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
|
import requests
from bs4 import BeautifulSoup
import re
import pandas as pd
import os
import time
from threading import Thread
from threading import Lock
import time
def getHTMLText(url):
"""
获取网页
"""
try:
r = requests.get(url, timeout=30)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
return ''
def getPages(infoList, url, pre_params, *args):
"""
获取当前需要爬取的页面数，及完整链接
"""
params = []
count = -1
for i in args:
count += 1
par_ = pre_params[count] + i
params.append(par_)
for param in params:
url += param + '&'
html = getHTMLText(url)
soup = BeautifulSoup(html, 'html.parser')
try:
pages_tag = soup.find_all('td', 'header')[1].string
pages = int(re.split('/', pages_tag)[1])
except:
pages = 0
if pages == 0:
pages += 1
return pages, url
page = 0
lock = Lock()
def getDataInfo(infoList, pages, url):
"""
获取数据信息
"""
global page
while True:
lock.acquire()
page += 1
lock.release()
if page > pages:
break
url = url + '&page=' + str(page)
time.sleep(1)
html = getHTMLText(url)
soup = BeautifulSoup(html, 'html.parser')
tbody = soup.find_all('tbody', 'forum_body_manage')[0]
trs = tbody.find_all('tr')
for tr in trs:
dicts = {}
href = tr.find_all('a')[0].get('href')
tds = tr.find_all('td')
lens = len(tds)
for i in range(lens):
if i == 0:
title = tds[i].find('a').string
dicts[i] = title
else:
dicts[i] = tds[i].string
dicts['href'] = href
print(dicts)
infoList.append(dicts)
def outputCSV(infoList, path):
"""
输出文档
"""
data = pd.DataFrame(infoList)
try:
data.columns = ['标题', '学校', '门类/专业', '招生人数', '发布时间', '链接']
data.sort_values(by='发布时间', ascending=False, inplace=True)
data = data.reset_index(drop=True)
except:
print('没有调剂信息...')
return
try:
if not os.path.exists(path):
data.to_csv(path)
print('爬取成功')
else:
print('路径存在')
except:
print('保存失败')
def parameters(pro_='', pro_1='', pro_2='', year=''):
"""
设定查询参数 -- 专业、年份
"""
paramsList = [pro_, pro_1, pro_2, year]
return paramsList
def threadingUp(count, infoList, pages, url):
"""
启动多线程
"""
threadList = []
iList = []
for i in range(count):
iList.append(i)
t = Thread(target=getDataInfo, args=(infoList, pages, url))
t.start()
threadList.append(t)
for thread in threadList:
thread.join()
def main():
url = 'http://muchong.com/bbs/kaoyan.php?'
path = './08.csv'
pre_params = ['r1%5B%5D=', 'r2%5B%5D=', 'r3%5B%5D=', 'year=']
params = parameters(pro_='08', year='2020')
dataList = []
count = 1000
pages, url_ = getPages(dataList, url, pre_params, *params)
start = time.time()
threadingUp(count, dataList, pages, url_)
outputCSV(dataList, path)
end = time.time()
print('时间:'+str(end - start))
if __name__ == "__main__":
main()
|
