def get_house_info(self, house_url_list):
for i in house_url_list:
try:
dongid = re.search('dongid=(.*?)&', i).group(1)
roomid = re.search('roomid=(.*?)&', i).group(1)
house_url = 'http://zjjg.0557fdc.com:9555/xiaoqu/roominfo.aspx?dongid=' + dongid + '&roomid=' + roomid
house = House(co_index)
house.co_name = 'Labelxqmc">(.*?)<'
house.area = 'Labelxzq">(.*?)<'
house.bu_num = 'Labeldongmc">(.*?)<'
house.ho_type = 'Labelyxyongtu">(.*?)<'
house.ho_name = '<span id="Labelroommc".*?>(.*?)</span>'
house.ho_build_size = 'Labeljzmianji">(.*?)<'
house.ho_true_size = 'Labeltaonei">(.*?)<'
house.ho_share_size = 'Labelgongtan">(.*?)<'
house.ho_room_type = 'Labelhuxing">(.*?)<'
house.bu_id = 'dongid=(.*?)&'
p = ProducerListUrl(page_url=house_url,
request_type='get',
encode='utf-8',
analyzer_rules_dict=house.to_dict(),
analyzer_type='regex',
headers=self.headers)
p.get_details()
except Exception as e:
print('房号错误,co_index={},url={}'.format(co_index, house_url), e)
def get_house_info(self, house_url, bu_id):
response = requests.get('http://thfdc.net/' + house_url, headers=self.headers)
html = response.text
house_info_list = re.findall('<tr onClick=.*?</tr>', html, re.S | re.M)
for i in house_info_list:
try:
house = House(co_index)
house.ho_name = re.search('<td.*?<td.*?>(.*?)<', i, re.S | re.M).group(1)
house.area = re.search('<td.*?<td.*?<td.*?>(.*?)<', i, re.S | re.M).group(1)
house.ho_build_size = re.search('<td.*?<td.*?<td.*?<td.*?<td.*?>(.*?)<', i, re.S | re.M).group(1)
house.ho_type = re.search('<td.*?<td.*?<td.*?<td.*?<td.*?<td.*?<td.*?>(.*?)<', i, re.S | re.M).group(1)
house.bu_id = bu_id
house.insert_db()
except Exception as e:
print('房号错误，co_index={},url={}'.format())
