorpCode'},
{'that': '', 'attr': '//div[@class="classContent t1"]/table/tr[5]/td[5]/text()', 'name': 'superCorpArea'},
]
construction = templates.Projects('ConstructionPermit')
construction = construction.html_analysis(response=response, attrs=attrs)
construction['companyName'] = response.meta['companyName']
construction_data = templates.ConstructionPermit(**construction)
print(construction_data.data(), '施工许可信息录入')
contract_data = construction_data.data()
yield scrapy.Request(url='https://api.maotouin.com/rest/companyInfo/addCompanyProjectBuilderLicence.htm',
body=json.dumps(contract_data),
callback=self.project_zz, method='POST',
headers={'Content-Type': 'application/json'},
meta={'type': '施工许可信息录入'}
)
def project(self, response):
basic_info = templates.Projects('Project')
attrs = [
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[1]/td[2]/text()', 'name': 'name'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[2]/td[2]/text()', 'name': 'code'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[2]/td[2]/text()', 'name': 'provinceCode'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[3]/td[2]/text()', 'name': 'unit'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[3]/td[4]/text()', 'name': 'catalog'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[4]/td[2]/text()', 'name': 'unitLicenseNum'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[4]/td[4]/text()', 'name': 'area'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[6]/td[2]/text()', 'name': 'docuCode'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[6]/td[4]/text()', 'name': 'level'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[7]/td[2]/text()', 'name': 'money'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[7]/td[4]/text()', 'name': 'acreage'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[8]/td[2]/text()', 'name': 'trait'},
{'that': '', 'attr': '//div[@class="detail_list"]/table/tr[8]/td[4]/text()', 'name': 'purpose'},
]
basic_data = basic_info.html_analysis(response, attrs)
basic_data['companyName'] = response.meta['companyName']
basic = templates.Project(**basic_data)
b_data = basic.data()
print(b_data, '基本信息', b_data['companyName'])
yield scrapy.Request(
# url='https://api.maotouin.com/rest/companyInfo/addCompanyProject.htm',
url='https://api.maotouin.com/rest/companyInfo/addCompanyProject.htm',
body=json.dumps(b_data),
callback=self.project_zz,
headers={'Content-Type': 'application/json'}, method='POST',
meta={'type': '基本信息', 'company_name': b_data['companyName']}
)
bid_url = Selector(response=response).xpath('//div[@class="classContent t1"]/table/tr')
bid_url = bid_url[1:]
for b in bid_url:
a = b.xpath('./td[7]/a/@href').extract_first()
a = 'http://115.29.2.37:8080/' + a
yield scrapy.Request(url=a, callback=self.bid_info, headers=heads,
meta={'companyName': response.meta['companyName']}
)
drawing_info = Selector(response=response).xpath('//div[@class="classContent t2"]/table/tr')
drawing_info = drawing_info[1:]
print(len(drawing_info), '施工图纸审查----bbbbbbbbbbbbbbbbbbbbbbbbbbbbb', response.url)
for d in drawing_info:
censorNum = d.xpath('./td[2]/text()').extract_first()
surveyCorpName = d.xpath('./td[3]/text()').extract_first()
designCorpName = d.xpath('./td[4]/text()').extract_first()
censorCorpName = d.xpath('./td[5]/text()').extract_first()
censorEDate = d.xpath('./td[6]/text()').extract_first()
drawing_data = templates.MakeDrawing(censorNum=censorNum, surveyCorpName=surveyCorpName,
designCorpName=designCorpName, censorCorpName=censorCorpName,
censorEDate=censorEDate
)
drawing_data = drawing_data.data()
print(drawing_data, '施工图纸审查')
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'}
)
contract_list = Selector(response=response).xpath('//div[@class="classContent t3"]/table/tr')
contract_list = contract_list[1:]
for c in contract_list:
print(c.xpath('./td[6]/a/@href').extract_first(), '合同备案url')
u = 'http://115.29.2.37:8080/' + c.xpath('./td[6]/a/@href').extract_first()
yield scrapy.Request(url=u, callback=self.contract_info,
meta={'companyName': response.meta['companyName']})
construction_list = Selector(response=response).xpath('//div[@class="classContent t4"]/table/tr/td/a/@href')
for c in construction_list:
u = 'http://115.29.2.37:8080/' + c.extract()
yield scrapy.Request(url=u, callback=self.construction_info,
meta={'companyName': response.meta['companyName']})
finish_list = Selector(response=response).xpath('//div[@class="classContent t5"]/table/tr/td/a/@href')
for f in finish_list:
u = 'http://115.29.2.37:8080/' + f.extract()
yield scrapy.Request(url=u, callback=self.finish_info,
meta={'companyName': response.meta['companyName']})
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 construction_info(self, response):
attrs = [
{
'that': '',
'attr': '//span[@id="lblPrjNum"]/text()',
'name': 'code'
},
{
'that': '',
'attr': '//span[@id="lblBuilderLicenceNum"]/text()',
'name': 'builderLicenceNum'
},
{
'that': '',
'attr': '//span[@id="lblBuilderLicenceNum"]/text()',
'name': 'provinceBuilderLicenceNum'
},
{
'that': '',
'attr': '//span[@id="lblCensorNum"]/text()',
'name': 'censorNum'
},
{
'that': '',
'attr': '//span[@id="lblContractMoney"]/text()',
'name': 'contractMoney'
},
{
'that': '',
'attr': '//span[@id="lblArea"]/text()',
'name': 'area'
},
{
'that': '',
'attr': '//span[@id="lblConstructorName"]/text()',
'name': 'constructorName'
},
{
'that': '',
'attr': '//span[@id="lblConstructorIDCard"]/text()',
'name': 'constructorIDCard'
},
{
'that': '',
'attr': '//span[@id="lblSupervisionName"]/text()',
'name': 'supervisionName'
},
{
'that': '',
'attr': '//span[@id="lblSupervisionIDCard"]/text()',
'name': 'supervisionIDCard'
},
{
'that': '',
'attr': '//span[@id="lblCreateDate"]/text()',
'name': 'createDate'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[2]/td[2]/a/text()',
'name': 'designCorpName'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[2]/td[3]/text()',
'name': 'designCorpCode'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[2]/td[4]/text()',
'name': 'designCorpArea'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[3]/td[2]/a/text()',
'name': 'consCorpName'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[3]/td[3]/text()',
'name': 'consCorpCode'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[3]/td[4]/text()',
'name': 'consCorpArea'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[4]/td[2]/a/text()',
'name': 'superCorpName'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[4]/td[3]/text()',
'name': 'superCorpCode'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[4]/td[4]/text()',
'name': 'superCorpArea'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[5]/td[2]/a/text()',
'name': 'econCorpName'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[5]/td[3]/text()',
'name': 'econCorpCode'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[5]/td[4]/text()',
'name': 'econCorpArea'
},
]
contract_object = templates.Projects('ConstructionPermit')
construction_data = contract_object.html_analysis(response, attrs)
construction_data['companyName'] = response.meta['companyName']
construction_zz = templates.ConstructionPermit(**construction_data)
construction_zz = construction_zz.data()
print(construction_zz, '施工许可信息')
construction_zz['code'] = response.meta['code']
yield scrapy.Request(
url=
'https://api.maotouin.com/rest/companyInfo/addCompanyProjectBuilderLicence.htm',
body=json.dumps(construction_zz),
callback=self.project_zz,
headers={'Content-Type': 'application/json'},
method='POST',
meta={'type': '施工许可信息'})
def contract_info(self, response):
attrs = [
{
'that': '',
'attr': '//span[@id="lblPrjNum"]/text()',
'name': 'code'
},
{
'that': '',
'attr': '//span[@id="lblRecordNum"]/text()',
'name': 'recordNum'
},
{
'that': '',
'attr': '//span[@id="lblRecordNum"]/text()',
'name': 'provinceRecordNum'
},
{
'that': '',
'attr': '//span[@id="lblContractNum"]/text()',
'name': 'contractNum'
},
{
'that': '',
'attr': '//span[@id="lblcontractclassnum"]/text()',
'name': 'contractClassify'
},
{
'that': '',
'attr': '//span[@id="lblContractTypeNum"]/text()',
'name': 'contractType'
},
{
'that': '',
'attr': '//span[@id="lblContractMoney"]/text()',
'name': 'contractMoney'
},
{
'that': '',
'attr': '//span[@id="lblPrjSize"]/text()',
'name': 'prjSize'
},
{
'that': '',
'attr': '//span[@id="lblContractDate"]/text()',
'name': 'contractDate'
},
{
'that': '',
'attr': '//span[@id="lblPropietorCorpName"]/text()',
'name': 'proprietorCorpName'
},
{
'that': '',
'attr': '//span[@id="lblPropietorCorpCode"]/text()',
'name': 'proprietorCorpCode'
},
{
'that': '',
'attr': '//span[@id="lblContractorCorpName"]/text()',
'name': 'contractorCorpName'
},
{
'that': '',
'attr': '//span[@id="lblContractorCorpCode"]/text()',
'name': 'contractorCorpCode'
},
{
'that': '',
'attr': '//span[@id="lblUnionCorpName"]/text()',
'name': 'unionCorpName'
},
{
'that': '',
'attr': '//span[@id="lblUnionCorpCode"]/text()',
'name': 'unionCorpCode'
},
{
'that': '',
'attr': '//span[@id="lblCreateDate"]/text()',
'name': 'createDate'
},
]
contract_object = templates.Projects('Contract')
contract_data = contract_object.html_analysis(response, attrs)
contract_data['companyName'] = response.meta['companyName']
contract_zz = templates.Contract(**contract_data)
contract_zz = contract_zz.data()
print(contract_zz, '合同备案信息')
contract_zz['code'] = response.meta['code']
yield scrapy.Request(
url=
'https://api.maotouin.com/rest/companyInfo/addCompanyProjectContract.htm',
body=json.dumps(contract_zz),
callback=self.project_zz,
headers={'Content-Type': 'application/json'},
method='POST',
meta={'type': '合同备案信息'})
def drawing_info(self, response):
attrs = [
{
'that': '',
'attr': '//span[@id="lblPrjNum"]/text()',
'name': 'code'
},
{
'that': '',
'attr': '//span[@id="lblCensorCorpName"]/text()',
'name': 'censorCorpName'
},
{
'that': '',
'attr': '//span[@id="lblCensorCorpCode"]/text()',
'name': 'censorCorpCode'
},
{
'that': '',
'attr': '//span[@id="lblCensorNum"]/text()',
'name': 'censorNum'
},
{
'that': '',
'attr': '//span[@id="lblCensorNum"]/text()',
'name': 'provinceCensorNum'
},
{
'that': '',
'attr': '//span[@id="lblCensorEDate"]/text()',
'name': 'censorEDate'
},
{
'that': '',
'attr': '//span[@id="lblPrjSize"]/text()',
'name': 'prjSize'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[2]//td[2]/a/text()',
'name': 'surveyCorpName'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[2]/td[3]/text()',
'name': 'surveyCorpCode'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[2]/td[4]/text()',
'name': 'surveyCorpArea'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[3]/td[2]/a/text()',
'name': 'designCorpName'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[3]/td[3]/text()',
'name': 'designCorpCode'
},
{
'that': '',
'attr':
'//table[@class="rpd_basic_table"][2]/tr[3]/td[4]/text()',
'name': 'designCorpArea'
},
]
drawing_object = templates.Projects('MakeDrawing')
drawing_data = drawing_object.html_analysis(response, attrs)
if drawing_data['censorNum']:
p_tr = Selector(response=response).xpath(
'//table[@class="rpd_basic_table"][3]/tr')
p_tr = p_tr[1:-1]
engineers = []
for p in p_tr:
person = {
'companyName': '',
'tradeName': '',
'prjDuty': '',
'name': '',
'card': '',
'specialty': ''
}
companyName = p.xpath('./td[1]/text()').extract_first()
if companyName:
person['companyName'] = companyName
tradeName = p.xpath('./td[2]/text()').extract_first()
if tradeName:
person['tradeName'] = tradeName
prjDuty = p.xpath('./td[3]/text()').extract_first()
if prjDuty:
person['prjDuty'] = prjDuty
name = p.xpath('./td[4]/text()').extract_first()
if name:
person['name'] = name
card = p.xpath('./td[5]/text()').extract_first()
if card:
person['card'] = card
specialty = p.xpath('./td[6]/text()').extract_first()
if specialty:
person['specialty'] = specialty
if person['name']:
engineers.append(person)
drawing_data['engineers'] = engineers
drawing_data['companyName'] = response.meta['companyName']
drawing_zz = templates.MakeDrawing(**drawing_data)
print(drawing_zz.data(), '施工图纸审查')
drawing_xx = drawing_zz.data()
drawing_xx['code'] = response.meta['code']
yield scrapy.Request(
url=
'https://api.maotouin.com/rest/companyInfo/addCompanyProjectCensor.htm',
body=json.dumps(drawing_xx),
callback=self.project_zz,
headers={'Content-Type': 'application/json'},
method='POST',
meta={'type': '施工图纸审查'})
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'})
def project_basic(self, response):
basic = templates.Projects('Project')
attrs = [
{
'that': '',
'attr': '//td[@colspan="3"]/text()',
'name': 'name'
},
{
'that': '',
'attr': '//td[@class="name_level3 col_01_value"]/text()',
'name': 'code'
},
{
'that': 0,
'attr': '//td[@class="col_02_value"]',
'name': 'provinceCode',
'then': 'text()'
},
{
'that': 1,
'attr': '//td[@class="col_01_value"]',
'name': 'unit',
'then': 'text()'
},
{
'that': 1,
'attr': '//td[@class="col_02_value"]',
'name': 'catalog',
'then': 'text()'
},
{
'that': 2,
'attr': '//td[@class="col_01_value"]',
'name': 'unitLicenseNum',
'then': 'text()'
},
{
'that': 2,
'attr': '//td[@class="col_02_value"]',
'name': 'area',
'then': 'text()'
},
{
'that': 4,
'attr': '//td[@class="col_01_value"]',
'name': 'docuCode',
'then': 'text()'
},
{
'that': 4,
'attr': '//td[@class="col_02_value"]',
'name': 'level',
'then': 'text()'
},
{
'that': 5,
'attr': '//td[@class="col_01_value"]',
'name': 'money',
'then': 'text()'
},
{
'that': 5,
'attr': '//td[@class="col_02_value"]',
'name': 'acreage',
'then': 'text()'
},
{
'that': 6,
'attr': '//td[@class="col_01_value"]',
'name': 'trait',
'then': 'text()'
},
{
'that': 6,
'attr': '//td[@class="col_02_value"]',
'name': 'purpose',
'then': 'text()'
},
]
code = Selector(response=response).xpath(
'//td[@class="name_level3 col_01_value"]/text()').extract_first()
name = Selector(response=response).xpath(
'//td[@colspan="3"]/text()').extract_first()
code = code.split()[0]
xx = 'PRJNUM=(.*)'
basic_d = basic.html_analysis(response, attrs)
basic_d['companyName'] = response.meta['companyName']
basic = templates.Project(**basic_d)
basic_data = basic.data()
print(basic_data, '基本信息')
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_url = 'http://218.60.144.163/LNJGPublisher/handle/ProjectHandler.ashx?method=ztb&PRJNUM=%s&_=1558598717869' \
% re.findall(xx, response.url)[0]
yield scrapy.Request(url=bid_url,
callback=self.project_bid_list,
meta={
'companyName': response.meta['companyName'],
'code': code
})
drawing_url = 'http://218.60.144.163/LNJGPublisher/handle/ProjectHandler.ashx?method=sgtsc&PRJNUM=%s&_=1558598717869' % \
re.findall(xx, response.url)[0]
print(response.url, '施工图纸审查')
yield scrapy.Request(url=drawing_url,
callback=self.project_drawing_list,
meta={
'companyName': response.meta['companyName'],
'code': code
})
contract_url = 'http://218.60.144.163/LNJGPublisher/handle/ProjectHandler.ashx?method=htba&PRJNUM=%s&_=1558598717869' % \
re.findall(xx, response.url)[0]
print(contract_url, '合同备案全部')
yield scrapy.Request(url=contract_url,
callback=self.project_contract_list,
meta={
'companyName': response.meta['companyName'],
'code': code
})
construction_url = 'http://218.60.144.163/LNJGPublisher/handle/ProjectHandler.ashx?method=sgxk&PRJNUM=%s&_=1558598717869' % \
re.findall(xx, response.url)[0]
print(construction_url, '施工许可详list')
yield scrapy.Request(url=construction_url,
callback=self.project_construction_list,
meta={
'companyName': response.meta['companyName'],
'name': name
})