def get_info(self, data):
info = {}
tr_list = data.xpath(".//table[@id='table_dcdy']//tr[@name = 'dcdy']")
for i, singledata in enumerate(tr_list):
temp = {}
td_list = singledata.xpath("./td")
if len(td_list) == 0:
continue
temp["code"] = deal_html_code.remove_symbol(
td_list[1].xpath("string(.)"))
dates = deal_html_code.remove_symbol(td_list[2].xpath("string(.)"))
temp["dates"] = deal_html_code.change_date_style(dates)
temp["dept"] = deal_html_code.remove_symbol(
td_list[3].xpath("string(.)"))
temp["amount"] = deal_html_code.remove_symbol(
td_list[4].xpath("string(.)"))
temp["status"] = deal_html_code.remove_symbol(
td_list[5].xpath("string(.)"))
onclick = td_list[6].xpath("./a/@onclick")[0]
tuple = deal_html_code.match_key_content(str(onclick))
xh = tuple[0]
detail_url = self._url.format(self._pripid, xh)
person_info, goods_info = self.get_detail_info(detail_url, temp)
temp["person_info"] = person_info
temp["goods_info"] = goods_info
info[i] = temp
return info
def get_info(self, data):
info = {}
tr_list = data.xpath(".//table[@id='table_sfxz']//tr[@name = 'sfxz']")
for i, singledata in enumerate(tr_list):
temp = {}
td_list = singledata.xpath("./td")
if len(td_list) == 0:
continue
executor = deal_html_code.remove_symbol(
td_list[1].xpath("string(.)"))
temp["exceutor"] = executor
stock_amount = deal_html_code.remove_symbol(
td_list[2].xpath("string(.)"))
temp["stock_amount"] = stock_amount
court = deal_html_code.remove_symbol(td_list[3].xpath("string(.)"))
temp["court"] = court
notice_no = deal_html_code.remove_symbol(
td_list[4].xpath("string(.)"))
temp["notice_no"] = notice_no
temp["enforce_no"] = notice_no
status = deal_html_code.remove_symbol(
td_list[5].xpath("string(.)"))
temp["status"] = status
onclik = td_list[6].xpath("./a/@onclick")[0]
tuple = deal_html_code.match_key_content(str(onclik))
xh = tuple[0]
lx = tuple[1]
detail_url = self._url.format(self._pripid, lx, xh)
self.get_deatail_info(detail_url, info)
info[i] = temp
return info
def get_info(self, data):
tr_list = data.xpath(".//tr[@name = 'xzxk']")
info = {}
for i, singledata in enumerate(tr_list):
temp = {}
td_list = singledata.xpath("./td")
# number = deal_html_code.remove_symbol(td_list[0].xpath("string(.)"))
temp["name"] = ''
temp["code"] = deal_html_code.remove_symbol(td_list[1].xpath("string(.)"))
temp["filename"] = deal_html_code.remove_symbol(td_list[2].xpath("string(.)"))
start_date = deal_html_code.remove_symbol(td_list[3].xpath("string(.)"))
temp["start_date"] = deal_html_code.change_chinese_date(start_date)
end_date = deal_html_code.remove_symbol(td_list[4].xpath("string(.)"))
temp["end_date"] = deal_html_code.change_chinese_date(end_date)
temp["gov_dept"] = deal_html_code.remove_symbol(td_list[5].xpath("string(.)"))
temp["content"] = deal_html_code.remove_symbol(td_list[6].xpath("string(.)"))
temp["status"] = deal_html_code.remove_symbol(td_list[7].xpath("string(.)"))
onclick = td_list[8].xpath("./a/@onclick")
if len(onclick) == 0:
logging.info("该条信息无详情信息！")
else:
onclick = onclick[0]
tuple = deal_html_code.match_key_content(str(onclick))
pripid = tuple[0]
xh = tuple[1]
lx = tuple[2]
detail_url = self._url.format(pripid, xh, lx)
self.get_detail_info(detail_url)
info[i] = temp
return info
def deal_single_page(self, info, data, start):
sbxx_detail = data.xpath("//li[@name = 'sbxx']//a/@onclick")
# enumerate(sbxx_date,start),start 代表的是i 的开始位置，enumerate详细用法找百度
# 是因为商标信息是需要进行翻页,保存信息的做法是用字典的（key,value）键值对,编号作为键值（key）,对应每条信息(value)
# 一是方便查找,二是便于存储,根据键值的唯一性,每一条信息都要有一个唯一的键值
# 如果页面中没有序号，就需要自己自定义每条信息的序号,页面中有序号的可以用页面中的序号作为键值,没有则可以采用这种做法
for i, value in enumerate(sbxx_detail, start):
tuple = deal_html_code.match_key_content(str(value))
reg_num = tuple[0]
picname = tuple[1]
detail = self._detail_url.format(reg_num, picname)
temp = self.get_single_info(detail)
temp["ia_img"] = host + picname
info[i] = temp
def deal_single_info(self, td_list, i, info):
json_data = {
"name": "",
"types": "",
"license_code": "",
"license_type": "",
"true_amount": "",
"reg_amount": "",
"ra_ways": "",
"ra_date": "0000-00-00",
"ta_ways": "",
"ta_date": "0000-00-00"
}
# 如果是投资人，即包含两个字段
if len(td_list) <= 2:
name = deal_html_code.remove_symbol(td_list[1].xpath("string(.)"))
types = deal_html_code.remove_symbol(td_list[2].xpath("string(.)"))
json_data["name"] = name
json_data["types"] = types
json_data["license_code"] = ''
json_data["license_type"] = ''
else:
# number = td_list[0].xpath("string(.)")
name = deal_html_code.remove_symbol(td_list[1].xpath("string(.)"))
json_data["name"] = name
types = deal_html_code.remove_symbol(td_list[2].xpath("string(.)"))
json_data["types"] = types
license_type = deal_html_code.remove_symbol(
td_list[3].xpath("string(.)"))
json_data["license_type"] = license_type
license_code = deal_html_code.remove_symbol(
td_list[3].xpath("string(.)"))
json_data["license_code"] = license_code
detail = td_list[4].xpath("./a")
# 如果长度为0证明是个假的详情，~-~即没有链接
if len(detail) == 0:
logging.info("该条信息无详情！")
else:
showRyxx = td_list[4].xpath("./a/@onclick")[0]
key = deal_html_code.match_key_content(str(showRyxx))
xh = key[0]
pripid = key[1]
isck = key[2]
detail_url = self.url.format(xh, pripid, isck)
self.deal_detail_info(detail_url)
info[i] = json_data
def get_info(self):
url = self._url.format(self._pripid)
headers = config.headers
result, status_code = Send_Request().send_requests(url, headers)
info = {}
if status_code == 200:
data = etree.HTML(result,
parser=etree.HTMLParser(encoding='utf-8'))
tr_list = data.xpath(
"//table[@id = 'table_xzcf']//tr[@name = 'xzcf']")
for i, singledata in enumerate(tr_list):
temp = {}
td_list = singledata.xpath("./td")
temp["number"] = deal_html_code.remove_symbol(
td_list[1].xpath("string(.)"))
temp["types"] = deal_html_code.remove_symbol(
td_list[2].xpath("string(.)"))
temp["content"] = deal_html_code.remove_symbol(
td_list[3].xpath("string(.)"))
temp["gov_dept"] = deal_html_code.remove_symbol(
td_list[4].xpath("string(.)"))
date = deal_html_code.remove_symbol(
td_list[5].xpath("string(.)"))
temp["date"] = deal_html_code.change_chinese_date(date)
pub_date = deal_html_code.remove_symbol(
td_list[6].xpath("string(.)"))
temp["pub_date"] = deal_html_code.change_chinese_date(pub_date)
if len(tr_list) > 7:
onclick = tr_list[7].xpath("./a[@onclick]")
if len(onclick) == 0:
tuple = deal_html_code.match_key_content(onclick[0])
pripid = tuple[0]
xh = tuple[1]
pdfurl = detail_url.format(pripid, xh)
else:
pdfurl = ''
temp["pdfutl"] = pdfurl
temp["name"] = ''
info[i] = temp
return info