抓取西刺高匿代理，并验证IP的可用性，存储到本地文件中。
代码如下
# 导入模块
import requests
import chardet
import random
from scrapy.selector import Selector
from telnetlib import Telnet # 这是用来验证IP是否可用
import time
def getXici(url): # 定义一个抓取函数
user_agent = [ # 浏览器头部
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",
"Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0",
"Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; .NET CLR 3.0.30729; .NET CLR 3.5.30729; InfoPath.3; rv:11.0) like Gecko",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
"Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)",
"Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5",
"Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10",
"Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
"Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+",
"Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0",
"Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
"UCWEB7.0.2.37/28/999",
"NOKIA5700/ UCWEB7.0.2.37/28/999",
"Openwave/ UCWEB7.0.2.37/28/999",
"Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
# iPhone 6：
"Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25",
]
html = requests.get(
url,
headers={'User-Agent': random.choice(user_agent)}
)
code = chardet.detect(html.content)['encoding'] # 寻找编码格式
html.encoding = code # 解码
selector = Selector(text=html.text) # 获取的网页内容
parent = selector.css('#ip_list')[0]
trs = parent.xpath('//tr')
trs.pop(0) # 寻找标签
ip_list = []
for each in trs: # 通过循环抓取字段
ip = each.xpath('./td[2]/text()').extract()[0]
port = each.xpath('./td[3]/text()').extract()[0]
ip_type = each.xpath('./td[6]/text()').extract()[0]
ip_time = each.xpath('./td[9]/text()').extract()[0]
if '分' in ip_time or '秒' in ip_time: # 剔除时间为秒和分的IP
continue
ip_list.append([ip, port, ip_type, ip_time])
# 创建一个空列表用来存储可用ip变量
avl_ip = []
print('一共有', len(ip_list), '个待验证')
for i, each in enumerate(ip_list):
time.sleep(1)
try:
# print(each)
print('正在验证第', i + 1, '个ip：', each[0] + ':' + each[1])
Telnet(each[0], each[1], timeout=1)
print(each[0] + ':' + each[1], '可用')
avl_ip.append(each)
except:
print(each[0] + ':' + each[1], '不可用')
# 验证IP是否可用，可用的保存到列表中
return avl_ip
def for_scrapy(avl_ip):
ips = [] # 储存拼接好的IP
# 拼接ip
for each in avl_ip:
eachip = each[2] + '://' + each[0] + ':' + each[1]
ips.append(eachip)
return ips
def save(ips): # 保存自己规定保存的格式
print('正在写入记事本...')
ip_str = 'ips=' + str(ips)
ip_str = ip_str.replace(',', ',\n')
with open('ips.txt', 'a+', encoding='utf-8') as f:
f.write(ip_str)
def main(n): # 主函数调用上面的函数
for i in range(1, n):
url = 'http://www.xicidaili.com/nn/' + str(i) # 每循环一次换一页抓取
avl_ip = getXici(url)
ips = for_scrapy(avl_ip)
save(ips)
if __name__ == '__main__':
main(5) # 爬取前5页ip