14 得到相关连的热词数据

我根据爬取的链接和热词,进行分析,如果两个词或多个词的文章链接相同,且热词名字不同,那么就爬取对应文章的

内容,根据内容进行分词,得到两个词或多个词的词频,若是差别不大,即可认定两词之间的紧密程度高,同时出现的概率大。
最后就输出到相关文件中,每行为相关的热词。

代码如下

def dbwords_guanxi():
    wordsname = dbgetWordsName()
    set_list = list(set(wordsname))  # 去重
    set_list.sort(key=wordsname.index) #恢复顺序
    yuanzu = dbgetHrefAndWordname()
    print(len(yuanzu))
    #去重后的元组
    yuanzu1 = tuple(set(yuanzu))
    print(len(yuanzu1))
    print(yuanzu1)
    #如果链接相同,热词不同,就得到链接。
    hrefs = []
    hotwords = []
    for row in yuanzu1:
        hrefs.append(row[0])
        hotwords.append(row[1])
    print(hrefs)
    print(hotwords)
    hrefs2 = hrefs
    f = open("ConnectWord.txt", "a+",encoding='utf-8')
    for i in range(0,len(hrefs)):
        for j in range(0,len(hrefs2)):
            #链接相同且热词不同的情况,即为我们所需的第一步条件,两热词初步相关。
            if hrefs[i] == hrefs2[j] and i != j:
                # print(i,j)
                # print(hotwords[i],hotwords[j])
                #得到链接,根据链接爬取文章
                #hrefs[i]
                getContentByHref(hrefs[i],hotwords[i],hotwords[j],f)
def getContentByHref(href,hotword1,hotword2,f):
    print(href,hotword1,hotword2)
    head = {
        'cookie': '_ga=GA1.2.617656226.1563849568; __gads=ID=c19014f666d039b5:T=1563849576:S=ALNI_MZBAhutXhG60zo7dVhXyhwkfl_XzQ; UM_distinctid=16cacb45b0c180-0745b471080efa-7373e61-144000-16cacb45b0d6de; __utmz=226521935.1571044157.1.1.utmcsr=baidu|utmccn=(organic)|utmcmd=organic; __utma=226521935.617656226.1563849568.1571044157.1571044156.1; SyntaxHighlighter=python; .Cnblogs.AspNetCore.Cookies=CfDJ8Nf-Z6tqUPlNrwu2nvfTJEgfH-Wr7LrYHIrX6zFY2UqlCesxMAsEz9JpAIbaPlpJgugnPrXvs5KuTOPnzbk1pa_VZIVlfx1x5ufN55Z8sb63ACHlNKd4JMqI93TE2ONBD5KSWd-ryP2Tq1WfI9e_uTiJIIO9vlm54pfLY0fIReGGtqJkQ5E90ahfHtJeDTgM1RHXRieqriLUIXRciu-3QYwk8x5vLZfJIEUMO5g_seeG6G6FW2kbd6Uw3BfRkkIi-g2O_LSlBqj0DdbJFlNmd-TnPmckz5AENnX9f3SPVVhfmg7zINi4G2SSUcYWSvtVqdUtQ8o9vbBKosXoFOTUNH17VXX_IX8V0ODbs8qQfCkPFaDjS8RWSRkW9KDPOmXyqrtHvRXgGRydee52XJ1N8V-Mu0atT0zMwqzblDj2PDahV1R0Y7nBvzIy8uit15vGtR_r0gRFmFSt3ftTkk63zZixWgK7uZ5BsCMZJdhqpMSgLkDETjau0Qe1vqtLvDGOuBZBkznlzmTa-oZ7D6LrDhHJubRpCICUGRb5SB6WcbaxwOqE1um40OSyila-PgwySA; .CNBlogsCookie=9F86E25644BC936FAE04158D0531CF8F01D604657A302F62BA92F3EB0D7BE317FDE7525EFE154787036095256D48863066CB19BB91ADDA7932BCC3A2B13F6F098FC62FDA781E0FBDC55280B73670A89AE57E1CA5E1269FC05B8FFA0DD6048B0363AF0F08; _gid=GA1.2.1435993629.1581088378; __utmc=66375729; __utmz=66375729.1581151594.2.2.utmcsr=cnblogs.com|utmccn=(referral)|utmcmd=referral|utmcct=/; __utma=66375729.617656226.1563849568.1581151593.1581161200.3; __utmb=66375729.6.10.1581161200'
    }
    r2 = requests.get(href, headers=head)
    html = r2.content.decode("utf-8")
    html1 = etree.HTML(html)
    content1 = html1.xpath('//div[@id="news_body"]')
    #print(content1)
    if len(content1) == 0:
        print("异常")
    else:
        content2 = content1[0].xpath('string(.)')
        # print(content2)
        content = content2.replace('\r', '').replace('\t', '').replace('\n', '').replace(' ', '')
        # print(content)
        fenci(content,hotword1,hotword2,f)
        # f = open("news.txt", "a+", encoding='utf-8')
        # f.write(title + ' ' + content + '\n')
        # &emsp
def fenci(content,hotword1,hotword2,f):
    # mystr = filehandle.read()
    seg_list = jieba.cut(content)  # 默认是精确模式
    #print(seg_list)
    # all_words = cut_words.split()
    # print(all_words)
    stopwords = {}.fromkeys([line.rstrip() for line in open(r'stopwords.txt')])
    c = Counter()
    for x in seg_list:
        if x not in stopwords:
            if len(x) > 1 and x != '\r\n':
                c[x] += 1

    print('\n词频统计结果:')
    # 创建热词文件
    f = open("ConnectWord.txt", "a+", encoding='utf-8')
    number1 = 0
    number2 = 0
    word1=''
    word2=''
    for (k, v) in c.most_common(100):  # 输出词频最高的前两个词
        if k == hotword1 :
            number1 = v
            word1 = k
            #print(number1 ,word1)
        if k == hotword2:
            number2 = v
            word2 = k
            #print(number2, word2)
        #print("%s:%d" % (k, v))
    numbercha = number2 -number1
    if numbercha < 0:
        numbercha = -numbercha
    #print("差值:"+str(numbercha))
    if numbercha <=5 and len(word1)!= 0 and len(word2)!= 0 and number1>3 and number2>3:
        print("有关联")
        # if len(word1) == 0:
        #     word1 =
        print(word1,word2)
        f.write(word1+"\t"+word2+"\n")
            #f.write(k + '\n')

    # print(mystr)
    #filehandle.close();
if __name__=='__main__':
    #热词关系图
    dbwords_guanxi()
View Code

得到的相关联的热词如下:

 

posted @ 2020-02-18 00:27  小神龙1258  阅读(311)  评论(0编辑  收藏  举报