1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
| import requests
from lxml import etree
import time
header = {
'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36 Edg/110.0.1587.69"
}
def get_detail(url):
'''
产权性质
//*[@id="houseInfo"]/table/tbody/tr[1]/td[2]/span[2]/text()
产权年限
//*[@id="houseInfo"]/table/tbody/tr[2]/td[2]/span[2]/text()
房本年限
//*[@id="houseInfo"]/table/tbody/tr[2]/td[3]/span[2]/text()
'''
time.sleep(0.3)
content = requests.get(url=url,headers=header).text
tree = etree.HTML(content)
try:
char = tree.xpath('//*[@id="houseInfo"]/table/tbody/tr[1]/td[2]/span[2]/text()')[0]
except:
char = None
try:
property_right_years = tree.xpath('//*[@id="houseInfo"]/table/tbody/tr[2]/td[2]/span[2]/text()')[0]
except:
property_right_years = None
try:
room_years = tree.xpath('//*[@id="houseInfo"]/table/tbody/tr[2]/td[3]/span[2]/text()')[0]
except:
room_years = None
res = f'{char},{property_right_years},{room_years}'
return res
def data_cat(root):
res = ''
ls = root.xpath('./span/text()')
for i in ls:
res+=i
return res
def get_data(i,fp):
print(f'=======正在爬取第{i}页=========')
time.sleep(1.2)
url = f'https://rizhao.anjuke.com/sale/p{i}/?from=HomePage_TopBar'
contents = requests.get(url=url,headers=header).text
'''
标题
//h3[@class="property-content-title-name"]
价格
//p[@class="property-price-total"]/span[1]/text()
几室几厅
//p[@class="property-content-info-text property-content-info-attribute"]
面积
//p[@class="property-content-info-text"][1]
朝向
//p[@class="property-content-info-text"][2]
楼层
//p[@class="property-content-info-text"][3]
建造年份
//p[@class="property-content-info-text"][4]
地址
//p[@class="property-content-info-comm-address"]
联系人
//span[@class="property-extra-text"][1]
链接
//div[@class="property"]/a/@href
'''
tree = etree.HTML(contents)
titles = tree.xpath('//h3[@class="property-content-title-name"]/text()')
prices = tree.xpath('//p[@class="property-price-total"]/span[1]/text()')
rooms = tree.xpath('//p[@class="property-content-info-text property-content-info-attribute"]')
areas = tree.xpath('//p[@class="property-content-info-text"][1]/text()')
forward = tree.xpath('//p[@class="property-content-info-text"][2]/text()')
floor = tree.xpath('//p[@class="property-content-info-text"][3]/text()')
years = tree.xpath('//p[@class="property-content-info-text"][4]/text()')
address = tree.xpath('//p[@class="property-content-info-comm-address"]')
persons = tree.xpath('//span[@class="property-extra-text"][1]/text()')
links = tree.xpath('//div[@class="property"]/a/@href')
for i in range(len(titles)):
print(f'第{i}个')
print(f'{titles[i].strip()},{prices[i].strip()},{data_cat(rooms[i]).strip()},{areas[i].strip()},{forward[i].strip()},{floor[i].strip()},{years[i].strip()},{data_cat(address[i]).strip()},{persons[i].strip()},{get_detail(links[i].strip())}',file=fp)
get_detail(links[i].strip())
if __name__ == '__main__':
with open('rizhao.txt','a+',encoding='utf-8') as fp:
for i in range(1,11):
get_data(i,fp)
|
