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)
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
