def get_index(code):
province = deal_html_code.judge_province(code)
first_url = config.url_list[province].format(code)
result,status_code = Send_Request().send_requests(first_url)
data = None
if status_code ==200:
info = json.loads(result)["info"][0]
uuid = info["uuid"]
second_url = config.detail_list[province].format(uuid)
data = Send_Request().send_requests(second_url)[0]
return data
def name(url):
headers = config.headers_detail
content, status_code = Send_Request().send_request(url, headers)
if status_code == 200:
flag = 1
result = etree.xpath(content,
parser=etree.HTMLParser(encoding='utf-8'))
dl = result.xpath("//div[@class = viewBox']//dl")[0]
info = {}
if "企业名称" in content:
datallist = etree.tostring(dl).split(
'<dd style="border-bottom:1px solid #AE0000;padding-bottom:10px;">'
)
datallist.remove(datallist[-1])
pattern = re.compile(u".*共(.*?)页.*")
number = re.findall(pattern, content)
if len(number) == 1:
totalpage = int(number[0])
else:
totalpage = 0
if int(totalpage) == 1:
j = 0
deal_single_info(datallist, info, j)
else:
j = 0
deal_single_info(datallist, info, j)
entid = deal_html_code.match_entid(url)
cid = deal_html_code.match_cid(url)
href = out_invest_url.format(entid, cid)
for k in xrange(2, totalpage + 1):
content, status_code = Send_Request().send_request(href)
if status_code == 200:
start = k * 5 + 1
result = etree.HTML(
content, parser=etree.HTMLParser(encoding='utf-8'))
dl = result.xpath("//div[@class='viewBox']/dl")[0]
datalist = etree.tostring(dl).split(
'<dd style="border-bottom:1px solid #AE0000;padding-bottom:10px;">'
)
if len(datalist) > 0:
datalist.remove(datalist[-1])
deal_single_info(datalist, info, start)
else:
pass
else:
flag = 100000004
else:
flag = 100000004
if flag == 1:
info = deal_html_code.remove_repeat(info)
return info, flag
def name(url):
headers = config.headers_detail
content, status_code = Send_Request().send_request(url, headers)
# print content
info = {}
if status_code == 200:
flag = 1
result = etree.HTML(content, parser=etree.HTMLParser(encoding='utf-8'))
dl = result.xpath("//div[@class='viewBox']//dl")[0]
datalist = etree.tostring(dl).split(
'<dt style="color:#333;margin-bottom:10px;"/>')
datalist.remove(datalist[0])
if len(datalist) > 0:
pattern = re.compile(".*共(.*?)页.*")
number = re.findall(pattern, content)
if len(number) == 1:
totalpage = int(number[0])
else:
totalpage = 0
if int(totalpage) == 1:
j = 0
deal_single_info(datalist, info, j)
else:
j = 0
deal_single_info(datalist, info, j)
entid = deal_html_code.match_entid(url)
cid = deal_html_code.match_cid(url)
for k in xrange(2, totalpage + 1):
href = share_url.format(entid, cid, k)
content, status_code = Send_Request().send_request(
href, headers)
if status_code == 200:
start = k * 5 + 1
result = etree.HTML(
content, parser=etree.HTMLParser(encoding='utf-8'))
dl = result.xpath("//div[@class='viewBox']//dl")[0]
datalist = etree.tostring(dl).split(
'<dt style="color:#333;margin-bottom:10px;"/>')
datalist.remove(datalist[0])
if len(datalist) > 0:
deal_single_info(datalist, info, start)
else:
pass
else:
logging.info("无股东及出资信息")
else:
flag = 100000004
info = deal_html_code.remove_repeat(info)
return info, flag
def get_info(self):
headers = config.headers
url = self._url.format(self._pripid)
result, status_code = Send_Request().send_requests(url, headers)
info = {}
if status_code == 200:
data = etree.xpath(result,
parser=etree.HTMLParser(encoding='utf-8'))
tr_list = data.xpath(
"//table[id= 'table_jyyc']//tr[@name = 'jyyc']")
for i, singledata in enumerate(tr_list):
temp = {}
td_list = singledata.xpath("./td")
temp["types"] = '经营异常'
temp["in_reason"] = deal_html_code.remove_symbol(
td_list[1].xpath("string(.)"))
in_date = deal_html_code.remove_symbol(
td_list[2].xpath("string(.)"))
temp["in_date"] = deal_html_code.change_chinese_date(in_date)
temp["out_reason"] = deal_html_code.remove_symbol(
td_list[4].xpath("string(.)"))
out_date = deal_html_code.remove_symbol(
td_list[5].xpath("string(.)"))
temp["out_date"] = deal_html_code.change_chinese_date(out_date)
temp["gov_dept"] = deal_html_code.remove_symbol(
td_list[6].xpath("string(.)"))
temp["out_gov"] = deal_html_code.remove_symbol(
td_list[7].xpath("string(.)"))
info[i] = temp
return info
def get_year_href(self):
information = {}
result, status_code = Send_Request().send_requests(self.url)
# print result
pattern = re.compile('.*/index/invalidLink.*|.*页面不存在.*')
fail = re.findall(pattern, result)
flag = 1
if status_code == 200 and len(fail) == 0:
pattern = re.compile(r'\[(.*?)\]')
result = re.findall(pattern, result)[0]
pattern = re.compile(u'{.*?}')
result = re.findall(pattern, result)
for i in xrange(len(result)):
singledata = json.loads(result[i])
anCheId = singledata["anCheId"]
anCheYear = singledata["anCheYear"]
entType = singledata["entType"]
annRepFrom = singledata["annRepFrom"]
province = anCheId[15:17]
province = config.province[province]
information[i] = [
anCheId, anCheYear, province, entType, annRepFrom
]
else:
flag = 100000004
logging.info("report url fail")
return information, flag
def name(self, url):
info = {}
content, status_code = Send_Request().send_request(url)
if status_code == 200:
flag = 1
result = etree.HTML(content, parser=etree.HTMLParser(encoding='utf-8'))
dl = result.xpath("//div[@class='viewBox']//dl")[0]
dlcontent = etree.tostring(dl)
string = '<dd style="border-top:1px dashed #ccc;">'
dllist = dlcontent.split(string)
dllist.remove(dllist[-1])
for i, single in enumerate(dllist):
single = etree.HTML(single, parser=etree.HTMLParser(encoding='utf-8'))
# string = u"主体名称"
# name = self.deal_dd_content(string,single)
string = u"抽查检查日期"
check_date = self.deal_dd_content(string, single)
string = u"检查实施机关"
gov_dept = self.deal_dd_content(string, single)
string = u"抽查检查结果"
result = self.deal_dd_content(string, single)
if u"抽查信息" in url:
types = "抽查"
elif u"检查信息" in url:
types = "检查"
else:
pass
info[i] = [check_date, gov_dept, result, types]
else:
flag = 100000004
# print info,flag
return info, flag
def name(self, url):
info = {}
content, status_code = Send_Request().send_request(url)
if status_code == 200:
flag = 1
result = etree.HTML(content,
parser=etree.HTMLParser(encoding="utf-8"))
dlinfo = result.xpath("//div[@class ='viewBox']//dl")[0]
dl = etree.tostring(dlinfo).split("<br/>")
# 将最后一项的无用数据移除
dl.remove(dl[-1])
for i, single in enumerate(dl):
single = etree.HTML(single,
parser=etree.HTMLParser(encoding="utf-8"))
name = deal_html_code.remove_symbol(
single.xpath(".//dt")[0].xpath("string(.)"))
templist = single.xpath('.//dd')
types = deal_html_code.remove_symbol(
templist[0].xpath("string(.)"))
license_type = deal_html_code.remove_symbol(
templist[1].xpath('string(.)'))
license_code = deal_html_code.remove_symbol(
templist[2].xpath('string(.)'))
info[i] = [name, types, license_type, license_code]
else:
flag = 100000004
return info, flag
def update_all_info(url, gs_basic_id):
result, status_code = Send_Request().send_requests(url)
pattern = re.compile(".*返回首页.*")
fail = re.findall(pattern, result)
if status_code == 200 and len(fail) == 0:
urllist,flag = QGGS_basic.main(url,gs_basic_id)
if flag <100000001:
QGGS_black.main(gs_basic_id, urllist["black"])
QGGS_branch.main(gs_basic_id, urllist["branch"])
QGGS_brand.main(gs_basic_id, urllist["brand"])
QGGS_change.main(gs_basic_id, urllist["change"])
QGGS_change.main(gs_basic_id, urllist["change2"])
QGGS_check.main(gs_basic_id, urllist["check"])
QGGS_clear.main(gs_basic_id, urllist["clear"])
QGGS_except.main(gs_basic_id, urllist["except"])
QGGS_freeze.main(gs_basic_id, urllist["freeze"])
QGGS_mort.main(gs_basic_id, urllist["mort"])
QGGS_permit.main(gs_basic_id, urllist["permit"])
QGGS_permit2.main(gs_basic_id, urllist["permit2"])
QGGS_person.main(gs_basic_id, urllist["person"])
QGGS_punish.main(gs_basic_id, urllist["punish"])
QGGS_punish2.main(gs_basic_id, urllist["punish2"])
QGGS_shareholder.main(gs_basic_id, urllist["shareholder"])
QGGS_stock.main(gs_basic_id, urllist["stock"])
QGGS_report.main(gs_basic_id, urllist["report"])
else:
logging.error('基本信息页访问失败！')
else:
logging.error('网页打开过程出错！')
def name(url):
result, status_code = Send_Request().send_requests(url)
info = {}
if status_code == 200:
data = json.loads(result)["data"]
if len(data) > 0:
data = data[0]
info = {}
uuid = data["soseId"]
if_owe = int(data["unpaidSocialInsDis"])
if_basenum = int(data["totalWagesDis"])
if_periodamount = int(data["totalPaymentDis"])
birth_owe = data["unpaidSocialInsSo510"]
birth_num = data["so510"]
birth = data["totalPaymentSo510"]
birth_base = data["totalWagesSo510"]
old_num = data["so110"]
old_owe = data["unpaidSocialInsSo110"]
old = data["totalPaymentSo110"]
old_base = data["totalWagesSo110"]
unemploy = data["totalPaymentSo210"]
unemploy_base = data["totalWagesSo210"]
unemploy_owe = data["unpaidSocialInsSo210"]
unemploy_num = data["so210"]
medical = data["totalPaymentSo310"]
medical_base = data["totalWagesSo310"]
medical_owe = data["unpaidSocialInsSo310"]
medical_num = data["so310"]
injury = data["totalPaymentSo410"]
injury_owe = data["unpaidSocialInsSo410"]
injury_num = data["so410"]
info[0] = [uuid,if_owe,if_basenum,if_periodamount,birth_owe,birth_num,birth,birth_base,old_num,old_owe,old,old_base,\
unemploy,unemploy_base,unemploy_owe,unemploy_num,medical,medical_base,medical_owe,medical_num,injury,injury_owe,injury_num]
return info
def name(url):
headers = config.headers_detail
content, status_code = Send_Request().send_request(url, headers)
info = {}
if status_code == 200:
flag = 1
result = etree.HTML(content, parser=etree.HTMLParser(encoding='utf-8'))
dl = result.path("//div[@class= 'viewBox']/dl")[0]
datallist = etree.tostring(dl).split(
'<dd style="border-bottom:1px solid #AE0000;padding-bottom:10px;">'
)
datallist.remove(datallist[-1])
for i, single in enumerate(datallist):
single = etree.xpath(content,
parser=etree.HTMLParser(encoding='utf-8'))
string = u"股东"
name = deal_dd_content(string, single)
string = u"变更前"
percent_pre = deal_dd_content(string, single)
string = u"变更后"
percent_after = deal_dd_content(string, single)
string = u"变更日期"
dates = deal_dd_content(string, single)
info[i] = [name, percent_pre, percent_after, dates]
else:
flag = 100000004
if flag == 1:
deal_html_code.remove_repeat(info)
return info, flag
def name(self, url):
info = {}
content, status_code = Send_Request().send_request(url)
if status_code == 200:
flag = 1
result = etree.HTML(content,
parser=etree.HTMLParser(encoding='utf-8'))
dl = result.xpath('//div[@class= "viewBox"]//dl')[0]
datalist = etree.tostring(dl).replace("<dl>", '').replace(
"</dl>", '').split('<dd style="border-top:1px dashed #ccc;">')
datalist.remove(datalist[-1])
for i, single in enumerate(datalist):
single = etree.HTML(single,
parser=etree.HTMLParser(encoding='utf-8'))
string = u'商标名称'
ia_name = self.deal_dd_content(string, single)
string = u'商标注册号'
ia_zch = self.deal_dd_content(string, single)
string = u'认定类别'
ia_type = self.deal_dd_content(string, single)
info[i] = [ia_name, ia_zch, ia_type]
# print info
else:
flag = 100000004
return info, flag
def get_info(self):
info = {}
name = urllib.quote(self._name)
url = self._url.format(name, 1)
result, status_code = Send_Request().send_requests(url, config.headers)
if status_code == 200:
start = 0
data = etree.HTML(result, parser=etree.HTMLParser(encoding='utf-8'))
self.deal_single_page(info, data, start)
totalpage = data.xpath("//input[@id = 'totalPage_sbxx']/@value")[0]
for i in xrange(2, int(totalpage) + 1):
start = (i - 1) * 6 # 定义开始位置
url = self._url.format(name, i)
result, start_code = Send_Request().send_requests(url, config.headers)
data = etree.HTML(result, parser=etree.HTMLParser(encoding='utf-8'))
self.deal_single_page(info, data, start)
def name(self, url):
info = {}
content, status_code = Send_Request().send_request(url)
if status_code == 200:
flag = 1
result = etree.HTML(content, parser=etree.HTMLParser(encoding="utf-8"))
dl = result.xpath("//div[@class = 'viewBox']//dl")[0]
dlcontent = etree.tostring(dl)
string = '<dd style="border-top:1px dashed #ccc;">'
dllist = dlcontent.split(string)
dllist.remove(dllist[-1])
for i, single in enumerate(dllist):
single = etree.HTML(single, parser=etree.HTMLParser(encoding="utf-8"))
string = u"主体名称"
name = self.deal_dd_content(string, single)
string = u"行政处罚决定书文号"
number = self.deal_dd_content(string, single)
string = u"处罚事由"
types = self.deal_dd_content(string, single)
string = u"处罚依据"
basis = self.deal_dd_content(string, single)
string = u"处罚结果"
result = self.deal_dd_content(string, single)
# print result
string = u"处罚决定日期"
date = self.deal_dd_content(string, single)
string = u"处罚机构"
gov_dept = self.deal_dd_content(string, single)
info[i] = [name, number, types, basis, result, date, gov_dept]
else:
flag = 100000004
return info, flag
def name(self, url):
info = {}
headers = config.headers_detail
content, status_code = Send_Request().send_request(url, headers)
if status_code == 200:
flag = 1
result = etree.HTML(content,
parser=etree.HTMLParser(encoding='utf-8'))
# total = result.xpath("//table[@id='tableIdStyle']//div/text()")[0]
# pattern = re.compile(u".*记录总数(.*?)条.*")
# number = re.findall(pattern,total)
# if len(number)==1:
# temp =int(number[0])
trlist = result.xpath("//table[@id = 'tableIdStyle']//tr")
for i, single in enumerate(trlist):
tdlist = single.xpath("./td")
if len(tdlist) == 0 or len(tdlist) < 4:
pass
else:
name = deal_html_code.remove_symbol(
tdlist[1].xpath("string(.)"))
code = deal_html_code.remove_symbol(
tdlist[2].xpath("string(.)"))
gov_dept = deal_html_code.remove_symbol(
tdlist[5].xpath("string(.)"))
info[i] = [name, code, gov_dept]
else:
flag = 100000004
return info, flag
def get_report_branch_href(self, url, cookies):
branch_list = {}
content, status_code = Send_Request().send_request3(
url, cookies, headers)
if status_code == 200:
flag = 1
result = etree.HTML(content,
parser=etree.HTMLParser(encoding='utf-8'))
div_list = result.xpath("//div[@class='categ_info_title_wz']")
for i, single in enumerate(div_list):
href = config.host + single.xpath('./a/@href')[0]
text = single.xpath('./a/text()')[0]
if '企业基本信息' in text:
branch_list["basic"] = str(href)
elif "股东及出资信息" in text:
branch_list["share"] = str(href)
elif "对外投资信息" in text:
branch_list["invest"] = str(href)
elif "企业资产状况信息" in text:
branch_list["run"] = str(href)
elif "生产经营情况" in text:
branch_list["run"] = str(href)
elif "担保信息" in text:
branch_list["assure"] = str(href)
elif "股权变更信息" in text:
branch_list["schange"] = str(href)
elif "网站或网店信息" in text:
branch_list["web"] = str(href)
else:
flag = 100000004
return branch_list, flag
def name(self, url):
headers = config.headers_detail
content, status_code = Send_Request().send_request(url, headers)
info = {}
if status_code == 200:
# print content
flag = 1
result = etree.HTML(content, parser=etree.HTMLParser(encoding='utf-8'))
dl = result.xpath("//div[@class='viewBox']//dl")[0]
datalsit = deal_html_code.remove_space(etree.tostring(dl)).split('<br/>')
datalsit.remove(datalsit[-1])
for i, single in enumerate(datalsit):
single = etree.HTML(single, parser=etree.HTMLParser(encoding='utf-8'))
name = single.xpath("//dt[@style='color:#333;margin-bottom:10px;']/text()")
string = u"投资人类型"
types = self.deal_dd_content(string, single)
string = u"认缴出资金额"
reg_amount = self.deal_dd_content(string, single)
string = u"认缴出资方式"
ra_ways = self.deal_dd_content(string, single)
string = u"认缴出资时间"
ra_date = self.deal_dd_content(string, single)
string = u"实缴出资金额"
true_amount = self.deal_dd_content(string, single)
string = u"实缴出资方式"
ta_ways = self.deal_dd_content(string, single)
string = u"实缴出资时间"
ta_date = self.deal_dd_content(string, single)
info[i] = [name, types, reg_amount, ra_ways, ra_date, true_amount, ta_ways, ta_date]
else:
flag = 100000004
return info, flag
def name(self, url):
info = {}
content, status_code = Send_Request().send_request(url)
if status_code == 200:
flag = 1
result = etree.HTML(content, parser=etree.HTMLParser(encoding='utf-8'))
dl = result.xpath("//div[@class='viewBox']//dl")[0]
string = u'执行法院'
court = self.deal_dd_content(string, dl)
string = u'被执行人'
executor = self.deal_dd_content(string, dl)
string = u'执行文书文号'
rule_no = self.deal_dd_content(string, dl)
string = u'执行事项'
items = self.deal_dd_content(string, dl)
string = u'冻结开始日期'
start_date = self.deal_dd_content(string, dl)
string = u'冻结结束日期'
end_date = self.deal_dd_content(string, dl)
string = u'公示日期'
pub_date = self.deal_dd_content(string, dl)
string = u"被执行人持有股权"
stock = self.deal_dd_content(string, dl)
string = u'被执行人证件种类'
cert_cate = self.deal_dd_content(string, dl)
string = u'被执行人证件号码'
cert_code = self.deal_dd_content(string, dl)
string = u"解冻日期"
end_freeze = self.deal_dd_content(string, dl)
info[0] = [court, executor, rule_no, items, start_date, end_date, pub_date, stock, cert_cate, cert_code,
end_freeze]
else:
flag = 100000004
# print info,flag
return info, flag
def deal_detail_content(detail_url):
# print detail_url
detail_code, status_code = Send_Request().send_requests(detail_url)
if status_code == 200:
detail_code = json.loads(detail_code)["data"]
if len(detail_code[1]) != 0:
content1 = detail_code[1][0]
elif len(detail_code[0]) != 0:
content1 = detail_code[0][0]
if len(content1) != 0:
if "conDate" in content1.keys():
ra_date = content1["conDate"]
ra_date = change_date_style(ra_date)
ta_date = ra_date
else:
ta_date = None
ra_date = None
if "conForm_CN" in content1.keys():
ra_ways = content1["conForm_CN"]
ta_ways = ra_ways
else:
ta_ways = None
ra_ways = None
if "subConAm" in content1.keys():
reg_amount = content1["subConAm"]
else:
reg_amount = None
if "acConAm" in content1.keys():
true_amount = content1["acConAm"]
else:
true_amount = None
return ra_date, ra_ways, true_amount, reg_amount, ta_ways, ta_date
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):
url = self._url.format(self._pripid)
headers = config.headers
result, status_code = Send_Request().send_requests(url,
headers=headers)
data = etree.HTML(result, parser=etree.HTMLParser(encoding='utf-8'))
tr_list = data.xpath("//table[@id ='table_xzxk']//tr[name = 'xzxk']")
info = {}
for i, singledata in enumerate(tr_list):
td_list = singledata.xpath("./td")
if len(td_list) == 0:
continue
temp = {}
# 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[6].xpath("string(.)"))
temp["content"] = deal_html_code.remove_symbol(
td_list[5].xpath("string(.)"))
info[i] = temp
return info
def get_list(string):
info = {}
flag = 0
try:
headers = config.headers_index
content, status_code = Send_Request().send_request(
config.index_url, headers)
if status_code == 200:
result = etree.HTML(content,
parser=etree.HTMLParser(encoding='utf-8'))
id = result.xpath('//span[@class = "shouButton"]/@onclick')[0]
pattern = re.compile(".*QueryIndex\('','(.*?)'\).*")
match_id = re.findall(pattern, id)[0]
url = config.list_url.format(match_id)
#随机生成UA
a = random.randrange(1, 1001) # 1-1000中生成随机数
headers = config.headers
params = config.list_parmas.format(string)
theline = linecache.getline(r'user-agent.txt', a)
theline = theline.replace("\n", '')
headers["User-Agent"] = theline
result = requests.post(url, params, headers=headers)
status_code = result.status_code
s = chardet.detect(result.content)["encoding"]
if status_code == 200 and s == 'utf-8':
pattern = re.compile(u".*无查询结果.*|.*访问频繁.*|.*访问异常.*")
match = re.findall(pattern, result.content)
if len(match) == 0:
content = etree.HTML(
result.content,
parser=etree.HTMLParser(encoding='utf-8'))
list = content.xpath("//li")
for i, single in enumerate(list):
item = single.xpath(".//a/@href")[0]
url = config.host + item
info[i] = url
flag = 1
else:
flag = 100000003
else:
flag = 100000004
else:
flag = 10000004
except Exception, e:
logging.error("search error:%s" % e)
flag = 100000004
def get_info(self,url, url_pattern):
result, status_code = Send_Request().send_requests(url)
data = json.loads(result)["data"]
if status_code == 200:
if len(data) == 0:
data = None
logging.info('暂无 %s' % url_pattern)
return data
def get_detail(info):
detaillist = {}
for key in info.keys():
url = info[key]
content, status_code = Send_Request().send_request(url)
if status_code == 200:
detaillist[key] = deal_single_info(content)
time.sleep(0.5)
return detaillist
def name(url):
headers = config.headers_detail
content, status_code = Send_Request().send_request(url, headers)
if status_code == 200:
flag = 1
result = etree.HTML(content, parser=etree.HTMLParser(encoding='utf-8'))
dl = result.xpath("//div[@class='viewBox']/dl")[0]
info = {}
if "企业名称" in content:
pattern = re.compile(".*共(.*?)页.*")
number = re.findall(pattern, content)
if len(number) == 1:
totalpage = int(number[0])
else:
totalpage = 0
if int(totalpage) == 1:
j = 0
deal_single_info(dl, info, j)
else:
j = 0
deal_single_info(dl, info, j)
entid = deal_html_code.match_entid(url)
cid = deal_html_code.match_cid(url)
for k in xrange(2, totalpage + 1):
href = out_invest_url.format(entid, cid, k)
content, status_code = Send_Request().send_request(
href, headers)
if status_code == 200:
start = (k - 1) * 5 + 1
result = etree.HTML(
content, parser=etree.HTMLParser(encoding='utf-8'))
dl = result.xpath("//div[@class='viewBox']/dl")[0]
deal_single_info(dl, info, start)
else:
pass
else:
flag = 100000004
else:
flag = 100000004
if flag == 1:
info = deal_html_code.remove_repeat(info)
return info, flag
def get_detail(info):
detaillist = {}
for key in info.keys():
url = info[key]
# print url
headers = config.headers_detail
content, status_code = Send_Request().send_request(url, headers)
# print status_code
if status_code == 200:
detaillist[key] = deal_single_info(content)
time.sleep(0.5)
return detaillist
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_url_list(url):
result, status_code = Send_Request().send_requests(url)
pattern = re.compile(".*返回首页.*|.*'/index/invalidLink'.*")
fail = re.findall(pattern, result)
if status_code == 200 and len(fail) == 0:
information, flag = get_basic_info(result, status_code)
url = get_singleinfo_url(result)
else:
information = None
flag = 100000004
url = {}
return information,flag,url
def get_html_data(url, print_url):
headers = config.headers
info = {}
result, status_code = Send_Request().send_requests(url, headers)
if status_code == 200:
flag = 1
data = etree.HTML(result, parser=etree.HTMLParser(encoding='utf-8'))
for key, value in dict.iteritems():
info[value] = deal_html_code.match_info(key, data)
if info["shareholder1"] != '':
info["shareholder"] = info["shareholder1"]
elif info["shareholder2"] != '':
info["shareholder"] = info["shareholder2"]
elif info["shareholder3"] != '':
info["shareholder"] = info["shareholder3"]
# 最后删除不要的键值，以防下面循环去键值对应信息时出错
del info["shareholder1"]
del info["shareholder2"]
del info["shareholder3"]
else:
flag = 100000004
print '获取基本信息失败！'
print_info, status_code = Send_Request().send_requests(print_url, headers)
if status_code == 200:
print_data = etree.HTML(print_info,
parser=etree.HTMLParser(encoding='utf-8'))
string = u'人员信息'
info["person"] = deal_html_code.match_info(string, print_data)
if info["person"] == '':
string = u'成员信息'
info["person"] = deal_html_code.match_info(string, print_data)
string = u'分支机构'
info["branch"] = deal_html_code.match_info(string, print_data)
# 将整个打印页的内容先赋值给info["report1],传递给Report类，report类根据年份查找对应年份的信息
info["report1"] = print_data
return info, flag
def get_preport_url(self, anCheId):
info = {}
url = host + '/corp-query-entprise-info-vAnnualPbReportBaseInfoForJs-%s.html' % anCheId
result, status_code = Send_Request().send_requests(url)
if status_code == 200:
data = json.loads(result)
vannualSfcAssertUrl = host + data["vAnnPbAssetUrl"]
webSiteInfoUrl = host + data["webSiteInfoUrl"] + "?entType=17"
# annSfcSocsecinfoUrl = host+data["annSfcSocsecinfoUrl"]
annulLicenceUrl = host + data["annulLicenceUrl"] + "?entType=17"
info["permit"] = annulLicenceUrl
info["web"] = webSiteInfoUrl
# info["society"] = annSfcSocsecinfoUrl
info["base"] = vannualSfcAssertUrl
return info
def name(self, url):
info = {}
content, status_code = Send_Request().send_request(url)
if status_code == 200:
result = etree.HTML(content,
parser=etree.HTMLParser(encoding='utf-8'))
dl = result.xpath("//div[@class ='viewBox']//dl")[0]
datalist = etree.tostring(dl).split(
'<dd style="border-top:1px dashed #ccc;">')
datalist.remove(datalist[-1])
for i, single in enumerate(datalist):
single = etree.HTML(single,
parser=etree.HTMLParser(encoding="utf-8"))
if u"登记编号" in content:
string = u'登记编号'
code = self.deal_dd_content(string, single)
else:
code = None
if u"登记日期" in content:
string = u"登记日期"
dates = self.deal_dd_content(string, single)
else:
dates = '0000-00-00'
if u"登记机关" in content:
string = u"登记机关"
dept = self.deal_dd_content(string, single)
else:
dept = None
string = u"抵押权人名称"
person_name = self.deal_dd_content(string, single)
string = u"抵押权人注册号"
number = self.deal_dd_content(string, single)
string = u"被担保债权种类"
cates = self.deal_dd_content(string, single)
string = u"被担保债权数额"
amount = self.deal_dd_content(string, single)
string = u"担保范围"
ranges = self.deal_dd_content(string, single)
string = u"履行债务开始日期"
start_date = self.deal_dd_content(string, single)
string = u"履行债务结束日期"
end_date = self.deal_dd_content(string, single)
period = start_date + '至' + end_date
info[i] = [
code, dates, dept, person_name, number, cates, amount,
ranges, period
]
return info
