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(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 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)
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('<br/>')
datalist.remove(datalist[-1])
for i, single in enumerate(datalist):
single = etree.HTML(single, parser=etree.HTMLParser(encoding="utf-8"))
string = u"许可文件名称"
types = deal_dd_content(string, single)
string = u"有效期至"
valto = deal_dd_content(string, single)
uuid = ''
info[i] = [types, valto, uuid]
else:
flag = 100000004
if flag == 1:
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)
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]
ddlist = dl.xpath('./dd')
remark = -1
for i, single in enumerate(ddlist):
if i % 4 == 0:
remark += 1
name = single.xpath("./text()")[0]
name = deal_html_code.remove_space(name)
info.setdefault(remark, []).append(name)
elif i % 4 == 1:
percent_pre = single.xpath("./text()")[0]
percent_pre = deal_html_code.remove_space(percent_pre)
info.setdefault(remark, []).append(percent_pre)
elif i % 4 == 2:
percent_after = single.xpath("./text()")[0]
percent_after = deal_html_code.remove_space(percent_after)
info.setdefault(remark, []).append(percent_after)
elif i % 4 == 3:
dates = single.xpath("./text()")[0]
dates = deal_html_code.remove_space(dates)
info.setdefault(remark, []).append(dates)
uuid = ''
info.setdefault(remark, []).append(uuid)
else:
flag = 100000004
if flag == 1:
deal_html_code.remove_repeat(info)
return info, 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 = 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()")[0]
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)
if ra_date == '':
ra_date = '0000-00-00'
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)
if ta_date == '':
ta_date = '0000-00-00'
info[i] = [
name, types, reg_amount, ra_ways, ra_date, true_amount,
ta_ways, ta_date
]
else:
flag = 100000004
if len(info) > 0:
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)
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
