1. 程式人生 > >python自動投票原始碼(自動爬取更換ip)

python自動投票原始碼(自動爬取更換ip)

import re
import random
import sys
import time
import datetime
import threading
from random import choice
import requests
import bs4
def get_ip():
    """獲取代理IP"""
    url = "http://www.xicidaili.com/nn"
    headers = { "Accept":"text/html,application/xhtml+xml,application/xml;",
                "Accept-Encoding":"gzip, deflate, sdch",
                "Accept-Language":"zh-CN,zh;q=0.8,en;q=0.6",
                "Referer":"http://www.xicidaili.com",
                "User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36"
                }
    r = requests.get(url,headers=headers)
    soup = bs4.BeautifulSoup(r.text, 'html.parser')
    data = soup.table.find_all("td")
    ip_compile= re.compile(r'<td>(\d+\.\d+\.\d+\.\d+)</td>')    # 匹配IP
    port_compile = re.compile(r'<td>(\d+)</td>')                # 匹配埠
    ip = re.findall(ip_compile,str(data))       # 獲取所有IP
    port = re.findall(port_compile,str(data))   # 獲取所有埠
    return [":".join(i) for i in zip(ip,port)]  # 組合IP+埠,如:115.112.88.23:8080
# 設定 user-agent列表,每次請求時,可在此列表中隨機挑選一個user-agnet
uas = [
    "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:17.0; Baiduspider-ads) Gecko/17.0 Firefox/17.0",
    "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9b4) Gecko/2008030317 Firefox/3.0b4",
    "Mozilla/5.0 (Windows; U; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 2.0.50727; BIDUBrowser 7.6)",
    "Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko",
    "Mozilla/5.0 (Windows NT 6.3; WOW64; rv:46.0) Gecko/20100101 Firefox/46.0",
    "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.99 Safari/537.36",
    "Mozilla/5.0 (Windows NT 6.3; Win64; x64; Trident/7.0; Touch; LCJB; rv:11.0) like Gecko",
    ]
def get_url(code=0,ips=[]):
    """
        投票
        如果因為代理IP不可用造成投票失敗,則會自動換一個代理IP後繼續投
    """
    try:
        ip = choice(ips)
    except:
        return False
    else:
        proxies = {
            "http":ip,
        }
        headers2 = { "Accept":"text/html,application/xhtml+xml,application/xml;",
                        "Accept-Encoding":"gzip, deflate, sdch",
                        "Accept-Language":"zh-CN,zh;q=0.8,en;q=0.6",
                        "Referer":"",
                        "User-Agent":choice(uas),
                        }
    try:
        num = random.uniform(0,1)
        hz_url = "http://www.xxxxx.com/xxxx%s" % num   # 某投票網站的地址,這裡不用真實的域名
        hz_r = requests.get(hz_url,headers=headers2,proxies=proxies)
    except requests.exceptions.ConnectionError:
        print "ConnectionError"
        if not ips:
            print "not ip"
            sys.exit()
        # 刪除不可用的代理IP
        if ip in ips:
            ips.remove(ip)
        # 重新請求URL
        get_url(code,ips)
    else:
        date = datetime.datetime.now().strftime('%H:%M:%S')
        print u"第%s次 [%s] [%s]:投票%s (剩餘可用代理IP數:%s)" % (code,date,ip,hz_r.text,len(ips))
ips = []
for i in xrange(6000):
    # 每隔1000次重新獲取一次最新的代理IP,每次可獲取最新的100個代理IP
    if i % 1000 == 0:
        ips.extend(get_ip())
    # 啟用執行緒,隔1秒產生一個執行緒,可控制時間加快投票速度 ,time.sleep的最小單位是毫秒
    t1 = threading.Thread(target=get_url,args=(i,ips))
    t1.start()
    time.sleep(1)