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
| import numpy as np
import requests,re
from bs4 import BeautifulSoup
def names(url):
a = []
b=[]
r = requests.get(url,timeout=30, headers=myHeader)
r.raise_for_status()
r.encoding = 'utf-8'
html = r.text
soup = BeautifulSoup(html, "html.parser")
dt = soup.find_all('a', attrs={'class': 'journal-item cf'})
for i in dt:
a.append('https://you.ctrip.com'+i.get('href'))
for i in a:
if 'nanjing' in i:
b.append(i)
return b
def spans(i,url,count):
try:
a=[]
r = requests.get(url, headers=myHeader)
r.raise_for_status()
r.encoding = 'utf-8'
html = r.text
soup = BeautifulSoup(html, "html.parser")
div=soup.find('div',attrs={'class':'ctd_content_controls cf'})
span1=div.find_all('span')
for i in span1:
a.append(re.sub(u"\\<.*?\\>",'',str(i)))
return a
except Exception as ex:
a=''
print("第{}页{}行出错：{}".format(i,count,ex))
return a
def values(span):
result = []
result1 ='无 '
result2 =result4= ' 无 '
result3 = ' 无 '
result5 = ' '
for i in range(len(span)):
i = re.sub(u"\\<.*?\\>", '', span[i]).replace(' ', '')
if i[0:3] == '天数：':
result1 = i[3:]
if i[0:3] == '时间：':
result2 = i[3:]
if i[0:3] == '人均：':
result3 = i[3:]
if i[0:3] == '和谁：':
result4 = i[3:]
if i[0:3] == '玩法：':
result5 = i[3:].replace('玩法：', '')
result.append(result1)
result.append(result2)
result.append(result3)
result.append(result4)
result.append(result5)
return result
def dls(url):
try:
a = ''
r = requests.get(url, headers=myHeader)
r.raise_for_status()
r.encoding = 'utf-8'
html = r.text
soup = BeautifulSoup(html, "html.parser")
dl1 = soup.find('div', attrs={'class': 'author_poi'})
dd=dl1.find_all('dd')
for i in dd:
a1=i.find('a')
a=a+a1.string+' '
return a
except Exception as ex:
a=' '
return a
def money(all_value):
a=0
j=0
for i in all_value:
if i[2]!=' 无 ':
a=a+int(str(i[2]).replace('元',''))
j+=1
return a/j
def month(all_value):
a=[0,0,0,0,0,0,0,0,0,0,0,0]
s=[]
for i in all_value:
if i[1]!=' 无 ':
a[int(str(i[1]).replace('月',''))-1]+=1
for i in range(len(a)):
if a[i]==np.max(a):
s.append(str(i+1)+'月')
return s
all_value=[]
myHeader = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36'}
for i in range(1,5):
with open("南京游记.txt", 'a+', encoding='utf-8') as file:
file.writelines('第{}页'.format(i))
file.write("\n")
url = "https://you.ctrip.com/travels/nanjing9/t3-p{}.html".format(i)
name=names(url)
count = 0
for j in name:
count+=1
span=spans(i,j,count)
if span!='':
value=values(span)
dl=dls(j)
value.append(dl)
with open("南京游记.txt",'a+',encoding='utf-8') as file:
for k in value:
file.write(k+' ')
file.write('\n')
all_value.append(value)
print(f'第{i}页打印成功')
print('平均花费',money(all_value))
print("推荐月份",month(all_value))
|
