爬虫代理池数据分析

叁歲伎倆 2022-05-04 07:28 193阅读 0赞

爬取豆瓣《镇魂》评论并进行数据分析

这是引用了一个写得还不错的朋友的博客，感觉会用到下面的处理手段，拿出来和大家分享一下。但是数据分析这块略显的单薄了些，如若自己有更好的分析方法和手段欢迎讨论！

#引入包
    import requests
    from bs4 import BeautifulSoup
    import random
    import matplotlib.pyplot as plt
    import jieba
    from wordcloud import WordCloud
    import PIL
    import numpy as np
    from snownlp import SnowNLP
    import csv
    import codecs
    import pandas as pd

#设置浏览器
    agents = [
        "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:17.0; Baiduspider-ads) Gecko/17.0 Firefox/17.0",
        "Mozilla/5.0 (Linux; U; Android 2.3.6; en-us; Nexus S Build/GRK39F) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
        "Avant Browser/1.2.789rel1 (http://www.avantbrowser.com)",
        "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.5 (KHTML, like Gecko) Chrome/4.0.249.0 Safari/532.5",
        "Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.9 (KHTML, like Gecko) Chrome/5.0.310.0 Safari/532.9",
        "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.7 (KHTML, like Gecko) Chrome/7.0.514.0 Safari/534.7",
        "Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/534.14 (KHTML, like Gecko) Chrome/9.0.601.0 Safari/534.14",
        "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.14 (KHTML, like Gecko) Chrome/10.0.601.0 Safari/534.14",
        "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.20 (KHTML, like Gecko) Chrome/11.0.672.2 Safari/534.20",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.27 (KHTML, like Gecko) Chrome/12.0.712.0 Safari/534.27",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.24 Safari/535.1",
        "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.120 Safari/535.2",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7",
        "Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre",
        "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9b4) Gecko/2008030317 Firefox/3.0b4",
        "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.10) Gecko/2009042316 Firefox/3.0.10",
        "Mozilla/5.0 (Windows; U; Windows NT 6.0; en-GB; rv:1.9.0.11) Gecko/2009060215 Firefox/3.0.11 (.NET CLR 3.5.30729)",
        "Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6 GTB5",
        "Mozilla/5.0 (Windows; U; Windows NT 5.1; tr; rv:1.9.2.8) Gecko/20100722 Firefox/3.6.8 ( .NET CLR 3.5.30729; .NET4.0E)",
        "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",
        "Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
        "Mozilla/5.0 (Windows NT 5.1; rv:5.0) Gecko/20100101 Firefox/5.0",
        "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0a2) Gecko/20110622 Firefox/6.0a2",
        "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:7.0.1) Gecko/20100101 Firefox/7.0.1",
        "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:2.0b4pre) Gecko/20100815 Minefield/4.0b4pre",
        "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0 )",
        "Mozilla/4.0 (compatible; MSIE 5.5; Windows 98; Win 9x 4.90)",
        "Mozilla/5.0 (Windows; U; Windows XP) Gecko MultiZilla/1.6.1.0a",
        "Mozilla/2.02E (Win95; U)",
        "Mozilla/3.01Gold (Win95; I)",
        "Mozilla/4.8 [en] (Windows NT 5.1; U)",
        "Mozilla/5.0 (Windows; U; Win98; en-US; rv:1.4) Gecko Netscape/7.1 (ax)",
        "HTC_Dream Mozilla/5.0 (Linux; U; Android 1.5; en-ca; Build/CUPCAKE) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
        "Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.2; U; de-DE) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/234.40.1 Safari/534.6 TouchPad/1.0",
        "Mozilla/5.0 (Linux; U; Android 1.5; en-us; sdk Build/CUPCAKE) AppleWebkit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
        "Mozilla/5.0 (Linux; U; Android 2.1; en-us; Nexus One Build/ERD62) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
        "Mozilla/5.0 (Linux; U; Android 2.2; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
        "Mozilla/5.0 (Linux; U; Android 1.5; en-us; htc_bahamas Build/CRB17) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
        "Mozilla/5.0 (Linux; U; Android 2.1-update1; de-de; HTC Desire 1.19.161.5 Build/ERE27) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
        "Mozilla/5.0 (Linux; U; Android 2.2; en-us; Sprint APA9292KT Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
        "Mozilla/5.0 (Linux; U; Android 1.5; de-ch; HTC Hero Build/CUPCAKE) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
        "Mozilla/5.0 (Linux; U; Android 2.2; en-us; ADR6300 Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
        "Mozilla/5.0 (Linux; U; Android 2.1; en-us; HTC Legend Build/cupcake) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
        "Mozilla/5.0 (Linux; U; Android 1.5; de-de; HTC Magic Build/PLAT-RC33) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1 FirePHP/0.3",
        "Mozilla/5.0 (Linux; U; Android 1.6; en-us; HTC_TATTOO_A3288 Build/DRC79) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
        "Mozilla/5.0 (Linux; U; Android 1.0; en-us; dream) AppleWebKit/525.10  (KHTML, like Gecko) Version/3.0.4 Mobile Safari/523.12.2",
        "Mozilla/5.0 (Linux; U; Android 1.5; en-us; T-Mobile G1 Build/CRB43) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari 525.20.1",
        "Mozilla/5.0 (Linux; U; Android 1.5; en-gb; T-Mobile_G2_Touch Build/CUPCAKE) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
        "Mozilla/5.0 (Linux; U; Android 2.0; en-us; Droid Build/ESD20) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
        "Mozilla/5.0 (Linux; U; Android 2.2; en-us; Droid Build/FRG22D) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
        "Mozilla/5.0 (Linux; U; Android 2.0; en-us; Milestone Build/ SHOLS_U2_01.03.1) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
        "Mozilla/5.0 (Linux; U; Android 2.0.1; de-de; Milestone Build/SHOLS_U2_01.14.0) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
        "Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/525.10  (KHTML, like Gecko) Version/3.0.4 Mobile Safari/523.12.2",
        "Mozilla/5.0 (Linux; U; Android 0.5; en-us) AppleWebKit/522  (KHTML, like Gecko) Safari/419.3",
        "Mozilla/5.0 (Linux; U; Android 1.1; en-gb; dream) AppleWebKit/525.10  (KHTML, like Gecko) Version/3.0.4 Mobile Safari/523.12.2",
        "Mozilla/5.0 (Linux; U; Android 2.0; en-us; Droid Build/ESD20) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
        "Mozilla/5.0 (Linux; U; Android 2.1; en-us; Nexus One Build/ERD62) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
        "Mozilla/5.0 (Linux; U; Android 2.2; en-us; Sprint APA9292KT Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
        "Mozilla/5.0 (Linux; U; Android 2.2; en-us; ADR6300 Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
        "Mozilla/5.0 (Linux; U; Android 2.2; en-ca; GT-P1000M Build/FROYO) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
        "Mozilla/5.0 (Linux; U; Android 3.0.1; fr-fr; A500 Build/HRI66) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
        "Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/525.10  (KHTML, like Gecko) Version/3.0.4 Mobile Safari/523.12.2",
        "Mozilla/5.0 (Linux; U; Android 1.6; es-es; SonyEricssonX10i Build/R1FA016) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
        "Mozilla/5.0 (Linux; U; Android 1.6; en-us; SonyEricssonX10i Build/R1AA056) AppleWebKit/528.5  (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
    ]

heads = {                                                # ip代理池获取时用的url的headers
            'User-Agent': random.choice(agents),
            'ue': 'utf-8'  # 设置翻译支持中文
        }

# 获取代理ip池,获得匿名的ip
    def get_ip_list():
        urlip = 'http://www.xicidaili.com/nn/'
        html = requests.get(urlip, headers=heads).text
        soup = BeautifulSoup(html, 'html.parser')
        ips = soup.find_all('tr')
        ip_list = []
        for i in range(1, len(ips)):
            ip_info = ips[i]
            tds = ip_info.find_all('td')
            ip_list.append(tds[1].text + ':' + tds[2].text)
        return ip_list
    # 从ip代理池随机选取一个ip返回
    def get_random_ip():
        ip_list = get_ip_list()
        proxy_list = []
        for ip in ip_list:
            proxy_list.append('http://' + ip)
        proxy_ip = random.choice(proxy_list)
        proxies = {'http': proxy_ip}
        return proxies
    #返回的是一个字典

# 用于评论页面html获取的url的headers
    heade = {
            'User-Agent': random.choice(agents),
            'proxies': get_random_ip(),                     # 反爬虫策略——每次从ip池中随机调取一个ip
            'ue': 'utf-8'  # 设置翻译支持中文
        }
    
    # 获取一个评论页面的所有html文本信息
    def get_html(url):
        response = requests.get(url, params=heade)
        response.encoding = 'utf-8'
        html = response.text
        #print(html)
        return html
    
    ## 获取下一页评论区信息的url
    def get_url(html):
        bs = BeautifulSoup(html, 'html.parser')
        url_list = bs.find_all('div', attrs={'id': "paginator"})
        #print(url_list)
        if len(url_list) > 0:
            url_next_part = url_list[0].find('a', attrs={'class': "next"})['href']
            url_next = 'https://movie.douban.com/subject/26979097/comments' + url_next_part
            return url_next
    
    
    #先把表头写好，以便后面构建表格
    
    comment_columns=['标号','评论','星标','地区','时间']
    with codecs.open("D:\\comment4.csv",'ab',"utf-8") as f:
        writer = csv.writer(f,delimiter ='\t',quotechar='"',quoting=csv.QUOTE_ALL)
        writer.writerow(comment_columns)
    
    #b_comment_list里面是逐条的记录
    b_comment_list=[]
    
    # 获取某一页评论每种等级和影评信息
    def get_star_and_comments(url_comment):
        global b_comment_list
        #print(url_comment)
        comment_html = get_html(url_comment)
        bs = BeautifulSoup(comment_html, 'html.parser')
        comment_list = bs.find_all('div', attrs={'class': "comment-item"})
        #print(comment_list)
        star=0
        name=0#表示每一个人的id号
        for comment in comment_list:
            name+=1#这个是用来作为id号码识别对象
            comments = (comment.find('p')).text.strip('\n')
            span = (comment.find_all('span')[4])['class']
            if span[0] == 'allstar50':
                star = 5
            elif span[0] == 'allstar40':
                star=4
            elif span[0] == 'allstar30':
                star=3
            elif span[0] == 'allstar20':
                star=2
            elif span[0] == 'allstar10':
                star=1
            #评论人的个人信息链接
            info_url=(comment.find_all('a')[2])['href']#字符串
            #print(type(info_url))
            info_html=get_html(info_url)
            info_bs=BeautifulSoup(info_html,"html.parser")
            #print(info_bs)
            #地区
            try:
                place=info_bs.find_all('div',attrs={"class":'user-info'})[0].find('a').text.strip()
            except:
                place=''
            #place=info_bs.find_all('div',attrs={"class":'user-info'})[0]
            #print(place)
            #print(type(place))
            #评论日期
            date=comment.find('span',attrs={"class":"comment-time"}).text.strip()
            #print(date)
            #一条数据的表示方法
            b_comment_list.append([name,comments,star,place,date])
            #print("haha:")
            #print(b_comment_list)
            #make_dir(file_path,b_comment_list)
    
    # 创建循环调用实现完成一个页面信息获取后，自动获取下个页面信息的函数，这是一个调用自己的函数
    i=0
    def get_all(url):
        global i
        i+=1
        print(url)  
        get_star_and_comments(url)#把当前页面的内容形成列表放在b_comment_list中    
        comment_url = get_url(get_html(url))
        #print(comment_url)
        if comment_url != None and i%5!=0:        
            get_all(comment_url)
        else:
            pass
    # 主函数运行程序
    if __name__ == '__main__':
        b_comment_list=[]
        file_path='D:\\comment4.csv'#放在c盘中会有权限的限制
        #逐行写入数据
        def make_dir(file_path,data_list):
            with codecs.open(file_path,'ab',"utf-8") as f:
                writer = csv.writer(f,delimiter ='\t',quotechar='"',quoting=csv.QUOTE_ALL)   
                writer.writerows(data_list) # 写入多行
        url = 'https://movie.douban.com/subject/26979097/comments?start=240&limit=20&sort=new_score&status=P'
        get_all(url)#表格构建完成
        make_dir(file_path,b_comment_list)
        #print(b_comment_list)  
    
    #读取形成的.csv文件
    cp=pd.read_csv('D:\comment4.csv',engine='python',delimiter ='\t',sep='"',encoding="utf-8")
    
    comment_list=list(cp["评论"])  
    #file_list是评论列表
    with open('haha.txt',"r",encoding='utf-8') as file:
        file_list=[i.strip() for i in file.readlines() if i!='\n']
    #接下来是情感分析
    def emotion():
        #f = open('comment.txt', 'r', encoding='UTF-8')
        #list = f.readlines()
        sentimentslist = []
        for i in comment_list:
            try:
                s = SnowNLP(i)
                #print(s.sentiments)
                sentimentslist.append(s.sentiments)
            except:
                break
        plt.hist(sentimentslist, bins=np.arange(0, 1, 0.01), facecolor='g')
        plt.xlabel('Value of sentiments')
        plt.ylabel('Quantity')
        plt.title('Sentiments probability of douban')
        plt.show()
    
    
    #####分别构建积极和消极评论的列表，用来分析是什么原因导致产生积极或者消极的评价
    def get_pos_neg_all(comment_list):
        pos_text=''
        neg_text=''
        comment_text=''
        with open('pos.txt', 'w', encoding='utf-8') as pos, open('neg.txt', 'w', encoding='utf-8') as neg,open('comment.txt', 'w', encoding='utf-8') as comment:        
            for i in comment_list:
    
                comment.write(i)
                s=i.strip()
                comment_text+=s
                try:
                    if SnowNLP(s).sentiments>0.5:
                        pos_text+=s
                        pos.write(s)
                    else:
                        neg_text+=s
                        neg.write(s)
                except:
                    continue
        return pos_text,neg_text,comment_text
    
    pos_text,neg_text,comment_text=get_pos_neg_all(comment_list)            
      # 调用wordcloud生成词云图并保存为ipg
    #comment里面是字符串
    def wc(text,name):
        path = r'C:\Windows\Fonts\STXINGKA.TTF'
        alien_mask = np.array(PIL.Image.open(r'C:\Users\ChengYiMing\Desktop\kuang.png')) 
    
        wc = WordCloud(font_path=path, background_color='white', margin=5, mask=alien_mask,width=1800, height=800, max_words=2000, max_font_size=60, random_state=42)
    
        a = []
        words = list(jieba.cut(text))
        for word in words:
            if len(word) > 1:
                a.append(word)
        txt = r' '.join(a)
        wc = wc.generate(txt)
        wc.to_file(name+'.jpg')       
    
    
    wc(pos_text,"pos") 
    wc(pos_text,"pos")

参考文献：   
python爬取豆瓣《狂暴巨兽》评分影评，matplotlib和wordcloud制作评分图和词云图

以下是爬取《镇魂》官微评论数据的过程，最后的分析过程没有写出来，和上面的豆瓣评论分析过程如出一辙，可以参考上面的。

爬取《镇魂》微博数据  
本文皆在于通过爬虫方式爬取微博镇魂。