谈谈反爬虫“政策与对策”

写博客，一部分是为了让自己今后能快速地复习之前学过的知识，整理下思路；另一方面是帮助到其他也遇到类似问题的童鞋。但是写博客很难坚持下来，原因嘛，各种各样。但说到底是没有“共鸣”。

高山流水，难觅知音。

其实，建立起写博客的习惯，就是那些点点滴滴的小事：每天看着博客的访问量，点赞数增加；看到自己的文章被别人评论等等。

好了，废话不多说。今天来谈谈关于刷浏览量的问题。虽然这远远的偏离了写博客的初衷，但是了解下这类问题还是不错的，毕竟“技术并不犯法！”。

反（反）爬虫机制

说到反爬虫，不得不说下爬虫了。其实这就是一个概念，爬虫就是将手动完成的事情交给了代码去自动化的实现罢了。而反爬虫就是探查用户是真实用户还是代码的一种手段。而反反爬虫就是针对反爬虫机制的一种手段。

都说“双重否定，表示肯定”，那么爬虫和反反爬虫应该是一样的了。其实不然，表面上行为是一致的，但是实际上反反爬虫做了更多的处理，而不是简单的小爬虫啦。

大体上来讲，反爬虫会从如下几个层面入手：
- header 浏览器的请求头
- User-Agent 用户代理，表明访问源身份的一种方式
- Referer 访问的目标链接是从哪个链接跳转过来的（做防盗链的话，就可以从它入手）
- Host 同源地址判断，用它会很有用
- IP 同一个IP短时多次访问，就很有可能是爬虫，反爬虫会对此做处理。
- 访问频率：短时多次高并发的访问，基本上就是有问题的访问。
上面这几个都是常见的反爬虫措施，当然还有更加高深的机制，比如最恶心的验证码（使用tesseract可以处理较为简单的验证码识别），用户行为分析，等等等等。

既然了解了常见的反爬虫机制，那相对应的进行“政策-对策”实现反反爬虫也就不是那么的没有头绪了。是的，针对上面的限制，我们会有一些对策。

• 针对User-Agent 的，可以整理一些常见的浏览器代理头，每次访问随机使用其中一个就好了。
• 针对IP的，可以使用代理IP嘛
• 针对频率限制的，做下访问间隙做下随机休眠就挺不错的。
• ……

实战

之前我一直是在CSDN上写博客，它的反爬虫机制说实话，做的比较的浅，一方面必要性不是很大，二来做反爬虫经纪上不太划算，估计他们也不愿意在这上面浪费吧。

所以，在CSDN上刷浏览量还是很随意的，说下我的思路。
- 代理IP爬取，验证清洗数据，定期更新。
- 浏览器User-Agent整理，添加访问的随机性。
- 随即休眠策略，日志处理，错误记录，定时重试等。

代理IP处理

# coding: utf8

# @Author: 郭 璞
# @File: proxyip.py                                                                 
# @Time: 2017/10/5                                   
# @Contact: 1064319632@qq.com
# @blog: http://blog.csdn.net/marksinoberg
# @Description: 抓取代理IP，并保存到redis相关的key中
import requests
from bs4 import BeautifulSoup
from redishelper import RedisHelper

class ProxyIP(object):
    """
    抓取代理IP，清洗，验证。
    """
    def __init__(self):
        self.rh = RedisHelper()

    def crawl(self):
        """
        不管是http还是https统统存进去再说。
        """
        # 先处理http模式的代理ip
        httpurl = "http://www.xicidaili.com/nn/"
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36'
        }
        html = requests.get(url=httpurl, headers=headers).text
        soup = BeautifulSoup(html, "html.parser")
        ips = soup.find_all("tr")
        for index in range(1, len(ips)):
            tds = ips[index].find_all('td')
            ip = tds[1].text
            port = tds[2].text
            ipinfo = "{}:{}".format(ip, port)
            if self._check(ip):
                self.rh.sAddAvalibeIp(ipinfo)
            # print(ipinfo)




    def _check(self, ip):
        """
        检测代理IP的有效性
        """
        checkurl = "http://47.94.19.186/common/checkip.php"
        localip = self._getLocalIp()
        # print("Local: {}, proxy: {}".format(localip, ip))
        return False if localip==ip else True

    def _getLocalIp(self):
        """
        获取本机的IP地址, 接口方式不太靠谱，暂时用手工方式在https://www.baidu.com/s?ie=UTF-8&wd=ip 进行手动复制粘贴即可
        """
        return "223.91.239.159"

    def clean(self):
        ips = self.rh.sGetAllAvalibleIps()
        for ipinfo in ips:
            ip, port = ipinfo.split(":")
            if self._check(ip):
                self.rh.sAddAvalibeIp(ipinfo)
            else:
                self.rh.sRemoveAvalibleIp(ipinfo)

    def update(self):
        pass


if __name__ == '__main__':
    pip = ProxyIP()
    # result = pip._check("223.91.239.159", 53281)
    # print(result)
    pip.crawl()
    # pip.clean()

Redis工具类

# coding: utf8

# @Author: 郭 璞
# @File: redishelper.py                                                                 
# @Time: 2017/10/5                                   
# @Contact: 1064319632@qq.com
# @blog: http://blog.csdn.net/marksinoberg
# @Description: 涉及redis的一些操作工具方法

import redis

class RedisHelper(object):
    """
    用于保存爬取到的博客内容链接。
    保存代理IP
    """
    def __init__(self):
        self.articlepool = "redis:set:article:pool"
        self.avalibleips = "redis:set:avalible:ips"
        self.unavalibleips = "redis:set:unavalibe:ips"

        pool = redis.ConnectionPool(host="localhost", port=6379)
        self.redispool = redis.Redis(connection_pool=pool)

    def sAddArticleId(self, articleid):
        """
        添加爬取到的博客id。
        :param articleid:
        :return:
        """
        self.redispool.sadd(self.articlepool, articleid)

    def sRemoveArticleId(self, articleid):
        self.redispool.srem(self.articlepool, articleid)

    def popupArticleId(self):
        return int(self.redispool.srandmember(self.articlepool))

    def sAddAvalibeIp(self, ip):
        self.redispool.sadd(self.avalibleips, ip)
    def sRemoveAvalibeIp(self, ip):
        self.redispool.srem(self.avalibleips, ip)
    def sGetAllAvalibleIps(self):
        return [ip.decode('utf8') for ip in self.redispool.smembers(self.avalibleips)]

    def popupAvalibeIp(self):
        return self.redispool.srandmember(self.avalibleips)

    def sAddUnavalibeIp(self, ip):
        self.redispool.sadd(self.unavalibleips, ip)
    def sRemoveUnavaibleIp(self, ip):
        self.redispool.srem(self.unavalibleips, ip)

csdn博文工具类

# coding: utf8

# @Author: 郭 璞
# @File: csdn.py                                                                 
# @Time: 2017/10/5                                   
# @Contact: 1064319632@qq.com
# @blog: http://blog.csdn.net/marksinoberg
# @Description: 爬取一个博主的全部博客链接工具类以及其他设计到的操作。
import re
import requests
from bs4 import BeautifulSoup

class BlogScanner(object):
    """
    抓取博主id下的所有文章链接id。
    """
    def __init__(self, bloger="marksinoberg"):
        self.bloger = bloger
        # self.blogpagelink = "http://blog.csdn.net/{}/article/list/{}".format(self.bloger, 1)

    def _getTotalPages(self):
        blogpagelink = "http://blog.csdn.net/{}/article/list/{}?viewmode=contents".format(self.bloger, 1)
        html = requests.get(url=blogpagelink).text
        soup = BeautifulSoup(html, "html.parser")
        # 比较hack的操作，实际开发还是不要这么随意的好
        temptext = soup.find('div', {"class": "pagelist"}).find("span").get_text()
        restr = re.findall(re.compile("(\d+).*?(\d+)"), temptext)
        # print(restr)
        pages = restr[0][-1]
        return pages

    def _parsePage(self, pagenumber):
        blogpagelink = "http://blog.csdn.net/{}/article/list/{}?viewmode=contents".format(self.bloger, int(pagenumber))
        html = requests.get(url=blogpagelink).text
        soup = BeautifulSoup(html, "html.parser")
        links = soup.find("div", {"id": "article_list"}).find_all("span", {"class": "link_title"})
        articleids = []
        for link in links:
            temp = link.find("a").attrs['href']
            articleids.append(temp.split("/")[-1])
        # print(len(articleids))
        # print(articleids)
        return articleids

    def get_all_articleids(self):
        pages = int(self._getTotalPages())
        articleids = []
        for index in range(pages):
            tempids = self._parsePage(int(index+1))
            articleids.extend(tempids)
        return articleids



if __name__ == '__main__':
    bs = BlogScanner(bloger="marksinoberg")
    # print(bs._getTotalPages())
    # bs._parsePage(1)
    articleids = bs.get_all_articleids()
    print(len(articleids))
    print(articleids)

Brush工具类

# coding: utf8

# @Author: 郭 璞
# @File: brushhelper.py                                                                 
# @Time: 2017/10/5                                   
# @Contact: 1064319632@qq.com
# @blog: http://blog.csdn.net/marksinoberg
# @Description: 开刷

import requests
import random
import time
from redishelper import RedisHelper


class FakeUserAgent(object):
    """
    搜集到的一些User-Agent，每次popup出不同的ua，减少反爬虫机制的影响。
    更多内容：http://www.73207.com/useragent
    """

    def __init__(self):
        self.uas = [
            "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",
            "JUC (Linux; U; 2.3.7; zh-cn; MB200; 320*480) UCWEB7.9.3.103/139/999",
            "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:7.0a1) Gecko/20110623 Firefox/7.0a1 Fennec/7.0a1",
            "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 (iPhone; U; CPU iPhone OS 3_0 like Mac OS X; en-us) AppleWebKit/420.1 (KHTML, like Gecko) Version/3.0 Mobile/1A542a Safari/419.3",
            "Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_0 like Mac OS X; en-us) AppleWebKit/532.9 (KHTML, like Gecko) Version/4.0.5 Mobile/8A293 Safari/6531.22.7",
            "Mozilla/5.0 (iPad; U; CPU OS 3_2 like Mac OS X; en-us) AppleWebKit/531.21.10 (KHTML, like Gecko) Version/4.0.4 Mobile/7B334b Safari/531.21.10",
            "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)",
            "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36",
            "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.1 Safari/537.36",
            "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10",
            "Mozilla/5.0 (Windows NT 5.1; U; en; rv:1.8.1) Gecko/20061208 Firefox/2.0.0 Opera 9.50",
            "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.57.2 (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2",
            "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36",
            "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER) ",
            "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
            "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.122 UBrowser/4.0.3214.0 Safari/537.36",
            "Mozilla/5.0 (Linux; U; Android 2.2.1; zh-cn; HTC_Wildfire_A3333 Build/FRG83D) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
            "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 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)",
            "Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999",
            "Openwave/ UCWEB7.0.2.37/28/999",
            "NOKIA5700/ UCWEB7.0.2.37/28/999",
            "UCWEB7.0.2.37/28/999",
            "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 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
            "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 (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",
        ]

    def _generateIndexes(self):
        numbers = random.randint(0, len(self.uas))
        indexes = []
        while len(indexes) < numbers:
            temp = random.randrange(0, len(self.uas))
            if temp not in indexes:
                indexes.append(temp)
        return indexes

    def popupUAs(self):
        uas = []
        indexes = self._generateIndexes()
        for index in indexes:
            uas.append(self.uas[index])
        return uas


class Brush(object):
    """
    开刷浏览量
    """

    def __init__(self, bloger="marksinoberg"):
        self.bloger = "http://blog.csdn.net/{}".format(bloger)
        self.headers = {
            'Host': 'blog.csdn.net',
            'Upgrade - Insecure - Requests': '1',
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.110 Safari/537.36',
        }
        self.rh = RedisHelper()

    def getRandProxyIp(self):
        ip = self.rh.popupAvalibeIp()
        proxyip = {}
        ipinfo = "http://{}".format(str(ip.decode('utf8')))
        proxyip['http'] = ipinfo
        # print(proxyip)
        return proxyip


    def brushLink(self, articleid, randuas=[]):
        # http://blog.csdn.net/marksinoberg/article/details/78058279
        bloglink = "{}/article/details/{}".format(self.bloger, articleid)
        for ua in randuas:
            self.headers['User-Agent'] = ua
            timeseed = random.randint(1, 3)
            print("临时休眠: {}秒".format(timeseed))
            time.sleep(timeseed)
            for index in range(timeseed):
                # requests.get(url=bloglink, headers=self.headers, proxies=self.getRandProxyIp())
                requests.get(url=bloglink, headers=self.headers)


if __name__ == '__main__':
    # fua = FakeUserAgent()

    # indexes = [0, 2,5,7]
    # indexes = generate_random_numbers(0, 18, 7)
    # randuas = fua.popupUAs(indexes)
    # randuas = fua.popupUAs()
    # print(len(randuas))
    # print(randuas)

    # print(fua._generateIndexes())

    brush = Brush("marksinoberg")
    # brush.brushLink(78058279, randuas)
    print(brush.getRandProxyIp())

入口

# coding: utf8

# @Author: 郭 璞
# @File: Main.py                                                                 
# @Time: 2017/10/5                                   
# @Contact: 1064319632@qq.com
# @blog: http://blog.csdn.net/marksinoberg
# @Description: 入口

from csdn import *
from redishelper import RedisHelper
from brushhelper import *
import threading

def main():
    rh = RedisHelper()
    bs = BlogScanner(bloger="marksinoberg")
    fua = FakeUserAgent()
    brush = Brush(bloger="marksinoberg")

    counter = 0
    while counter < 12:
        # 开刷
        print("第{}次！".format(counter))
        try:
            uas = fua.popupUAs()
            articleid = rh.popupArticleId()
            brush.brushLink(articleid, uas)
        except Exception as e:
            print(e)
            # 待添加日志处理程序
        counter+=1


if __name__ == '__main__':
    for i in range(280):
        temp = threading.Thread(target=main)
        temp.start()

运行结果

我拿了之前写过的一篇文章做了下测试。
博文链接：http://blog.csdn.net/marksinoberg/article/details/78058279

开刷之前为301个浏览量，简单刷了下之后，访问量为下图：

总结

大致就是这个样子啦，虽然这顶多算个原型，因为代码完成度45%左右。有兴趣的可以加我QQ1064319632， 或者在评论中留下您的建议，大家一起交流，一起学习。