Python-爬取音悦台MV列表以及反爬虫方法

来源：互联网发布：mac奶瓶粉底液好用吗编辑：程序博客网时间：2024/06/11 13:22

这次比2345电影那个多了一个resource.py文件,里面包含UserAgents,PROXIES,这样我们在爬取时可以写一个函数,随机从这两项中选取,以此绕开反爬虫.

1.目标:音悦台-V榜-MV作品榜
2.所使用的库:

from bs4 import BeautifulSoupimport requestsimport codecs import timeimport resourceimport random

测试环境 Python 3.6.0
3.目标链接
http://vchart.yinyuetai.com/vchart/trends?area=ML&page=2
通过点击图中红圈部分观察后,发现area=后面的和&page=后面的会变化

这里写图片描述

(1)写一个url地址拼接的函数
这样urls列表中就保存了我们想要的链接地址

def getUrls(self):        areas = ['ML','HT','US','KR','JP']        pages =[str(i) for i in range(1,4)]        for area in areas:            urls =[]            for page in pages:                urlEnd = 'area='+area+'&page='+page                url = self.urlBase+urlEnd                urls.append(url)            self.spider(area,urls)

(2)我们再来看一些spider()函数

def spider(self,area,urls):        items = []        for url in urls:            html = self.getResponseContent(url)            if not html:                continue            soup = BeautifulSoup(html,'lxml')            tags = soup.find_all('li',attrs={'name':'dmvLi'})            # tags = soup.find_all('li',attrs={'class','vitem J_li_toggle_date'})            for tag in tags:                item = Item()                item.top_num = tag.find('div',attrs={'class':'top_num'}).get_text()                # if tag.find('h3',attrs={'class':'desc_score'}):                #   item.score = tag.find('h3',attrs={'class':'des_score'}).text()                # else:                #   item.score = tag.find('h3',attrs={'class':'asc_score'}).get_text()                item.mvName = tag.find('img').get('alt')                item.singer = tag.find('a',attrs={'class':'special'}).get_text()                item.releasTime = tag.find('p',attrs={'class':'c9'}).get_text()                items.append(item)        self.sava(items,area)

(3)随机获取UserAgents和PROXIES的函数

def getRandomProxy(self):        return random.choice(resource.PROXIES)    def getRandomHeader(self):        return random.choice(resource.UserAgents)

(4)上面两个函数在获取页面时调用

def getResponseContent(self,url):        fakeHeaders = {'user-agent':self.getRandomHeader()}        proxies = self.getRandomProxy()        try:            r = requests.get(url,headers = fakeHeaders,proxies = proxies,timeout = 30)            r.raise_for_status()            r.encoding = r.apparent_encoding            time.sleep(1)            return r.text            # print(r.text)        except:            return

完整代码以及resource.py

from bs4 import BeautifulSoupimport requestsimport codecs import timeimport resourceimport randomclass Item(object):    top_num = None    score = None    mvName = None    singer = None    releasTime = Noneclass GetMvList(object):    def __init__(self):        self.urlBase = 'http://vchart.yinyuetai.com/vchart/trends?'        self.areasDic = {'ML':'MainLand','HT':'HongKong&Taiwan','US':'Americ','KR':'Korea','JP':'Japan'}        self.getUrls()    def getUrls(self):        areas = ['ML','HT','US','KR','JP']        pages =[str(i) for i in range(1,4)]        for area in areas:            urls =[]            for page in pages:                urlEnd = 'area='+area+'&page='+page                url = self.urlBase+urlEnd                urls.append(url)            self.spider(area,urls)    def getResponseContent(self,url):        fakeHeaders = {'user-agent':self.getRandomHeader()}        proxies = self.getRandomProxy()        try:            r = requests.get(url,headers = fakeHeaders,proxies = proxies,timeout = 30)            r.raise_for_status()            r.encoding = r.apparent_encoding            time.sleep(1)            return r.text            # print(r.text)        except:            return    def spider(self,area,urls):        items = []        for url in urls:            html = self.getResponseContent(url)            if not html:                continue            soup = BeautifulSoup(html,'lxml')            tags = soup.find_all('li',attrs={'name':'dmvLi'})            # tags = soup.find_all('li',attrs={'class','vitem J_li_toggle_date'})            for tag in tags:                item = Item()                item.top_num = tag.find('div',attrs={'class':'top_num'}).get_text()                # if tag.find('h3',attrs={'class':'desc_score'}):                #   item.score = tag.find('h3',attrs={'class':'des_score'}).text()                # else:                #   item.score = tag.find('h3',attrs={'class':'asc_score'}).get_text()                item.mvName = tag.find('img').get('alt')                item.singer = tag.find('a',attrs={'class':'special'}).get_text()                item.releasTime = tag.find('p',attrs={'class':'c9'}).get_text()                items.append(item)        self.sava(items,area)        # print(items[0])    def getRandomProxy(self):        return random.choice(resource.PROXIES)    def getRandomHeader(self):        return random.choice(resource.UserAgents)    def sava(self,items,area):        fileName = 'mvTopList.txt'        nowTime = time.strftime('%Y-%m-%d %H:%M:%S',time.localtime())        with codecs.open(fileName,'w','utf8') as fp:            fp.write('%s --------%s\r\n' %(self.areasDic.get(area),nowTime))            for item in items:                fp.write('%s  \t %s \t %s \t %s \r\n' %(item.top_num,item.releasTime,item.singer,item.mvName))        print('success')if __name__ == '__main__':    GML = GetMvList()

resource.py

#!/usr/bin/env python#-*- coding: utf-8 -*-UserAgents = [  "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",  "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",  "Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",  "Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",  "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",  "Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",  "Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",  "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",  "Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",  "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",  "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",  "Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",  "Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",  "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",  "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",  "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",]PROXIES = ['58.20.238.103:9797','123.7.115.141:9797','121.12.149.18:2226','176.31.96.198:3128','61.129.129.72:8080','115.238.228.9:8080','124.232.148.3:3128','124.88.67.19:80','60.251.63.159:8080','118.180.15.152:8102'    ]

阅读全文

0 0