利用python爬取新闻并获取新闻内容

 1.获取URL的网页内容

2.利用正则表达式筛选需要的数据

3.将数据保存到excel表中

#coding:gbk
from bs4 import BeautifulSoup                #网页解析，获取数据
import re                                    #正则表达式，进行文字匹配
import urllib.request,urllib.error           #制定URL，获取网页数据
import xlwt                                  #进行excel操作
import http.client



#创建正则表达式对象，表示规则
findlink = re.compile(r'<a href="(.*?)">')                               
findjs = re.compile(r'">(.*)</a>')                                 

def main():
    http.client.HTTPConnection._http_vsn = 10
    http.client.HTTPConnection._http_vsn_str = 'HTTP/1.0'

    a = 1
    #爬取网页，获取数据
    baseurl =  "https://news.163.com/"
    Datelist,a = getDate(baseurl,a)
    #保存数据
    savepath = "新闻.xls"
    saveDate(savepath,Datelist,a)

def getDate(baseurl,a):
    datelist = []
    #for i in range(0,10):
    #    url=baseurl+str(i*25)
        #baseurl+"i*25"
    html = askURL(baseurl)    
    soup = BeautifulSoup(html,"html.parser")
    
    for item in soup.select(".hidden"):                      #查找符合要求的字符串,形成列表
       
        for c in item.select('a'):
            #print(c)
            date=[]
            c=str(c)
            Js=findjs.findall(c)
            date.append(Js)
            Link=findlink.findall(c)
            date.append(Link[0])
            date.append('')
            Html = askURL(Link[0])
            Soup = BeautifulSoup(Html,"html.parser") 
            for item1 in Soup.select(".post_body"):
                date.insert(2,item1.get_text().strip())
                  
            print("已保存第%.3d条新闻数据"%a)
            a+=1
            datelist.append(date)
   
    
    return datelist,a

   

def saveDate(savepath,Datelist,a):
    
    book = xlwt.Workbook(encoding="utf-8",style_compression=0)              #创建workbook对象
    sheet = book.add_sheet(savepath,cell_overwrite_ok=True)                 #创建工作表
    crl=("新闻标题","新闻链接","新闻内容")
    for i in range(0,len(crl)):
        sheet.write(0,i,crl[i])
    for i in range(1,a):
        for j in range(0,len(crl)):
            sheet.write(i,j,Datelist[i-1][j])
    print("保存完毕")
    book.save(savepath)



#得到指定URL的网页内容
def askURL(url):
    head = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36 Edge/18.17763"}
    #模拟浏览器头部信息，向服务器发送消息
    request = urllib.request.Request(url,headers=head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8",'ignore')
        
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)
    return html

if __name__ == "__main__":
    main()