Repository navigation
Expand file tree
/
Copy pathgetinfo.py
More file actions
56 lines (47 loc) · 1.54 KB
/
Copy pathgetinfo.py
File metadata and controls
56 lines (47 loc) · 1.54 KB
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
#!/bin/env python
# -*- coding:utf-8 -*-
# _author:kaliarch
import re
import requests
from bs4 import BeautifulSoup
class Getinformation:
def __init__(self):
"""init url"""
self.init_url = 'http://www.xaglkp.com/ClassSearch/IndexPost'
def getsoup(self):
""":return soup"""
response = requests.post(self.init_url)
soup = BeautifulSoup(response.text, 'html.parser')
return soup
def getStartAddress(self,soup):
"""get start address dict"""
staraddress = soup.find_all('option', text=re.compile("\w+客运站"))
num_list = [1000]
add_list = ["全部"]
for num in staraddress:
num_list.append(num['value'])
add_list.append(num.text)
startaddrdict = dict(zip(add_list, num_list))
return startaddrdict
def getStartDate(self,soup):
"""get time"""
date = soup.find_all('option', text=re.compile("2018.*?"))
date_list = []
for num in date:
date_list.append(num.text)
return date_list
def getStartTime(self,soup):
"""
get start time
:return start time list
"""
times = soup.find_all('option', text=re.compile("\w.*?后"))
time_list = ['05:00后']
for num in times:
time_list.append(num.text)
return time_list
if __name__ == '__main__':
test = Getinformation()
soup = test.getsoup()
add = test.getStartAddress(soup)
print(add)