python 爬蟲 獲取西刺網免費高匿代理ip
阿新 • • 發佈:2018-12-14
import chardet import requests from scrapy.selector import Selector import random from telnetlib import Telnet ip_list = [] def getData(url): 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", ] #獲取網頁內容 html = requests.get(url,headers={'User-Agent':random.choice(user_agent)}) code = chardet.detect(html.content)['encoding'] html.encoding=code selector = Selector(text=html.text) #三種網頁內容選擇方法 parent = selector.xpath('//table[@id="ip_list"]') #parent = soup.find('table',id='ip_list') #parent = selector.css('#ip_list')[0] trs = parent.xpath('//tr') trs.pop(0) for each in trs: ip = each.xpath('./td[2]/text()').extract()[0] port = each.xpath('./td[3]/text()').extract()[0] type = each.xpath('./td[6]/text()').extract()[0] servive = each.xpath('./td[9]/text()').extract()[0] if '分' in servive or '秒' in servive: continue ip_list.append([ip,port,type,servive]) #驗證ip是否可用 print("一共有",len(ip_list),"個待驗證") for i,each in enumerate(ip_list): try: print("正在驗證",i+1,"個ip:",each[0]+':'+each[1]) Telnet(each[0],each[1],timeout=0) print("第", i + 1, "個ip可用") except: print("第",i+1,"個ip不可用") ip_list.remove(each) #拼接成scrapy可用的列表 ips1=[] ips2=[] def for_requests(ip_list): for each in ip_list: if each[2]=='HTTP': ips1.append(each[0]+':'+each[1]) else: ips2.append(each[0]+':'+each[1]) #多頁爬取 def main(n): for index in range(1,n+1): url = 'http://www.xicidaili.com/nn/'+str(index) print("正在爬取第" + str(index) + "頁") getData(url) for_requests(ip_list) ips3 = zip(ips1, ips2) lis1 = list(ips3) lis2 = [] for i in lis1: dict1 = {'HTTP': list(i)[0], 'HTTPS': list(i)[1]} lis2.append(dict1) ip_all = 'ips =' + str(lis2) ip_all = ip_all.replace('},', '},\n') print(ip_all) # 儲存 with open('ip_all.txt', 'w', encoding='utf-8')as f: f.write(ip_all) main(3)