def get_detail_info(self, detail_url, info):
dict = {
u"种类": "cates",
u"范围": "ranges",
u"期限": "period",
u"备注": "remark",
}
headers = config.headers
result, status_code = Send_Request().send_requests(detail_url, headers)
if status_code == 200:
data = etree.xpath(result,
parser=etree.HTMLParser(encoding='utf-8'))
string = u"被担保债权概况信息"
table = data.xpath("//*[contains(.,'%s')]" % string)[0]
for key, value in dict.iteritems():
info[value] = deal_html_code.get_match_info(key, table)
string = u"抵押权人概况信息"
person_info = data.xpath("//*[contains(.,'%s')]" % string)[0]
string = u"抵押权物概况信息"
goods_info = data.xpath("//*[contains(.,'%s')]" % string)[0]
else:
info["cates"] = ''
info["ranges"] = ''
info["period"] = ''
info["remark"] = ''
person_info = {}
goods_info = {}
return person_info, goods_info
def get_info(self, data):
info = {}
for key, value in config.report_lab_dict.iteritems():
info[value] = deal_html_code.get_match_info(key, data)
# 这两种情况的采集没有太大意义就不再入库
if info["birth_num"] == '' or info["birth_num"] == '人':
info = {}
else:
# 判定欠费金额，实际缴费金额，缴费基数 是否公示
# 判定标准选取生育的各个对应信息进行标准，
# 即认为如果生育、医疗、养老、失业中有一个欠费，实缴，基数是不公示的
# 则其他的也是不公示的
if info["birth_owe"] > 0:
if_owe = 0
else:
if_owe = 1
info["if_owe"] = if_owe
if info["birth_base"] == 0:
if_basenum = 0
else:
if_basenum = 1
info["if_basenum"] = if_basenum
if info["birth"] == 0:
if_periodamount = 0
else:
if_periodamount = 1
info["if_periodamount"] = if_periodamount
for key, value in info.iteritems():
print key, value
if "if" in key:
continue
info[key] = deal_html_code.match_float(value)
return info
def get_info(self, data):
info = {}
for key, value in dict.iteritems():
info[value] = deal_html_code.get_match_info(key, data)
# 调用juege_if_public判断是否公示，判断是否公示是根据所取到的该部分信息中是否含有元
# 进行判断的，可能总结不够全面，以后见到不含元的再更改函数
info["if_asset"] = self.judge_if_public(info["asset"])
# 判断完是否公示后调用match_float取里面的数字
info["asset"] = deal_html_code.match_float(info["asset"])
info["if_benifit"] = self.judge_if_public(info["benifit"])
info["benifit"] = deal_html_code.match_float(info["benifit"])
info["if_main"] = self.judge_if_public(info["main_income"])
info["main_income"] = deal_html_code.match_float(info["main_income"])
info["if_net"] = self.judge_if_public(info["net_income"])
info["net_income"] = deal_html_code.match_float(info["net_income"])
info["if_tax"] = self.judge_if_public(info["tax"])
info["tax"] = deal_html_code.match_float(info["tax"])
info["if_loan"] = self.judge_if_public(info["loan"])
info["loan"] = deal_html_code.match_float(info["loan"])
info["if_subsidy"] = self.judge_if_public(info["subsidy"])
info["subsidy"] = deal_html_code.match_float(info["subsidy"])
info["if_income"] = deal_html_code.match_float(info["income"])
info["income"] = self.judge_if_public(info["income"])
info["if_profit"] = deal_html_code.match_float(info["profit"])
info["profit"] = self.judge_if_public(info["profit"])
info["if_debt"] = deal_html_code.match_float(info["debt"])
info["debt"] = self.judge_if_public(info["debt"])
return info
def get_info(self, data):
info = {}
for key, value in config.report_basic_dict.iteritems():
info[value] = deal_html_code.get_match_info(key, data)
if u"不公示" in info["employee"] or info["employee"] == '':
info["if_empnum"] = 0
else:
info["if_empnum"] = 1
womennum = info["womennum"]
if u"不公示" in womennum or womennum == '':
info["if_womennum"] = 0
else:
info["if_womennum"] = 1
holding = info["holding"]
if u"不公示" in holding or holding == '':
if_holding = 0
info["if_holding"] = if_holding
else:
info["if_holding"] = 1
info["if_invest"] = self.transform_ifornot(info["if_invest"])
info["if_fwarnnt"] = self.transform_ifornot(info["if_fwarnnt"])
info["if_website"] = self.transform_ifornot(info["if_website"])
info["if_sharetrans"] = self.transform_ifornot(info["if_sharetrans"])
return info
def get_info(self, data):
info = {}
string = u'清算组负责人'
leader = deal_html_code.get_match_info(string, data)
list = leader.split('、')
for i, value in enumerate(list):
temp = {}
temp["person_name"] = value
temp["position"] = string
info[i] = temp
string = u"清算组成员"
member = deal_html_code.get_match_info(string, data)
list = member.split('、')
for j, value in enumerate(list, i + 1):
temp = {}
temp["person_name"] = value
temp["position"] = string
info[j] = temp
return info
def get_deatail_info(self, detail_url, info):
dict = {
u"执行事项": "items",
u"裁定书文号": "rule_no",
u"证照种类": "cert_cate",
u"证照号码": "cert_code",
u"冻结期限自": "start_date",
u"冻结期限至": "end_date",
u"冻结期限": "period",
u"公示日期": "pub_date"
}
headers = config.headers
result, status_code = Send_Request().send_requests(detail_url, headers)
if status_code == 200:
data = result.xpath(result,
parser=etree.HTMLParser(encoding='utf-8'))
for key, value in dict:
content = deal_html_code.get_match_info(key, data)
info[value] = content
else:
logging.info("获取司法协助详情信息失败！")
def get_single_info(self, detail_url):
dict = {
u"注册号": "ia_zch",
u"公告日期": "ia_zcdate",
u"类别": "ia_flh",
u"公告期号": "ia_zcgg",
u"起止日期": "ia_zyqqx",
u'服务项目': "ia_servicelist"
}
result, status_code = Send_Request().send_requests(detail_url, config.headers)
temp = {}
if status_code == 200:
data = etree.HTML(result, parser=etree.HTMLParser(encoding='utf-8'))
for key, value in dict.iteritems():
temp[value] = deal_html_code.get_match_info(key, data)
else:
temp["ia_zch"] = ''
temp["ia_zcdate"] = ''
temp["ia_flh"] = ''
temp["ia_zcgg"] = ''
temp["ia_zyqqx"] = ''
temp["ia_servicelist"] = ''
return temp