Python爬虫——主题爬取搜狐新闻（步骤及代码实现）

it2024-12-16 13

一、实现思路

本次爬取搜狐新闻时政类

获取url——爬取新闻名称及其超链接——判断与主题契合度——得到最终结果

二、获取url变化规律

观察发现，搜狐新闻页面属于动态页面但是F12——network——XHR下并没有文件所以不能从这里找从ALL中发现该文件中有想要找的内容发现该文件属于js文件观察四个feed开头的文件的url规律 page变化 callback变化无规律最后的数字每页+8 将callback去掉发现对网页内容无影响所以最终的page获取代码采用字符串拼接的形式

for p in range(1,10): p2=1603263206992+p*8 url='https://v2.sohu.com/public-api/feed?scene=CATEGORY&sceneId=1460&page='+str(p)+'&size=20&_='+str(p2)

三、爬取新闻名称及其超链接

本次用正则表达式获取

实现代码：

headers={ 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.75 Safari/537.36', 'cookie':'itssohu=true; BAIDU_SSP_lcr=https://news.hao123.com/wangzhi; IPLOC=CN3300; SUV=201021142102FD7T; reqtype=pc; gidinf=x099980109ee124d51195e802000a3aab2e8ca7bf7da; t=1603261548713; jv=78160d8250d5ed3e3248758eeacbc62e-kuzhE2gk1603261903982; ppinf=2|1603261904|1604471504|bG9naW5pZDowOnx1c2VyaWQ6Mjg6MTMxODgwMjEyODc2ODQzODI3MkBzb2h1LmNvbXxzZXJ2aWNldXNlOjMwOjAwMDAwMDAwMDAwMDAwMDAwMDAwMDAwMDAwMDAwMHxjcnQ6MTA6MjAyMC0xMC0yMXxlbXQ6MTowfGFwcGlkOjY6MTE2MDA1fHRydXN0OjE6MXxwYXJ0bmVyaWQ6MTowfHJlbGF0aW9uOjA6fHV1aWQ6MTY6czExZjVhZTI2NTJiNmM3Nnx1aWQ6MTY6czExZjVhZTI2NTJiNmM3Nnx1bmlxbmFtZTowOnw; pprdig=L2Psu-NwDR2a1BZITLwhlxdvI2OrHzl6jqQlF3zP4z70gqsyYxXmf5dCZGuhPFZ-XWWE5mflwnCHURGUQaB5cxxf8HKpzVIbqTJJ3_TNhPgpDMMQdFo64Cqoay43UxanOZJc4-9dcAE6GU3PIufRjmHw_LApBXLN7sOMUodmfYE; ppmdig=1603261913000000cfdc2813caf37424544d67b1ffee4770' } res=requests.get(url,headers=headers) soup=BeautifulSoup(res.text,'lxml') news=re.findall('"mobileTitle":"(.*?)",',str(soup)) herf=re.findall('"originalSource":"(.*?)"',str(soup)) #news=soup.find_all("div",attrs={'class':'news-wrapper'}) #html=etree.HTML(res.text) #news=html.xpath('/html/body/div[2]/div[1]/div[2]/div[2]/div/div[3]/div[3]/h4/a/text()') news_dic=dict(zip(news,herf))#把标题和链接储存到字典 for k,v in news_dic.items(): news_dictall[k]=v #每一页的字典合并

四、判断与主题的契合度

def ifsim(topicwords): news_dicfin={} news_dic=getdata() ana.set_stop_words('D:\作业\python\文本挖掘\数据集\新闻数据集\data\stopwords.txt') # 输入停用词 for k,v in news_dic.items(): word_list=ana.extract_tags(k,topK=50,withWeight=False) #去除停用词+词频分析 #word_lil.append(word_list) word_lil=[] for i in word_list: word_lil.append([i])#将分词转化为list in list 形式以便传入dictionary word_dic=Dictionary(word_lil)#转化为dictionary词典形式以便分析 d=dict(word_dic.items()) docwords=set(d.values()) #相关度计算 commwords=topicwords.intersection(docwords)#取交集 if len(commwords)>0:#交集>0符合条件的存入最终的字典 news_dicfin[k]=v print(news_dicfin)

若直接输出word_dic结果为： docwords输出结果为：

word_list输出结果： word_lil输出结果为： d的输出结果为：

四、输出结果

本次通过判断标题与我给定主题词的相同的个数即交集>0即判定该词属于主题模型并将其存入最终字典 news_sicfin的输出结果为：

五、总代码

import requests from bs4 import BeautifulSoup import jieba from gensim.corpora.dictionary import Dictionary import re import jieba.analyse as ana def getdata(): #news_all=[] news_dictall={} for p in range(1,10): p2=1603263206992+p*8 url='https://v2.sohu.com/public-api/feed?scene=CATEGORY&sceneId=1460&page='+str(p)+'&size=20&_='+str(p2) headers={ 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.75 Safari/537.36', 'cookie':'itssohu=true; BAIDU_SSP_lcr=https://news.hao123.com/wangzhi; IPLOC=CN3300; SUV=201021142102FD7T; reqtype=pc; gidinf=x099980109ee124d51195e802000a3aab2e8ca7bf7da; t=1603261548713; jv=78160d8250d5ed3e3248758eeacbc62e-kuzhE2gk1603261903982; ppinf=2|1603261904|1604471504|bG9naW5pZDowOnx1c2VyaWQ6Mjg6MTMxODgwMjEyODc2ODQzODI3MkBzb2h1LmNvbXxzZXJ2aWNldXNlOjMwOjAwMDAwMDAwMDAwMDAwMDAwMDAwMDAwMDAwMDAwMHxjcnQ6MTA6MjAyMC0xMC0yMXxlbXQ6MTowfGFwcGlkOjY6MTE2MDA1fHRydXN0OjE6MXxwYXJ0bmVyaWQ6MTowfHJlbGF0aW9uOjA6fHV1aWQ6MTY6czExZjVhZTI2NTJiNmM3Nnx1aWQ6MTY6czExZjVhZTI2NTJiNmM3Nnx1bmlxbmFtZTowOnw; pprdig=L2Psu-NwDR2a1BZITLwhlxdvI2OrHzl6jqQlF3zP4z70gqsyYxXmf5dCZGuhPFZ-XWWE5mflwnCHURGUQaB5cxxf8HKpzVIbqTJJ3_TNhPgpDMMQdFo64Cqoay43UxanOZJc4-9dcAE6GU3PIufRjmHw_LApBXLN7sOMUodmfYE; ppmdig=1603261913000000cfdc2813caf37424544d67b1ffee4770' } res=requests.get(url,headers=headers) soup=BeautifulSoup(res.text,'lxml') news=re.findall('"mobileTitle":"(.*?)",',str(soup)) herf=re.findall('"originalSource":"(.*?)"',str(soup)) #news=soup.find_all("div",attrs={'class':'news-wrapper'}) #html=etree.HTML(res.text) #news=html.xpath('/html/body/div[2]/div[1]/div[2]/div[2]/div/div[3]/div[3]/h4/a/text()') news_dic=dict(zip(news,herf))#把标题和链接储存到字典 for k,v in news_dic.items(): news_dictall[k]=v #每一页的字典合并 return(news_dictall)#返回总字典 def ifsim(topicwords): news_dicfin={} news_dic=getdata() ana.set_stop_words('D:\作业\python\文本挖掘\数据集\新闻数据集\data\stopwords.txt') # 输入停用词 for k,v in news_dic.items(): word_list=ana.extract_tags(k,topK=50,withWeight=False) #去除停用词+词频分析 #word_lil.append(word_list) word_lil=[] for i in word_list: word_lil.append([i])#将分词转化为list in list 形式以便传入dictionary word_dic=Dictionary(word_lil)#转化为dictionary词典形式以便分析 d=dict(word_dic.items()) docwords=set(d.values()) #相关度计算 commwords=topicwords.intersection(docwords)#取交集 if len(commwords)>0:#交集>0符合条件的存入最终的字典 news_dicfin[k]=v print(news_dicfin) if __name__=='__main__': topicwords={"疫情","新冠","肺炎","确诊","病例"} ifsim(topicwords)

最新回复(0)