def main(**kwargs):
url = kwargs.get('id_tag')
global proxies
proxies = kwargs.get('proxies')
headers = {
'Host': 'sh.gsxt.gov.cn',
'User-Agent': ('Mozilla/5.0 (Windows NT 6.1; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/54.0.2840.99 Safari/537.36'),
'Referer': 'http://sh.gsxt.gov.cn/notice/search/ent_info_list'
}
resp = url_requests.get(url, headers=headers, proxies=proxies)
page_soup = BeautifulSoup(resp.content, 'lxml')
if len(resp.content) < 1000:
url = page_soup.find('script').text.split("'")[1]
resp = url_requests.get(url, headers=headers, proxies=proxies)
page_soup = BeautifulSoup(resp.content, 'lxml')
all_execute = [
'basicinfo_execute', 's_h_execute', 'b_c_execute', 'member_execute',
'branch_execute', 'adm_punishment_execute', 'abnormal_execute',
'mortgage_basic_execute', 'pledge_execute',
'black_info_execute', 'spot_check_execute',
'stock_freeze_execute', 'stockholder_change_execute',
]
mortgage_execute = [
'c_mortgage_execute', 's_creditor_execute', 'mortgage_execute'
]
credit = CompanyInfo(url) # 实例化
for each in all_execute:
print "Executing: %s" % each
getattr(credit, each)(page_soup)
# businessInfo.pledge_execute(page_soup)
if credit.qyxx_mortgage_basic:
for each in credit.qyxx_mortgage_basic:
url = ('http://sh.gsxt.gov.cn/notice/notice/view_mortage?uuid'
'=') + each['xiangqing'].split("'")[1]
resp = url_requests.get(url, headers=headers, proxies=proxies)
mortgage_soup = BeautifulSoup(resp.content, 'lxml')
for each_mort in mortgage_execute:
print "Executing: %s" % each_mort
getattr(credit, each_mort)(mortgage_soup)
# credit.c_mortgage_execute(page_soup)
results = credit.returnData()
return results
def get_raw_img(self):
headers = {
'User-Agent': ('Mozilla/5.0 (Windows NT 6.1; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/54.0.2840.71 Safari/537.36')
}
r_bg = url_requests.get(self.bg_url, headers=headers, proxies=proxies)
r_fullbg = url_requests.get(self.fullbg_url,
headers=headers,
proxies=proxies)
raw_chunk_img = BytesIO(r_bg.content)
raw_source_img = BytesIO(r_fullbg.content)
return raw_source_img, raw_chunk_img
def branch_execute(self, **kwargs):
key_list = ['xuhao', 'company_num', 'company_name', 'authority']
all_url = kwargs.get('all_url')
keyword = 'branchUrlAll'
# if '个体工商户' in self.qyxx_basicinfo[0]['company_type']:
# keyword = 'gtkeyPersonUrl'
url = None
for each in all_url:
if keyword in each:
url = 'http://www.gsxt.gov.cn' + each.split('"')[1].strip()
break
if url:
headers = get_headers()
response = url_requests.get(url=url,
headers=headers,
proxies=proxies)
url = 'http://www.gsxt.gov.cn' + re.search(
'branchUrlData ="(.*?)"', response.content, re.S).group(1)
headers = get_headers()
response = url_requests.get(url=url,
headers=headers,
proxies=proxies)
json_data = json.loads(response.content)
all_data = json_data.get('data')
total_page = json_data.get('totalPage')
per_page = json_data.get('perPage') # 每页可获取的条目数
if total_page > 1:
for page in range(1, total_page):
form_data = {
# 'draw': 1,
'start': page * per_page,
# 'length': 5
}
headers = get_headers()
response = url_requests.get(url=url,
params=form_data,
headers=headers,
proxies=proxies)
json_data = json.loads(response.content)
data = json_data.get('data')
all_data.extend(data)
result_list = []
for each in all_data:
item = {}
item['company_num'] = each.get('regNo', '')
item['company_name'] = each.get('brName', '')
item['authority'] = each.get('regOrg_CN', '')
result_list.append(item)
self.qyxx_branch = result_list
def member_execute(self, **kwargs):
key_list = ['xuhao', 'person_name', 'p_position']
all_url = kwargs.get('all_url')
keyword = 'keyPersonUrl'
if '个体工商户' in self.qyxx_basicinfo[0]['company_type']:
keyword = 'gtkeyPersonUrl'
url = None
for each in all_url:
if keyword in each:
url = 'http://www.gsxt.gov.cn' + each.split('"')[1].strip()
break
if url:
headers = get_headers()
response = url_requests.get(url=url,
headers=headers,
proxies=proxies)
json_data = json.loads(response.content)
all_data = json_data.get('data')
total_page = json_data.get('totalPage')
per_page = json_data.get('perPage') # 每页可获取的条目数
if total_page > 1:
for page in range(1, total_page):
form_data = {
# 'draw': 1,
'start': page * per_page,
# 'length': 5
}
headers = get_headers()
response = url_requests.get(url=url,
params=form_data,
headers=headers,
proxies=proxies)
json_data = json.loads(response.content)
data = json_data.get('data')
all_data.extend(data)
result_list = []
for each in all_data:
item = {}
name = each.get('name', '')
if name:
name = base64.b64decode(name.split('>')[1].split('<')[0])
item['person_name'] = name
item['p_position'] = each.get('position_CN', '').strip()
result_list.append(item)
self.qyxx_member = result_list
def stockholder_change_execute(self, page_soup):
url = 'http://gx.gsxt.gov.cn/newChange/newChangeAction!getTabForNB_new.dhtml'
# self.params["regno"] = self.regno
self.params["urltag"] = '15'
self.params["flag_num"] = '2'
# self.params["ent_id"] = self.params["entId"]
headers = {
'Host':
'gx.gsxt.gov.cn',
'User-Agent': ('Mozilla/5.0 (Windows NT 6.1; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/54.0.2840.99 Safari/537.36')
}
resp = url_requests.get(url,
headers=headers,
params=self.params,
proxies=proxies)
page_soup = BeautifulSoup(resp.content, 'lxml')
key_list = [
'xuhao', 'person', 'stock', 'person_get', 'court', 'detail'
]
soup = page_soup.find('div', {'id': 'layout-06_02_01'})
if soup:
info = CreditInfo.parse(soup,
'table', {'class': 'tableG'},
key_list=key_list)
self.qyxx_stockholder_change.extend(info)
def spot_check_execute(self, page_soup):
url = 'http://gx.gsxt.gov.cn/gsgs/gsxzcfAction!xj_list_ccjcxx.dhtml'
# self.params["regno"] = self.regno
self.params["urltag"] = '10'
self.params["ent_id"] = self.params["entId"]
headers = {
'Host':
'gx.gsxt.gov.cn',
'User-Agent': ('Mozilla/5.0 (Windows NT 6.1; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/54.0.2840.99 Safari/537.36')
}
resp = url_requests.get(url,
headers=headers,
params=self.params,
proxies=proxies)
page_soup = BeautifulSoup(resp.content, 'lxml')
soup = page_soup.find('div', {'class': 'qyqx-detail'})
if soup:
key_list = [
'xuhao', 'authority', 'spot_type', 'spot_date', 'spot_result'
]
info = CreditInfo.parse(soup,
'table', {'class': 'table-result'},
key_list=key_list)
self.qyxx_spot_check.extend(info)
def pledge_execute(self, **kwargs):
hyperlinks = kwargs.get('hyperlink')
keyword = ['股权出资']
url = get_url(hyperlinks, self.query, keyword)
params = kwargs.get('params')
if url:
response = url_requests.get(url=url,
params=params,
headers=self.headers,
proxies=proxies)
try:
jsn = json.loads(response.content)
items = jsn[0]['list']
except:
print response.content
raise
for each_item in items:
item = {}
item['reg_code'] = each_item.get('equityno', '')
item['pleder'] = each_item.get('pledgor', '')
item['id_card'] = each_item.get('pledblicno', '')
item['plede_amount'] = each_item.get('impam', '')
item['brower'] = each_item.get('imporg', '')
item['brower_id_card'] = each_item.get('imporgblicno', '')
item['reg_date'] = each_item.get('equpledate', '')
item['status'] = each_item.get('type_text', '')
item['changes'] = '详情'
self.qyxx_pledge.append(item)
def spot_check_execute(self):
url = ('http://%s/aiccips//cipSpotCheInfo/cipSpotCheInfoList' %
self.host)
response = url_requests.get(url=url,
params=self.data,
headers=self.headers,
proxies=proxies)
items = json.loads(response.text)['list']['list'] # type is list
if items:
for each_item in items:
item = {}
item['authority'] = each_item.get('aicName', '')
item['spot_type'] = each_item.get('typeStr', '')
item['spot_date'] = each_item.get('insDate', '')
if item['spot_date']:
# 将时间戳转换成日期
date = time.localtime(item['spot_date'] / 1000)
item['spot_date'] = time.strftime("%Y-%m-%d", date)
item['spot_result'] = (each_item.get(
'inspectDetail', '').replace('1', '正常').replace(
'2',
'未按规定公示年报').replace('3', '未按规定公示其他应当公示的信息').replace(
'4', '公示信息隐瞒真实情况、弄虚作假').replace(
'5', '通过登记的住所（经营场所）无法联系').replace(
'6',
'不予配合情节严重').replace('7', '该主体已注销').replace(
'8', '该主体未建财务账').replace('9', '其他'))
self.qyxx_spot_check.append(item)
def black_info_execute(self, **kwargs):
hyperlinks = kwargs.get('hyperlink')
keyword = ['严重违法']
url = get_url(hyperlinks, self.query, keyword)
params = kwargs.get('params')
if url:
response = url_requests.get(url=url,
params=params,
headers=self.headers,
proxies=proxies)
try:
jsn = json.loads(response.content)
items = jsn[0]['list']
except:
print response.content
raise
for each_item in items:
item = {}
item['reason_in'] = each_item.get('serillrea_cn', '')
item['date_in'] = each_item.get('abntime', '')
item['authority_in'] = each_item.get('decorg_cn', '')
item['reason_out'] = each_item.get('remexcpres_cn', '')
item['date_out'] = each_item.get('remdate', '')
item['authority_out'] = each_item.get('recorg_cn', '')
if item['authority_out'] == '' and item['authority_in']:
item['authority'] = item.pop('authority_in')
item.pop('authority_out')
else:
item['authority'] = item.pop('authority_out')
item.pop('authority_in')
self.qyxx_black_info.append(item)
def get_register(self):
'''
可能会被更改值的参数：
self.cookies
self.challenge(32bit)
self.gt
'''
headers = {
'Cookie':
'', #self.cookies
'Host':
'gx.gsxt.gov.cn',
'Referer':
'http://sc.gsxt.gov.cn/ztxy.do?method=index&random=1483924925344', #+ str(int(time.time() * 1000)),
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36'
}
resp = url_requests.get(self.url_start_captcha,
headers=headers,
proxies=proxies)
print 11, resp.cookies
# < RequestsCookieJar[ < Cookie JSESSIONID = yDcJY1kdRLNcQCGLxP4vL5XhLSc1jpvzJh4ZGp8sndsZjyLQ9QTQ!-1937398610 for gx.gsxt.gov.cn / >, < Cookie insert_cookie=72414398 for gx.gsxt.gov.cn / >] >
#<RequestsCookieJar[<Cookie JSESSIONID=hx0GY1sVD85vBGHkhvNbMnNbLpyCy8PsM25D5N1WGH8kpyLnqdXp!1439207493 for gx.gsxt.gov.cn/>, <Cookie insert_cookie=62339635 for gx.gsxt.gov.cn/>]>
# if len(str(resp.cookies).split(" "))>1:
# self.cookies = self.cookies.split(";")[0] + ";" + str(resp.cookies).split(" ")[1]
part_data = resp.json()
if part_data['success'] == 1:
self.challenge = part_data['challenge']
self.gt = part_data['gt']
resp.close()
print 'self.challenge[30:]', self.challenge[30:]
def get_data(urls, keyword):
'''获取版块信息
:param urls: List, 该列表来源于企业信息页面的源代码中，是每个版块的url后缀列表。
:param keyword: str， 板块关键字
:return: List，所需板块的数据
'''
result = []
url = None
for each in urls:
if keyword in each:
url = 'http://www.gsxt.gov.cn' + each.split('"')[1].strip()
break
if url:
headers = get_headers()
response = url_requests.get(url=url, headers=headers, proxies=proxies)
json_data = json.loads(response.content)
all_data = json_data.get('data') # 先获取第一页的数据
total_page = json_data.get('totalPage')
if total_page > 1:
for page in range(1, total_page):
form_data = {'draw': 1, 'start': page * 5, 'length': 5}
headers = get_headers()
response = url_requests.post(url=url,
data=form_data,
headers=headers,
proxies=proxies)
json_data = json.loads(response.content)
data = json_data.get('data')
all_data.extend(data) # 将翻页获取的数据合并
result = all_data
return result
def b_c_execute(self, page_soup):
url = 'http://gx.gsxt.gov.cn/gjjbj/gjjQueryCreditAction!xj_biangengFrame.dhtml'
self.params["regno"] = self.regno
self.params["urlflag"] = '5'
self.params["ent_id"] = self.params["entId"]
headers = {
'Host':
'gx.gsxt.gov.cn',
'User-Agent': ('Mozilla/5.0 (Windows NT 6.1; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/54.0.2840.99 Safari/537.36')
}
resp = url_requests.get(url,
headers=headers,
params=self.params,
proxies=proxies)
page_soup = BeautifulSoup(resp.content, 'lxml')
key_list = [
'xuhao', 'reason', 'before_change', 'after_change',
'date_to_change'
]
soup = page_soup.find('div', {'class': 'qyqx-detail'})
if soup:
info = CreditInfo.parse(soup,
'table', {'class': 'table-result'},
key_list=key_list)
self.qyxx_b_c.extend(info)
def get_checkCode(cookies):
"""用首页的cookie访问验证码，返回验证码字符串
params:
cookies: 访问首页时产生的cookies值
"""
url = 'http://gsxt.ynaic.gov.cn/notice/captcha?preset=0'
headers = {
'Host':
'gsxt.ynaic.gov.cn',
'User-Agent': ('Mozilla/5.0 (Windows NT 6.1; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/54.0.2840.71 Safari/537.36')
}
response = url_requests.get(url,
headers=headers,
cookies=cookies,
timeout=10)
f = BytesIO(response.content)
image = Image.open(f)
# image.show()
# checkCode = raw_input('please input the checkCode: ')
checkCode = image_recognition(image, 'yunnan', config='-psm 7 character')
# print checkCode
return checkCode
def mortgage_execute(self, **kwargs):
mort_id = kwargs.get('mort_id')
url = ('http://cq.gsxt.gov.cn/gsxt/api/mortguarantee/queryList'
'/%s' % mort_id)
params = kwargs.get('params')
response = url_requests.get(url=url,
params=params,
headers=self.headers,
proxies=proxies)
try:
jsn = json.loads(response.content)
items = jsn[0]['list']
except:
print response.content
raise
item_list = []
for each_item in items:
item = {}
item['mortgage_reg_num'] = self.mortgage_reg_num
item['mortgage_name'] = each_item.get('guaname', '')
item['belongs'] = each_item.get('own', '')
item['information'] = each_item.get('guades', '')
item['mortgage_range'] = each_item.get('remark', '')
item_list.append(item)
self.qyxx_mortgage.extend(item_list)
def s_creditor_execute(self, **kwargs):
mort_id = kwargs.get('mort_id')
url = ('http://cq.gsxt.gov.cn/gsxt/api/mortprincipalclaim/dcdydb'
'/%s' % mort_id)
params = kwargs.get('params')
response = url_requests.get(url=url,
params=params,
headers=self.headers,
proxies=proxies)
try:
jsn = json.loads(response.content)
info = jsn[0]['form']
except:
print response.content
raise
item = {}
item['mortgage_reg_num'] = self.mortgage_reg_num
item['mortgage_type'] = info.get('priclaseckind_cn', '')
item['amount'] = info.get('priclasecam', '') + '万元'
item['mortgage_range'] = info.get('warcov', '')
item['time_range'] = info.get('pefperform', '') + '至' + info.get(
'pefperto', '')
self.qyxx_s_creditor.append(item)
def c_mortgage_execute(self, **kwargs):
mort_id = kwargs.get('mort_id')
url = ('http://cq.gsxt.gov.cn/gsxt/api/mortreginfo/dcdy'
'/%s' % mort_id)
params = kwargs.get('params')
response = url_requests.get(url=url,
params=params,
headers=self.headers,
proxies=proxies)
try:
jsn = json.loads(response.content)
info = jsn[0]['form']
except:
print response.content
raise
item = {}
item['mortgage_reg_num'] = info.get('morregcno', '')
self.mortgage_reg_num = info.get('morregcno', '')
item['date_reg'] = info.get('regidate', '')
item['authority'] = info.get('regorg_cn', '')
item['mortgage_type'] = ''
item['amount'] = ''
item['time_range'] = ''
item['mortgage_range'] = ''
self.qyxx_c_mortgage.append(item)
def stock_freeze_execute(self, **kwargs):
hyperlinks = kwargs.get('hyperlink')
keyword = ['司法协助']
url = get_url(hyperlinks, self.query, keyword)
params = kwargs.get('params')
if url:
response = url_requests.get(url=url,
params=params,
headers=self.headers,
proxies=proxies)
try:
jsn = json.loads(response.content)
items = jsn[0]['list']
except:
print response.content
raise
for each_item in items:
item = {}
item['person'] = each_item.get('inv', '')
item['stock'] = each_item.get('infroam', each_item.get(
'froam', ''))
item['court'] = each_item.get('froauth', '')
item['notice_number'] = each_item.get('executeno', '')
item['status'] = each_item.get('frozstate_cn', '')
self.qyxx_stock_freeze.append(item)
def spot_check_execute(self, **kwargs):
hyperlinks = kwargs.get('hyperlink')
keyword = ['抽查检查']
url = get_url(hyperlinks, self.query, keyword)
params = kwargs.get('params')
if url:
response = url_requests.get(url=url,
params=params,
headers=self.headers,
proxies=proxies)
try:
jsn = json.loads(response.content)
items = jsn[0]['list']
except:
print response.content
raise
for each_item in items:
item = {}
item['authority'] = each_item.get('insauth_cn', '')
item['spot_type'] = each_item.get('instype', '')
item['spot_date'] = each_item.get('insdate', '')
item['spot_result'] = each_item.get('insres_cn', '')
self.qyxx_spot_check.append(item)
def branch_execute(self, page_soup):
url = 'http://gx.gsxt.gov.cn/gjjbj/gjjQueryCreditAction!fzjgFrame.dhtml'
self.params["regno"] = self.regno
self.params["urltag"] = '4'
self.params["ent_id"] = self.params["entId"]
headers = {
'Host':
'gx.gsxt.gov.cn',
'User-Agent': ('Mozilla/5.0 (Windows NT 6.1; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/54.0.2840.99 Safari/537.36')
}
resp = url_requests.get(url,
headers=headers,
params=self.params,
proxies=proxies)
page_soup = BeautifulSoup(resp.content, 'lxml')
soup = page_soup.find('div', {'class': 'qyqx-detail'})
if soup:
td = soup.find_all('table')
for each in td:
info = {}
td = each.find_all(
'td') # 'company_num', 'company_name', 'authority'
info['company_name'] = td[0].text.strip()
info['company_num'] = td[1].text.split(
'：')[1].strip() if len(td) > 1 else ''
info['authority'] = td[2].text.split(
'：')[1].strip() if len(td) > 2 else ''
self.qyxx_branch.append(info)
def get_cookies():
"""获取首页的cookies
:return: cookies
"""
url = 'http://www.jsgsj.gov.cn:58888/province/'
headers = {
'Host':
'www.jsgsj.gov.cn:58888',
'X-Forwarded-For':
'8.8.8.8',
'Referer':
'http://gsxt.saic.gov.cn/',
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/44.0.2403.155 Safari/537.36'
}
response = url_requests.get(url=url,
headers=headers,
proxies=proxies,
timeout=20)
cookies = dict(response.cookies)
return cookies
def get_home(self):
'''
可能会被更改值的参数：
self.cookies
'''
headers = {
'Host':
'gx.gsxt.gov.cn',
# 'Connection': 'keep-alive',
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'User-Agent': ('Mozilla/5.0 (Windows NT 6.1; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/54.0.2840.99 Safari/537.36')
}
resp = url_requests.get(url=self.url_home,
headers=headers,
proxies=proxies)
print "00:", resp.cookies
if len(str(resp.cookies).split(" ")) > 5:
print 'get'
self.cookies = str(resp.cookies).split(" ")[5] + ";" + str(
resp.cookies).split(" ")[1]
elif 5 > len(str(resp.cookies).split(" ")) > 2:
print 'get2'
self.cookies = self.cookies.split(";")[0] + ";" + str(
resp.cookies).split(" ")[1]
resp.close()
def mortgage_basic_execute(self):
url = ('http://%s/aiccips//PleInfo/PleInfoList' % self.host)
response = url_requests.get(url=url,
params=self.data,
headers=self.headers,
proxies=proxies)
items = json.loads(response.text)['list']['list'] # type is list
if items:
for each_item in items:
item = {}
item['mortgage_reg_num'] = each_item.get('pleNo', '')
item['date_reg'] = each_item.get('regiDate', '')
if item['date_reg']:
# 将时间戳转换成日期
date = time.localtime(item['date_reg'] / 1000)
item['date_reg'] = time.strftime("%Y-%m-%d", date)
item['authority'] = each_item.get('regOrgStr', '')
item['amount'] = str(each_item.get('priClaSecAm', '')) + '万元'
if '1' in each_item.get('type', ''):
item['status'] = '有效'
else:
item['status'] = '无效'
item['gongshiriqi'] = each_item.get('pefPerForm', '')
if item['gongshiriqi']:
# 将时间戳转换成日期
date = time.localtime(item['gongshiriqi'] / 1000)
item['gongshiriqi'] = time.strftime("%Y-%m-%d", date)
item['detail'] = each_item # 后面通过这个信息里的字段获取详细信息
self.qyxx_mortgage_basic.append(item)
def mortgage_basic_execute(self, page_soup):
url = 'http://gx.gsxt.gov.cn/gjjbjTab/gjjTabQueryCreditAction!dcdyFrame.dhtml'
# self.params["regno"] = self.regno
self.params["urltag"] = '12'
# self.params["ent_id"] = self.params["entId"]
headers = {
'Host':
'gx.gsxt.gov.cn',
'User-Agent': ('Mozilla/5.0 (Windows NT 6.1; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/54.0.2840.99 Safari/537.36')
}
resp = url_requests.get(url,
headers=headers,
params=self.params,
proxies=proxies)
page_soup = BeautifulSoup(resp.content, 'lxml')
soup = page_soup.find('div', {'class': 'qyqx-detail'})
# print soup
if soup:
key_list = [
'xuhao', 'mortgage_reg_num', 'date_reg', 'authority', 'amount',
'status', 'gsrq', 'xiangqing'
]
info = CreditInfo.parse(soup,
'table', {'class': 'table-result'},
key_list=key_list)
self.qyxx_mortgage_basic.extend(info)
def adm_punishment_execute(self, **kwargs):
hyperlinks = kwargs.get('hyperlink')
keyword = ['行政处罚']
url = get_url(hyperlinks, self.query, keyword)
params = kwargs.get('params')
if url:
response = url_requests.get(url=url,
params=params,
headers=self.headers,
proxies=proxies)
try:
jsn = json.loads(response.content)
items = jsn[0]['list']
except:
print response.content
raise
for each_item in items:
item = {}
item['pun_number'] = each_item.get('pendecno', '')
item['reason'] = each_item.get('illegacttype', '')
item['fines'] = each_item.get('pencontent', '')
item['authority'] = each_item.get('penauth_cn', '')
item['pun_date'] = each_item.get('pendecissdate', '')
item['gongshiriqi'] = each_item.get('publicdate', '')
self.qyxx_adm_punishment.append(item)
def get_checkCode():
"""用cookies获取验证码并识别成字符串
:return: string
"""
captcha_url = 'http://www.jsgsj.gov.cn:58888/province/rand_img.jsp'
headers = {
'X-Forwarded-For':
'8.8.8.8',
'Host':
'www.jsgsj.gov.cn:58888',
'Referer':
'http://www.jsgsj.gov.cn:58888/province/',
'User-Agent': ('Mozilla/5.0 (Windows NT 6.1; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/44.0.2403.155 Safari/537.36')
}
html = url_requests.get(url=captcha_url,
headers=headers,
cookies=cookies,
proxies=proxies,
timeout=20).content
file = BytesIO(html)
im = Image.open(file)
checkCode = image_to_string(im)
return checkCode
def pledge_execute(self, page_soup):
url = 'http://gx.gsxt.gov.cn/gdczdj/gdczdjAction!gdczdjFrame.dhtml'
# self.params["regno"] = self.regno
self.params["urltag"] = '13'
# self.params["ent_id"] = self.params["entId"]
headers = {
'Host':
'gx.gsxt.gov.cn',
'User-Agent': ('Mozilla/5.0 (Windows NT 6.1; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/54.0.2840.99 Safari/537.36')
}
resp = url_requests.get(url,
headers=headers,
params=self.params,
proxies=proxies)
page_soup = BeautifulSoup(resp.content, 'lxml')
key_list = [
'xuhao', 'reg_code', 'pleder', 'id_card', 'plede_amount', 'brower',
'brower_id_card', 'reg_date', 'status', 'gongshiriqi', 'changes'
]
soup = page_soup.find('div', {'class': 'qyqx-detail'})
# print soup
if soup:
info = CreditInfo.parse(soup,
'table', {'class': 'table-result'},
key_list=key_list)
self.qyxx_pledge.extend(info)
def pledge_execute(self):
url = ('http://%s/aiccips//StoPleInfo/StoPleInfoList' % self.host)
response = url_requests.get(url=url,
params=self.data,
headers=self.headers,
proxies=proxies)
items = json.loads(response.text)['list']['list'] # type is list
if items:
for each_item in items:
item = {}
item['reg_code'] = each_item.get('stoRegNo', '').strip()
item['pleder'] = each_item.get('inv', '')
item['id_card'] = each_item.get('invID', '')
item['plede_amount'] = str(each_item.get('impAm', '')) + '万元'
item['brower'] = each_item.get('impOrg', '')
item['brower_id_card'] = each_item.get('impOrgID', '')
item['reg_date'] = each_item.get('registDate', '')
if item['reg_date']:
# 将时间戳转换成日期
date = time.localtime(item['reg_date'] / 1000)
item['reg_date'] = time.strftime("%Y-%m-%d", date)
if '1' in each_item.get('type', ''):
item['status'] = '有效'
else:
item['status'] = '无效'
item['changes'] = '详情'
self.qyxx_pledge.append(item)
def adm_punishment_execute(self, page_soup):
url = 'http://gx.gsxt.gov.cn//gdgq/gdgqAction!xj_qyxzcfFrame.dhtml'
# self.params["regno"] = self.regno
self.params["urltag"] = '14'
# self.params["ent_id"] = self.params["entId"]
headers = {
'Host':
'gx.gsxt.gov.cn',
'User-Agent': ('Mozilla/5.0 (Windows NT 6.1; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/54.0.2840.99 Safari/537.36')
}
resp = url_requests.get(url,
headers=headers,
params=self.params,
proxies=proxies)
page_soup = BeautifulSoup(resp.content, 'lxml')
key_list = [
'xuhao', 'pun_number', 'reason', 'fines', 'authority', 'pun_date',
'gongshiriqi', 'detail'
]
soup = page_soup.find('div', {'class': 'qyqx-detail'})
if soup:
info = CreditInfo.parse(soup,
'table', {'class': 'table-result'},
key_list=key_list)
self.qyxx_adm_punishment.extend(info)
def stock_freeze_execute(self):
url = ('http://%s/aiccips//judiciaryAssist/judiciaryAssistList' %
self.host)
response = url_requests.get(url=url,
params=self.data,
headers=self.headers,
proxies=proxies)
items = json.loads(response.text)['list']['list'] # type is list
if items:
for each_item in items:
item = {}
item['person'] = each_item.get('inv', '')
item['stock'] = str(each_item.get('froAm', '')) + '万元人民币'
item['court'] = each_item.get('froAuth', '')
item['notice_number'] = each_item.get('froDocNo', '')
item['status'] = each_item.get('frozState', '').strip()
if item['status'] in ['1', '2', '3', '4']:
item['status'] = '冻结'
elif item['status'] == '5':
item['status'] = '解除冻结'
else:
item['status'] = '失效'
self.qyxx_stock_freeze.append(item)
def abnormal_execute(self, page_soup):
url = 'http://gx.gsxt.gov.cn/gsgs/gsxzcfAction!list_jyycxx.dhtml'
self.params["regno"] = self.regno
self.params["urlflag"] = '8'
headers = {
'Host':
'gx.gsxt.gov.cn',
'User-Agent': ('Mozilla/5.0 (Windows NT 6.1; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/54.0.2840.99 Safari/537.36')
}
resp = url_requests.get(url,
headers=headers,
params=self.params,
proxies=proxies)
page_soup = BeautifulSoup(resp.content, 'lxml')
# print page_soup
key_list = [
'xuhao', 'reason', 'date_occurred', 'authority_occurred',
'reason_out', 'date_out', 'authority'
]
info = CreditInfo.parse(page_soup,
'table', {'class': 'table-result'},
key_list=key_list)
self.qyxx_adm_punishment.extend(info)
