def spot_check_execute(self, pageSoup):
br_keyword = ["chouchaxinxi"]
key_list = [
'xuhao', 'authority', 'spot_type', 'spot_date', 'spot_result'
]
dict_ba_list = common.get_dict_list(pageSoup, key_list, br_keyword)
return dict_ba_list
def black_info_execute(self, pageSoup):
key_list = [
'xuhao', 'reason_in', 'date_in', 'reason_out', 'date_out',
'authority', 'xiangqing'
]
br_keyword = ["yanzhongweifaqiye"]
dict_ba_list = common.get_dict_list(pageSoup, key_list, br_keyword)
return dict_ba_list
def stock_freeze_execute(self, pageSoup):
br_keyword = ["EquityFreezeDiv"]
key_list = [
'xuhao', 'person', 'stock', 'court', 'notice_number', 'statues',
'xiangqing'
]
dict_ba_list = common.get_dict_list(pageSoup, key_list, br_keyword)
return dict_ba_list
def stockholder_change_execute(self, pageSoup):
key_list = [
'xuhao', 'person', 'stock', 'person_get', 'court', 'xiangqing'
]
br_keyword = ["xzcfDiv"]
dict_ba_list = []
dict_ba_list = common.get_dict_list(pageSoup, key_list, br_keyword)
if dict_ba_list != []:
raise ValueError("dict_ba_list is not empty.")
else:
return dict_ba_list
def mul_page(pageSoup, page_tag, url_page_part, key_list, dlink, idname,
glb_id):
# 这个只能判断初始的pageSoup中带的翻页tag，如果页数太多的话是不ok的，因为改变后的pageSoup不会找得到的。
'''
id, idname: 针对动产抵押详情页面的翻页情况，key并不等于'mainId'，需要idname传值，key对应的value用id存；
pagelt: page limit, 页数限制边缘值，用于range中，比最大页数大1，初始值为2；
i：结合page_tag，查找是否存在翻页的情况，并将找到的最大值赋值给pagelt，因此从2开始循环查找；
j： 获取翻页html时传data需要用到.
'''
dict_ba_list = []
id = glb_id
url_home = "http://gxqyxygs.gov.cn/"
id = id.split("=")[-1]
pagelt = 2
for i in range(2, 100):
page_i_tag = pageSoup.find(id=page_tag + str(i))
if page_i_tag == None:
pagelt = i # max j is i-1.
break
for j in range(1, pagelt):
url = url_home + url_page_part
if idname != "": # 针对抵押物的翻页
if dlink != "":
a = re.findall("[0-9]+", dlink)
if a != []:
id = a[0]
data = {'pno': str(j), idname: id}
else:
data = {'pno': str(j), 'mainId': id}
pageSoup = get_html(url, data)
if pageSoup != None:
br_keyword = [""]
dict_ba_list_0 = common.get_dict_list(pageSoup, key_list,
br_keyword)
dict_ba_list = dict_ba_list + dict_ba_list_0
return dict_ba_list