def get_gu_dong_detail(self, inv_id):
url = "http://www.gsxt.gov.cn/corp-query-entprise-info-shareholderDetail-%s.html" % urllib.quote(
inv_id.encode('utf-8')).replace('%7C', '|')
try:
r = self.get_request(url)
j = json.loads(r.text)
except (requests.exceptions.ContentDecodingError, ValueError):
return {u'认缴明细': [], u'实缴明细': []}
rjmx = []
sjmx = []
if 'data' in j:
sj_data = j['data'][0]
rj_data = j['data'][1]
for sj in sj_data:
sje = sj['acConAm']
sjczfs = sj['conForm_CN']
sjczrq = TimeUtils.get_date(sj['conDate'])
sjmx.append({
u'实缴出资方式': sjczfs,
u'实缴出资额(万元)': sje,
u'实缴出资日期': sjczrq
})
for rj in rj_data:
rje = rj['subConAm']
rjczfs = rj['conForm_CN']
rjczrq = TimeUtils.get_date(rj['conDate'])
rjmx.append({
u'认缴出资方式': rjczfs,
u'认缴出资额(万元)': rje,
u'认缴出资日期': rjczrq
})
return {u'认缴明细': rjmx, u'实缴明细': sjmx}
def get_dong_chan_di_ya_detail(self, dy_id, output_data):
# 抵押权人信息
dyqrxx_url = 'http://www.gsxt.gov.cn/corp-query-entprise-info-mortregpersoninfo-%s.html' % dy_id
dyqrxx_res = self.get_request(dyqrxx_url)
dyqrxx_data = json.loads(dyqrxx_res.text)['data']
dyqrxx_dict = {
'bLicType_CN': 'dyqr_zzlx', # 抵押权人证照类型
'more': 'dyqr_mc', # 抵押权人名称
'bLicNo': 'dyqr_zzhm', # 证照号码
# '': '', # 住所地
}
# 被担保主债权信息
bdbzzqxx_url = 'http://www.gsxt.gov.cn/corp-query-entprise-info-mortCreditorRightInfo-%s.html' % dy_id
bdbzzqxx_res = self.get_request(bdbzzqxx_url)
bdbzzqxx_data = json.loads(bdbzzqxx_res.text)['data']
bdbzzqxx_dict = {
'priClaSecKind_CN': 'dbzq_zl', # 种类
'priClaSecAm': 'dbzq_sl', # 数额
'warCov': 'dbzq_fw', # 担保的范围
'remark': 'dbzq_bz', # 备注
}
# 抵押物信息
dywxx_url = 'http://www.gsxt.gov.cn/corp-query-entprise-info-mortGuaranteeInfo-%s.html' % dy_id
dywxx_res = self.get_request(dywxx_url)
dywxx_data = json.loads(dywxx_res.text)['data']
dywxx_dict = {
'guaDes': 'dyw_xq', # 数量、质量、状况、所在地等情况
'own': 'dyw_gs', # 所有权或使用权归属
'guaName': 'dyw_mc', # 抵押物名称
}
for d in dyqrxx_data:
for k in d:
if k in dyqrxx_dict:
col = dyqrxx_dict[k]
val = d[k]
output_data[col] = val
for d in bdbzzqxx_data:
for k in d:
if k in bdbzzqxx_dict:
col = bdbzzqxx_dict[k]
val = d[k]
# if col == 'pefPerForm' or col == 'pefPerTo' and val:
# val = TimeUtils.get_date(val)
if col == 'priClaSecAm':
val = val + bdbzzqxx_data['regCapCur_CN']
output_data[col] = val
output_data['dbzq_qx'] = TimeUtils.get_date(
d['pefPerForm']) + u'至' + TimeUtils.get_date(d['pefPerTo'])
# val = TimeUtils.get_date(val)
for d in dywxx_data:
for k in d:
if k in dywxx_dict:
col = dywxx_dict[k]
val = d[k]
output_data[col] = val
def get_gt_challenge(self, t=1):
if t == 15:
raise Exception(u'获取不到challenge')
self.info(u'第%d次获取challenge。。。' % t)
ts_1 = TimeUtils.get_cur_ts_mil()
url_1 = "http://sd.gsxt.gov.cn/pub/geetest/register/%s?_=%s" % (TimeUtils.get_cur_ts_mil(), ts_1)
r_1 = self.get_request(url_1)
try:
self.challenge = str(json.loads(r_1.text)['challenge'])
self.gt = str(json.loads(r_1.text)['gt'])
except:
self.get_gt_challenge(t+1)
def get_chou_cha_jian_cha(self):
"""
获取抽查检查信息
:return:
"""
draw = 1
chou_cha_jian_cha_data = []
while True:
params = {
'draw': draw,
'length': 5,
'start': 5 * (draw - 1),
}
r = self.post_request(self.chou_cha_jian_cha_url, params=params)
json_obj = json.loads(r.text)
data = json_obj['data']
for item in data:
chou_cha_jian_cha_data.append({})
for k in item:
if k in TianJinConfig.chou_cha_jian_cha_dict:
col = TianJinConfig.chou_cha_jian_cha_dict[k]
val = item[k]
if type(val) == unicode:
if '<span' in val:
val = re.sub('<span[^<]*</span>', '', val)
if '<div' in val:
val = re.sub('<div[^<]*</div>', '', val)
val = re.sub(r'\s', '', val)
if col == 'check_type':
if str(val) == '1':
val = u'抽查'
elif str(val) == '2':
val = u'检查'
elif col == 'check_date' and val:
val = TimeUtils.get_date(val)
chou_cha_jian_cha_data[-1][col] = val
if int(json_obj['draw']) < int(json_obj['totalPage']):
draw += 1
# self.get_chou_cha_jian_cha(draw + 1, chou_cha_jian_cha_data)
else:
# print json.dumps(chou_cha_jian_cha_data, ensure_ascii=False)
family = 'Spot_Check'
table_id = '16'
self.json_result[family] = []
for i in range(len(chou_cha_jian_cha_data)):
row = chou_cha_jian_cha_data[i]
self.json_result[family].append({})
self.json_result[family][-1][
'rowkey'] = '%s_%s_%s_%s%d' % (self.cur_mc, table_id,
self.reg_code,
self.today, i + 1)
self.json_result[family][-1][
family + ':registrationno'] = self.reg_code
self.json_result[family][-1][
family + ':enterprisename'] = self.cur_mc
for k in row:
col = family + ':' + k
val = row[k]
self.json_result[family][-1][col] = val
break
def break_params(self):
bg_img = self.down_geetest_img(self.bg_url)
slice_img = self.down_geetest_img(self.slice_url)
fullbg_path = os.path.join(os.path.dirname(__file__), '../data/fullbg/' + self.fullbg_url.split('/')[-1])
if not os.path.exists(fullbg_path):
print u'New fullbg image'
fullbg_img = self.down_geetest_img(self.fullbg_url)
fullbg_img.save(fullbg_path)
fullbg_img = Image.open(fullbg_path)
distance = GeetestDistanceV2.get_distance(bg_img, fullbg_img, slice_img)
# print 'distance->', distance
trail_arr = BreakTrail.get_trali_arr(distance)
# print 'distance:', distance
pass_time = trail_arr[-1][-1]
# print trail_arr
params = {
'challenge': str(self.challenge),
'gt': str(self.gt),
'userresponse': GeetestParamsBroker.imitate_userrespose(distance, self.challenge),
'passtime': pass_time,
'imgload': random.randint(70, 150),
'aa': GeetestParamsBroker.imitate_aa(trail_arr, self.c, self.s),
'callback': 'geetest_%s' % TimeUtils.get_cur_ts_mil(),
}
# print json.dumps(params, indent=4)
return params, trail_arr[-1][2]
def get_gt_challenge(self):
url_1 = 'http://bj.gsxt.gov.cn/pc-geetest/register?t=%s' % TimeUtils.get_cur_ts_mil(
)
# print url_1
r_1 = self.get_request(url_1)
self.challenge = str(json.loads(r_1.text)['challenge'])
self.gt = str(json.loads(r_1.text)['gt'])
def get_dong_chan_di_ya(self):
draw = 1
dong_chan_di_ya_data = []
while True:
params = {
'draw': draw,
'length': 5,
'start': 5 * (draw - 1),
}
r = self.post_request(self.dong_chan_di_ya_url, params=params)
json_obj = json.loads(r.text)
data = json_obj['data']
for item in data:
dong_chan_di_ya_data.append({})
for k in item:
if k in ZongJuConfig.dong_chan_di_ya_dict:
col = ZongJuConfig.dong_chan_di_ya_dict[k]
val = item[k]
if type(val) == unicode:
if '<span' in val:
val = re.sub('<span[^<]*</span>', '', val)
if '<div' in val:
val = re.sub('<div[^<]*</div>', '', val)
val = re.sub(r'\s', '', val)
if col == 'chattelmortgage_status':
if str(val) == '1':
val = u'有效'
else:
val = u'无效'
elif col == 'chattelmortgage_guaranteedamount':
val = str(val) + re.sub(r'\s', '',
item['regCapCur_Cn'])
elif col == 'chattelmortgage_registrationdate' and val:
val = TimeUtils.get_date(val)
dong_chan_di_ya_data[-1][col] = val
if int(json_obj['draw']) < int(json_obj['totalPage']):
draw += 1
# self.get_gu_quan_chu_zhi(draw + 1, dong_chan_di_ya_data)
else:
# print json.dumps(dong_chan_di_ya_data, ensure_ascii=False)
family = 'Chattel_Mortgage'
table_id = '11'
self.json_result[family] = []
for i in range(len(dong_chan_di_ya_data)):
row = dong_chan_di_ya_data[i]
self.json_result[family].append({})
self.json_result[family][-1][
'rowkey'] = '%s_%s_%s_%s%d' % (self.input_company_name,
table_id, self.reg_code,
self.today, i + 1)
self.json_result[family][-1][
family + ':registrationno'] = self.reg_code
self.json_result[family][-1][
family + ':enterprisename'] = self.input_company_name
for k in row:
col = family + ':' + k
val = row[k]
self.json_result[family][-1][col] = val
break
def get_gt_challenge(self):
url_1 = "http://zj.gsxt.gov.cn/pc-geetest/register?t=%s" % TimeUtils.get_cur_ts_mil(
)
self.info(u'获取gt和challenge...')
r_1 = self.get_request(url_1)
json_1 = json.loads(r_1.text)
self.gt = json_1['gt']
self.challenge = json_1['challenge']
def get_gt_challenge(self):
url_1 = "http://www.gsxt.gov.cn/SearchItemCaptcha?v=%s" % TimeUtils.get_cur_ts_mil()
# print url_1
self.info(u'**获取gt和challenge...')
r_1 = self.get(url_1)
json_1 = json.loads(r_1.text)
self.gt = json_1['gt']
self.challenge = json_1['challenge']
def get_jing_ying_yi_chang(self):
"""
获取经营异常信息
:return:
"""
draw = 1
jing_ying_yi_chang_data = []
while True:
params = {
'draw': draw,
'length': 5,
'start': 5 * (draw - 1),
}
r = self.post_request(self.jing_ying_yi_chang_url, params=params)
json_obj = json.loads(r.text)
data = json_obj['data']
for item in data:
jing_ying_yi_chang_data.append({})
for k in item:
if k in TianJinConfig.jing_ying_yi_chang_dict:
col = TianJinConfig.jing_ying_yi_chang_dict[k]
val = item[k]
if type(val) == unicode:
if '<span' in val:
val = re.sub('<span[^<]*</span>', '', val)
if '<div' in val:
val = re.sub('<div[^<]*</div>', '', val)
val = re.sub(r'\s', '', val)
if col == 'abnormal_datesin' or col == 'abnormal_datesout' and val:
val = TimeUtils.get_date(val)
jing_ying_yi_chang_data[-1][col] = val
if int(json_obj['draw']) < int(json_obj['totalPage']):
draw += 1
# self.get_jing_ying_yi_chang(draw + 1, jing_ying_yi_chang_data)
else:
# print json.dumps(jing_ying_yi_chang_data, ensure_ascii=False)
family = 'Business_Abnormal'
table_id = '14'
self.json_result[family] = []
for i in range(len(jing_ying_yi_chang_data)):
row = jing_ying_yi_chang_data[i]
self.json_result[family].append({})
self.json_result[family][-1][
'rowkey'] = '%s_%s_%s_%s%d' % (self.cur_mc, table_id,
self.reg_code,
self.today, i + 1)
self.json_result[family][-1][
family + ':registrationno'] = self.reg_code
self.json_result[family][-1][
family + ':enterprisename'] = self.cur_mc
for k in row:
col = family + ':' + k
val = row[k]
self.json_result[family][-1][col] = val
break
def submit_search_request(self,
keyword,
flags=True,
account_id='null',
task_id='null'):
"""
提交详细查询请求，解析详情内容
:param keyword: 查询输入内容
:param flags: 查询内容信用代码还是公司名
:param account_id: 账户id
:param task_id: 任务id
:return:
"""
self.json_result = {}
self.today = TimeUtils.get_today()
keyword = keyword.replace('(', u'（').replace(')',
u'）').replace(' ', '')
mc, xydm = '', ''
if flags:
mc = keyword
else:
xydm = keyword
self.tag_a = self.get_tag_a_from_page(keyword)
if self.tag_a:
self.json_result['inputCompanyName'] = keyword
self.json_result['taskId'] = task_id
self.json_result['accountId'] = account_id
# self.info('jiben')
self.get_ying_ye_zhi_zhao()
# self.info('zhuyaorenyuan')
try:
self.get_zhu_yao_ren_yuan()
except Exception as e:
self.info(u'主要人员表失败:%s' % e)
pass
# self.info('biangeng')
self.get_bian_geng()
# self.info('gudong')
self.get_gu_dong()
# self.get_gu_quan_chu_zhi()
# self.get_dong_chan_di_ya()
# self.get_jing_ying_yi_chang()
# self.get_chou_cha_jian_cha()
# self.get_xing_zheng_chu_fa()
# self.send_msg(json.dumps(self.json_result, ensure_ascii=False)) # 已失效
self.send_msg_to_kafka(
json.dumps(self.json_result, ensure_ascii=False))
return 1
else:
return 0
def refresh_api(self):
self.info(u'轨迹有误，刷新极验api...')
url_2 = "http://api.geetest.com/refresh.php?" \
"challenge=%s" \
">=%s" \
"&callback=geetest_%s" % (self.challenge, self.gt, TimeUtils.get_cur_ts_mil())
r_2 = self.get(url_2)
# print r_2.text
json_2 = json.loads(r_2.text[r_2.text.find('{'):r_2.text.rfind('}') + 1])
self.bg_url = 'http://' + self.static_server + json_2['bg']
self.fullbg_url = 'http://' + self.static_server + json_2['fullbg']
self.slice_url = 'http://' + self.static_server + json_2['slice']
self.challenge = json_2['challenge']
def get_bian_geng(self):
draw = 1
bian_geng_data = []
while True:
params = {
'draw': draw,
'length': 5,
'start': 5 * (draw - 1),
}
r = self.post_request(self.bian_geng_url, params=params)
json_obj = json.loads(r.text)
data = json_obj['data']
for item in data:
bian_geng_data.append({})
for k in item:
col = ZongJuConfig.bian_geng_dict[k]
val = item[k]
if type(val) == unicode:
if '<span' in val:
val = re.sub('<span[^<]*</span>', '', val)
if '<div' in val:
val = re.sub('<div[^<]*</div>', '', val)
val = re.sub(r'\s', '', val)
if col == 'changedannouncement_date' and val:
val = TimeUtils.get_date(val)
bian_geng_data[-1][col] = val
if int(json_obj['draw']) < int(json_obj['totalPage']):
draw += 1
# self.get_bian_geng(draw + 1, bian_geng_data)
else:
# print json.dumps(bian_geng_data, ensure_ascii=False)
family = 'Changed_Announcement'
table_id = '05'
self.json_result[family] = []
for i in range(len(bian_geng_data)):
row = bian_geng_data[i]
self.json_result[family].append({})
self.json_result[family][-1][
'rowkey'] = '%s_%s_%s_%s%d' % (self.input_company_name,
table_id, self.reg_code,
self.today, i + 1)
self.json_result[family][-1][
family + ':registrationno'] = self.reg_code
self.json_result[family][-1][
family + ':enterprisename'] = self.input_company_name
for k in row:
col = family + ':' + k
val = row[k]
self.json_result[family][-1][col] = val
break
def get_gt_challenge(self, t=0):
if t == 15:
raise Exception(u'获取gt和challenge失败')
url_1 = 'http://hb.gsxt.gov.cn/registerValidate.jspx?t=%s' % TimeUtils.get_cur_ts_mil(
)
r_1 = self.get_request(url_1)
# print r_1.text, r_1.text.strip().startswith('{'), r_1.text.strip().endswith('}')
if r_1.text.strip().startswith('{') and r_1.text.strip().endswith('}'):
self.challenge = str(json.loads(r_1.text)['challenge'])
self.gt = str(json.loads(r_1.text)['gt'])
else:
time.sleep(1)
self.reset_session()
self.get_gt_challenge(t + 1)
def get_tag_a_from_page(self, keyword):
cur_ts_mil = TimeUtils.get_cur_ts_mil()
yzm_url = "http://qyxy.baic.gov.cn/CheckCodeYunSuan?currentTimeMillis=%s" % cur_ts_mil
yzm = self.get_yzm(yzm_url)
print 'yzm', yzm
check_url = "http://qyxy.baic.gov.cn/login/loginAction!checkCode.dhtml?check_code=%s¤tTimeMillis=%s&random=%s" \
% (yzm, cur_ts_mil, random.randint(10000, 100000))
print check_url
r = self.post_request(
check_url,
headers={
"User-Agent":
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.11; rv:52.0) Gecko/20100101 Firefox/52.0",
"Host": "qyxy.baic.gov.cn",
})
print r.text
search_url = "http://qyxy.baic.gov.cn/es/esAction!entlist.dhtml?currentTimeMillis=%s&credit_ticket=%s&check_code=%s" % (
cur_ts_mil, self.credit_ticket, yzm)
print search_url
params = {
'idFlag': 'qyxy',
'module': '',
'queryStr': keyword,
'currentTimeMillis': cur_ts_mil,
'credit_ticket': self.credit_ticket,
'check_code': yzm
}
print params
search_url = "http://qyxy.baic.gov.cn/es/esAction!entlist.dhtml?currentTimeMillis=" + cur_ts_mil + "&credit_ticket=" + self.credit_ticket + "&check_code=" + yzm + "&idFlag=qyxy&module=&queryStr=%E9%94%A4%E5%AD%90%E7%A7%91%E6%8A%80"
print search_url
r = self.post_request(
search_url,
headers={
"User-Agent":
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.11; rv:52.0) Gecko/20100101 Firefox/52.0",
"Host": "qyxy.baic.gov.cn",
# "Content-Length": "0",
# "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
# "Accept-Encoding": "gzip, deflate",
# "Accept-Language": "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3",
# "Connection": "keep-alive",
# "Upgrade-Insecure-Requests": "1",
# "Referer": "http://qyxy.baic.gov.cn/simple/dealSimpleAction!transport_ww.dhtml?fourth=fourth&sysid=0150008788304366b7d3903b5067bb8c&module=wzsy&styleFlag=sy",
})
r.encoding = 'utf-8'
print r.text
print self.session.cookies
def run(self):
cnt_0 = 0
cnt_1 = 0
cnt_2 = 0
while True:
sql_1 = "select mc,province from " \
"(" \
"select * from %s where update_status=-1 limit 30 " \
") t " \
"order by RAND() limit 1" % self.src_table
# print sql_1
res_1 = MySQL.execute_query(sql_1)
if len(res_1) > 0:
mc = res_1[0][0]
last_update_date = TimeUtils.get_today()
sql_2 = "update %s set update_status=-2 " \
"where mc='%s'" \
% (self.src_table, mc)
MySQL.execute_update(sql_2)
try:
update_status = self.searcher.submit_search_request(
keyword=mc)
sql_3 = "update %s set update_status=%d, last_update_time=now() " \
"where mc='%s'" % \
(self.src_table, update_status, mc)
except Exception, e:
self.info(traceback.format_exc(e))
update_status = -1
self.info(str(e))
sql_3 = "update %s set update_status=%d,last_update_time=now() " \
"where mc='%s'" % \
(self.src_table, update_status, mc)
MySQL.execute_update(sql_3)
if update_status == 0:
cnt_0 += 1
elif update_status == 1:
cnt_1 += 1
else:
cnt_2 += 1
self.info(u'查询有结果: %d, 查询无结果: %d, 查询失败:%d' %
(cnt_1, cnt_0, cnt_2))
else:
self.info(u'更新完毕')
break
def submit_search_request(self,
keyword,
account_id='null',
task_id='null'):
"""
:param keyword:
:param flags: {True： 名称查询，False：信用代码查询}
:param account_id:
:param task_id:
:return:
"""
if check(keyword):
is_xydm = True
else:
is_xydm = False
keyword = self.process_mc(keyword)
update_status = 0
self.json_result.clear()
# keyword = self.process_mc(keyword)
self.json_result['accountId'] = account_id
self.json_result['taskId'] = task_id
self.today = TimeUtils.get_today()
self.tag_a = self.get_tag_a_from_page(keyword)
self.json_result['inputCompanyName'] = self.input_company_name
# print self.tag_a
if self.tag_a:
if is_xydm or self.input_company_name == keyword:
update_status = 1
else:
update_status = 888
if self.get_ying_ye_zhi_zhao():
self.get_zhu_yao_ren_yuan()
self.get_bian_geng()
self.get_gu_dong()
# self.get_gu_quan_chu_zhi()
# self.get_dong_chan_di_ya()
# self.get_jing_ying_yi_chang()
# self.get_chou_cha_jian_cha()
# self.get_xing_zheng_chu_fa()
self.send_msg_to_kafka(
json.dumps(self.json_result, ensure_ascii=False))
else:
update_status = -1
return update_status
def load_api(self):
self.info(u'获取极验api...')
ts = TimeUtils.get_cur_ts_mil()
url_1 = 'http://api.geetest.com/gettype.php?gt=%s&callback=geetest_%s' % (self.gt, ts)
# print 'url_1', url_1
r_1 = self.get(url_1)
# print r_1.text
# print r_1.text[len('geetest_%s(' % ts):-1]
if 'data' in json.loads(r_1.text[len('geetest_%s(' % ts):-1]):
path = json.loads(r_1.text[len('geetest_%s(' % ts):-1])['data']['path']
else:
path = json.loads(r_1.text[len('geetest_%s(' % ts):-1])['path']
url_2 = "http://api.geetest.com/get.php?" \
"gt=%s" \
"&challenge=%s" \
"&product=%s" \
"&offline=false" \
"&protocol=" \
"&type=slide" \
"&path=%s" \
"&callback=geetest_%s" % (self.gt, self.challenge, self.geetest_product, path, TimeUtils.get_cur_ts_mil())
# print 'url_2', url_2
r_2 = self.get(url_2, headers={})
# print r_2.text
json_2 = json.loads(r_2.text[r_2.text.find('{'):r_2.text.rfind('}') + 1])
self.s = json_2['s']
self.c = json_2['c']
if 'staticservers' in json_2:
self.static_server = json_2['staticservers'][0]
self.bg_url = 'http://' + self.static_server + json_2['bg']
self.fullbg_url = 'http://' + self.static_server + json_2['fullbg']
self.slice_url = 'http://' + self.static_server + json_2['slice']
self.challenge = json_2['challenge']
elif 'static_servers' in json_2:
self.static_server = json_2['static_servers'][0]
self.bg_url = 'http://' + self.static_server + json_2['bg']
self.fullbg_url = 'http://' + self.static_server + json_2['fullbg']
self.slice_url = 'http://' + self.static_server + json_2['slice']
self.challenge = json_2['challenge']
else:
self.session.cookies.clear(domain='api.geetest.com')
self.get_gt_challenge()
self.load_api()
def info(msg):
try:
print TimeUtils.get_cur_time() + ' ->', msg
except UnicodeEncodeError:
pass
def get_xing_zheng_chu_fa(self):
"""
获取行政处罚信息
:return:
"""
draw = 1
xing_zheng_chu_fa_data = []
while True:
params = {
'draw': draw,
'length': 5,
'start': 5 * (draw - 1),
}
r = self.post_request(self.xing_zheng_chu_fa_url, params=params)
json_obj = json.loads(r.text)
data = json_obj['data']
for item in data:
if not item['illegActType'] and not item['penAuth_CN'] \
and not item['penContent'] and not item['penDecIssDate'] \
and not item['penDecNo']:
continue
xing_zheng_chu_fa_data.append({})
for k in item:
if k in TianJinConfig.xing_zheng_chu_fa_dict:
col = TianJinConfig.xing_zheng_chu_fa_dict[k]
val = item[k]
if type(val) == unicode:
if '<span' in val:
val = re.sub('<span[^<]*</span>', '', val)
if '<div' in val:
val = re.sub('<div[^<]*</div>', '', val)
val = re.sub(r'\s', '', val)
if col in ('penalty_decisiondate',
'penalty_announcedate') and val:
val = TimeUtils.get_date(val)
xing_zheng_chu_fa_data[-1][col] = val
if item['vPunishmentDecision'] and item['vPunishmentDecision'][
'fileName'].endswith('.pdf'):
detail_url = 'http://tj.gsxt.gov.cn/doc/%s/casefiles/%s' % (
item['nodeNum'],
item['vPunishmentDecision']['fileName'])
xing_zheng_chu_fa_data[-1]['penalty_details'] = detail_url
if int(json_obj['draw']) < int(json_obj['totalPage']):
# self.get_xing_zheng_chu_fa(draw + 1, xing_zheng_chu_fa_data)
draw += 1
else:
# print json.dumps(xing_zheng_chu_fa_data, ensure_ascii=False)
family = 'Administrative_Penalty'
table_id = '13'
self.json_result[family] = []
for i in range(len(xing_zheng_chu_fa_data)):
row = xing_zheng_chu_fa_data[i]
self.json_result[family].append({})
self.json_result[family][-1][
'rowkey'] = '%s_%s_%s_%s%d' % (self.cur_mc, table_id,
self.reg_code,
self.today, i + 1)
self.json_result[family][-1][
family + ':registrationno'] = self.reg_code
self.json_result[family][-1][
family + ':enterprisename'] = self.cur_mc
for k in row:
col = family + ':' + k
val = row[k]
self.json_result[family][-1][col] = val
break
def get_gu_quan_chu_zhi(self):
"""
获取股权出质信息
:return:
"""
draw = 1
gu_quan_chu_zhi_data = []
while True:
params = {
'draw': draw,
'length': 5,
'start': 5 * (draw - 1),
}
r = self.post_request(self.gu_quan_chu_zhi_url, params=params)
json_obj = json.loads(r.text)
data = json_obj['data']
for item in data:
gu_quan_chu_zhi_data.append({})
for k in item:
if k in TianJinConfig.gu_quan_chu_zhi_dict:
col = TianJinConfig.gu_quan_chu_zhi_dict[k]
val = item[k]
if type(val) == unicode:
if '<span' in val:
val = re.sub('<span[^<]*</span>', '', val)
if '<div' in val:
val = re.sub('<div[^<]*</div>', '', val)
val = re.sub(r'\s', '', val)
if col == 'equitypledge_status':
if str(val) == '1':
val = u'有效'
else:
val = u'无效'
elif col == 'equitypledge_amount' and val:
if item['pledAmUnit']:
val = str(val) + re.sub(
r'\s', '', item['pledAmUnit'])
else:
val = str(val) + u'万元'
elif col == 'equitypledge_registrationdate' and val:
val = TimeUtils.get_date(val)
gu_quan_chu_zhi_data[-1][col] = val
if int(json_obj['draw']) < int(json_obj['totalPage']):
draw += 1
# self.get_gu_quan_chu_zhi(draw + 1, gu_quan_chu_zhi_data)
else:
# print json.dumps(gu_quan_chu_zhi_data, ensure_ascii=False)
family = 'Equity_Pledge'
table_id = '12'
self.json_result[family] = []
for i in range(len(gu_quan_chu_zhi_data)):
row = gu_quan_chu_zhi_data[i]
self.json_result[family].append({})
self.json_result[family][-1][
'rowkey'] = '%s_%s_%s_%s%d' % (self.cur_mc, table_id,
self.reg_code,
self.today, i + 1)
self.json_result[family][-1][
family + ':registrationno'] = self.reg_code
self.json_result[family][-1][
family + ':enterprisename'] = self.cur_mc
for k in row:
col = family + ':' + k
val = row[k]
self.json_result[family][-1][col] = val
break
def get_gt_challenge(self):
url_1 = 'http://gd.gsxt.gov.cn/aiccips//verify/start.html?t=%s' % TimeUtils.get_cur_ts_mil(
)
r_1 = self.get_request(url_1)
self.challenge = str(json.loads(r_1.text)['challenge'])
def get_gt_challenge(self):
url_1 = "http://www.jsgsj.gov.cn:58888/province/geetestViladateServlet.json?register=true&t=%s" % TimeUtils.get_cur_ts_mil(
)
self.info(u'获取gt和challenge...')
r_1 = self.get_request(url_1)
json_1 = json.loads(r_1.text)
self.gt = json_1['gt']
self.challenge = json_1['challenge']