從西刺網獲取可用的代理IP
阿新 • • 發佈：2018-12-17
import requests import chardet import random from scrapy.selector import Selector from telnetlib import Telnet url = 'http://www.xicidaili.com/nn/' user_agent = [ "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", ] proxies = [ {'HTTPS': '116.77.206.56:80', 'HTTP': '116.1.11.19:80'}, {'HTTPS': '106.75.226.36:808', 'HTTP': '106.75.225.83:808'}, {'HTTPS': '175.18.215.50:80', 'HTTP': '61.135.217.7:80'}, {'HTTPS': '175.148.159.199:80', 'HTTP': '118.190.95.35:9001'}, {'HTTPS':'113.74.172.185:33380', 'HTTP':'123.157.67.30:34942'}, {'HTTPS':'111.72.155.7:53128', 'HTTP':'218.71.163.47:80'}, {'HTTPS':'106.75.226.36:808', 'HTTP':'118.190.95.35:9001'}, {'HTTPS':'123.207.237.42:3128','HTTP':'106.75.225.83:808'} ] #獲取網頁內容 html = requests.get( url, headers={'User-Agent':random.choice(user_agent)}, proxies = random.choice(proxies) ) code = chardet.detect(html.content)['encoding'] html.encoding = code selector = Selector(text=html.text) parent = selector.css('#ip_list')[0] trs = parent.xpath('//tr') trs.pop(0) ip_list=[] for each in trs: ip = each.xpath('./td[2]/text()').extract()[0] port = each.xpath('./td[3]/text()').extract()[0] itype = each.xpath('./td[6]/text()').extract()[0] itime = each.xpath('./td[9]/text()').extract()[0] if '分' not in itime or '秒' not in itime: ip_list.append([ip,port,itype,itime]) #驗證ip是否可用 import time avl_ip=[] #儲存可用IP print('一共有',len(ip_list),'個ip待驗證') for i,each in enumerate(ip_list): #time.sleep(1) try: Telnet(each[0],each[1],timeout=1) print("正在驗證第",i+1,"個ip") print(each[0],":",each[1]," 可用") avl_ip.append(each) except: print("正在驗證第", i + 1, "個ip") print(each[0]+':'+each[1],'不可用') #拼接成scrapy可用的列表 #'http://' # def for_scrapy(ip_list): # ips = [] # for i in ip_list: # ips.append(i[2]+'://'+i[0]+':'+i[1]) # return ips # # last_ips = for_scrapy(avl_ip) # print('正在寫入記事本...') # # ip_str = 'ips = '+str(last_ips) # ip_str = ip_str.replace(',',',\n') # with open('ips.txt','w',encoding='utf-8') as f: # f.write(ip_str) def for_requests(ip_list): http1 = [] https1 = [] for i in ip_list: if i[2] =='HTTPS': https1.append([i[0]+':'+i[1]]) else: http1.append([i[0]+':'+i[1]]) ips = [] for m in list(zip(https1,http1)): dict = {'HTTPS':m[0][0],'HTTP':m[1][0]} ips.append(dict) return ips last_ips = for_requests(avl_ip) print(last_ips) print('已寫入記事本') ip_str = 'ips = '+str(last_ips) ip_str = ip_str.replace('},','},\n') with open('ipforrequests.txt','w',encoding='utf-8') as f: f.write(ip_str)