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
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
| import scrapy
from scrapy.selector import Selector
from scrapy.http import FormRequest
class HotelSpider(scrapy.Spider):
name = 'hotel'
allowed_domains = ['checkhrs.zzzdex.com']
login_url = 'http://checkhrs.zzzdex.com/piston/login'
url = 'http://checkhrs.zzzdex.com/piston/hotel'
start_urls = ['http://checkhrs.zzzdex.com/piston/hotel']
def login(self, response):
fd = {'username':'usernamexxx', 'password':'passwordxxx'}
yield FormRequest.from_response(response,
formdata = fd,
callback = self.parse_login)
def parse_login(self, response):
if 'usernamexxx' in response.text:
print("login success!")
yield from self.start_hotel_list()
else:
print("login fail!")
def start_requests(self):
yield scrapy.Request(self.login_url,
meta = {
},
encoding = 'utf8',
headers = {
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36'
},
dont_filter = True,
callback = self.login)
def start_hotel_list(self):
yield scrapy.Request(self.url,
meta = {
},
encoding = 'utf8',
headers = {
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36'
},
dont_filter = True)
def parse(self, response):
print("parse")
selector = Selector(response)
select_list = selector.xpath('//table//tbody//tr')
for sel in select_list:
address = sel.xpath('.//td[3]/text()').extract_first()
next_url = sel.xpath('.//td//a[text()="编辑"]/@href').extract_first()
next_url = response.urljoin(next_url)
print(next_url)
yield scrapy.Request(next_url,
meta = {
'address': address
},
encoding = 'utf8',
headers = {
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36'
},
dont_filter = True,
callback = self.parseDetail)
totalStr = selector.xpath('//ul[@class="pagination"]//li[last()-1]//text()').extract_first();
print(totalStr)
pageStr = selector.xpath('//ul[@class="pagination"]//li[@class="active"]//text()').extract_first();
print(pageStr)
total = int(totalStr)
print(total)
page = int(pageStr)
print(page)
if page >= total:
print("last page")
else:
next_page = self.url + "?page=" + str(page + 1)
print("continue next page: " + next_page)
yield scrapy.Request(next_page,
meta = {
},
encoding = 'utf8',
headers = {
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36'
},
dont_filter = True)
def parseDetail(self, response):
address = response.meta['address']
print("parseDetail address is " + address)
addresses = address.split('/')
print(addresses)
country = ""
province = ""
city = ""
address_len = len(addresses)
if address_len > 0:
country = addresses[0].strip()
if address_len > 1:
province = addresses[1].strip()
if address_len > 2:
city = addresses[2].strip()
selector = Selector(response)
hotelId = selector.xpath('//input[@id="id"]/@value').extract_first()
group_list = selector.xpath('//form//div[@class="form-group js_group"]')
hotelName = group_list[1].xpath('.//input[@id="hotel_name"]/@value').extract_first()
select_list = selector.xpath('//form//div[contains(@class,"company_container")]')
for sel in select_list:
company_list = sel.xpath('.//div[@class="panel-body"]//div[@class="form-group"]')
companyName = company_list[0].xpath('.//input[@id="company"]/@value').extract_first()
singlePrice = company_list[1].xpath('.//input/@value')[0].extract()
doublePrice = company_list[1].xpath('.//input/@value')[1].extract()
risk = company_list[2].xpath('.//input/@value').extract_first()
remark = company_list[3].xpath('.//input/@value').extract_first()
yield {
'ID': hotelId,
'国家': country,
'省份': province,
'城市': city,
'酒店名': hotelName,
'公司': companyName,
'单早': singlePrice,
'双早': doublePrice,
'风险指数': risk,
'备注': remark
}
|
