西刺代理是一个国内ip代理，由于代理倒闭了，所以我就把原来的代码放出来供大家学习吧。
镜像地址：https://www.blib.cn/url/xcdl.html
首先找到所有的tr标签，与class="odd"的标签，然后提取出来。
然后再依次找到tr标签里面的所有td标签，然后只提取出里面的[1,2,5,9]这四个标签的位置，其他的不提取。
最后可以写出提取单一页面的代码，提取后将其保存到文件中。
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
|
import sys,re,threading
import requests,lxml
from queue import queue
import argparse
from bs4 import beautifulsoup
head = {"user-agent": "mozilla/5.0 (windows nt 10.0; wow64) applewebkit/537.36 (khtml, like gecko) chrome/80.0.3987.100 safari/537.36"}
if __name__ == "__main__":
ip_list=[]
fp = open("spideraddr.json","a+",encoding="utf-8")
url = "https://www.blib.cn/url/xcdl.html"
request = requests.get(url=url,headers=head)
soup = beautifulsoup(request.content,"lxml")
data = soup.find_all(name="tr",attrs={"class": re.compile("|[^odd]")})
for item in data:
soup_proxy = beautifulsoup(str(item),"lxml")
proxy_list = soup_proxy.find_all(name="td")
for i in [1,2,5,9]:
ip_list.append(proxy_list[i].string)
print("[+] 爬行列表: {} 已转存".format(ip_list))
fp.write(str(ip_list) + '\n')
ip_list.clear()
|
爬取后会将文件保存为 spideraddr.json 格式。
最后再使用另一段代码，将其转换为一个ssr代理工具直接能识别的格式，{'http': 'http://119.101.112.31:9999'}
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
|
import sys,re,threading
import requests,lxml
from queue import queue
import argparse
from bs4 import beautifulsoup
if __name__ == "__main__":
result = []
fp = open("spideraddr.json","r")
data = fp.readlines()
for item in data:
dic = {}
read_line = eval(item.replace("\n",""))
protocol = read_line[2].lower()
if protocol == "http":
dic[protocol] = "http://" + read_line[0] + ":" + read_line[1]
else:
dic[protocol] = "https://" + read_line[0] + ":" + read_line[1]
result.append(dic)
print(result)
|
完整多线程版代码如下所示。
|
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
|
import sys,re,threading
import requests,lxml
from queue import queue
import argparse
from bs4 import beautifulsoup
head = {"user-agent": "mozilla/5.0 (windows nt 10.0; wow64) applewebkit/537.36 (khtml, like gecko) chrome/80.0.3987.100 safari/537.36"}
class agentspider(threading.thread):
def __init__(self,queue):
threading.thread.__init__(self)
self._queue = queue
def run(self):
ip_list=[]
fp = open("spideraddr.json","a+",encoding="utf-8")
while not self._queue.empty():
url = self._queue.get()
try:
request = requests.get(url=url,headers=head)
soup = beautifulsoup(request.content,"lxml")
data = soup.find_all(name="tr",attrs={"class": re.compile("|[^odd]")})
for item in data:
soup_proxy = beautifulsoup(str(item),"lxml")
proxy_list = soup_proxy.find_all(name="td")
for i in [1,2,5,9]:
ip_list.append(proxy_list[i].string)
print("[+] 爬行列表: {} 已转存".format(ip_list))
fp.write(str(ip_list) + '\n')
ip_list.clear()
except exception:
pass
def startthread(count):
queue = queue()
threads = []
for item in range(1,int(count)+1):
url = "https://www.xicidaili.com/nn/{}".format(item)
queue.put(url)
print("[+] 生成爬行链接 {}".format(url))
for item in range(count):
threads.append(agentspider(queue))
for t in threads:
t.start()
for t in threads:
t.join()
# 转换函数
def conversionagentip(filename):
result = []
fp = open(filename,"r")
data = fp.readlines()
for item in data:
dic = {}
read_line = eval(item.replace("\n",""))
protocol = read_line[2].lower()
if protocol == "http":
dic[protocol] = "http://" + read_line[0] + ":" + read_line[1]
else:
dic[protocol] = "https://" + read_line[0] + ":" + read_line[1]
result.append(dic)
return result
if __name__ == "__main__":
parser = argparse.argumentparser()
parser.add_argument("-p","--page",dest="page",help="指定爬行多少页")
parser.add_argument("-f","--file",dest="file",help="将爬取到的结果转化为代理格式 spideraddr.json")
args = parser.parse_args()
if args.page:
startthread(int(args.page))
elif args.file:
dic = conversionagentip(args.file)
for item in dic:
print(item)
else:
parser.print_help()
|
以上就是python多线程爬取西刺代理的示例代码的详细内容，更多关于python多线程爬取代理的资料请关注服务器之家其它相关文章！
原文链接：https://www.cnblogs.com/LyShark/p/13850457.html